WO2022022384A1 - 车辆运动状态识别方法及装置 - Google Patents

车辆运动状态识别方法及装置 Download PDF

Info

Publication number
WO2022022384A1
WO2022022384A1 PCT/CN2021/107918 CN2021107918W WO2022022384A1 WO 2022022384 A1 WO2022022384 A1 WO 2022022384A1 CN 2021107918 W CN2021107918 W CN 2021107918W WO 2022022384 A1 WO2022022384 A1 WO 2022022384A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
lane
information
trajectory
threshold
Prior art date
Application number
PCT/CN2021/107918
Other languages
English (en)
French (fr)
Inventor
龚胜波
周伟
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP21849900.2A priority Critical patent/EP4180295A4/en
Priority to JP2023506149A priority patent/JP2023536483A/ja
Publication of WO2022022384A1 publication Critical patent/WO2022022384A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • B60W60/00276—Planning or execution of driving tasks using trajectory prediction for other traffic participants for two or more other traffic participants

Definitions

  • the embodiments of the present application relate to the field of automatic driving, and in particular, to a method and device for recognizing a motion state of a vehicle.
  • the vehicle In the field of vehicle automatic driving and assisted driving, the vehicle needs to know the motion status of other vehicles on the road in a timely and accurate manner, such as whether other vehicles are changing lanes, so as to perform path planning, adaptive cruise, And operations such as reasonable deceleration in emergency situations. Therefore, during the driving process of the vehicle, it is necessary to monitor the motion state of other vehicles on the road.
  • the vehicle can collect information such as the turn signals of other vehicles, the lateral distance between other vehicles and the lane lines of the lanes where they are located, the speed and acceleration of other vehicles through sensors, and predict the driving trajectories of other vehicles based on the aforementioned information collected; The vehicle can then identify whether other vehicles are changing lanes based on the predicted driving trajectories of other vehicles.
  • the vehicle can also collect information such as the lane line information of the lane where the other vehicle is located, the lateral distance and heading angle between the other vehicle and the lane line of the lane where the other vehicle is located, and determine the actual driving trajectory of the other vehicle according to the aforementioned information collected. , and then compare the actual driving trajectories of other vehicles with the driving trajectories of vehicles that normally keep the lane in the vehicle driving database. When the distance between the two is greater than a set threshold, it is considered that other vehicles are changing lanes.
  • the embodiments of the present application provide a vehicle motion state identification method and device, which can effectively reduce the sensitivity to the instantaneous kinematic information of other vehicles and reduce misidentification of the motion states of other vehicles when monitoring the motion states of other vehicles.
  • an embodiment of the present application provides a method for recognizing a motion state of a vehicle.
  • the method includes: acquiring first lane information, second lane information, and position information and motion information of a second vehicle; the first lane information is the first lane information.
  • the position information of the second vehicle may be the relative position of the second vehicle relative to the first vehicle, such as relative position coordinates.
  • the position information of the second vehicle may also be the absolute position of the second vehicle.
  • the actual position of the second vehicle may be determined according to the position coordinates of the first vehicle and the relative position coordinates of the second vehicle relative to the first vehicle. (absolute) position coordinates.
  • the motion information of the second vehicle may include kinematic information such as speed, acceleration, and trajectory curvature of the second vehicle.
  • Each predicted driving trajectory corresponds to each type of lane information contained in the second lane information, which means: when the second lane information includes two types of lane information, it can be determined that two predicted driving tracks corresponding to the two types of lane information can be determined. trajectory. When the second lane information includes three types of lane information, three predicted driving trajectories corresponding to the three types of lane information can be determined.
  • the predicted driving that the second vehicle keeps driving in the current lane may be determined accordingly.
  • the predicted driving that the second vehicle keeps driving in the current lane may be determined accordingly.
  • the second lane information may include the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane information of the second adjacent lane of the lane where the second vehicle is located, it may be determined accordingly that the second vehicle has changed.
  • the second lane information includes the lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane information of the second adjacent lane of the lane where the second vehicle is located.
  • the predicted driving trajectory of the second vehicle staying in the current lane, the predicted driving trajectory of the second vehicle changing to the first adjacent lane of the current lane, and the second vehicle changing to the lane can be determined accordingly.
  • the method may be based on the position information and motion information of the second vehicle, as well as the lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the second adjacent lane of the lane where the second vehicle is located. At least two of the lane information of the lane are used to predict the driving trajectory of the second vehicle, and at least two predicted driving trajectories corresponding to the at least two types of lane information described above are obtained.
  • the motion state of the second vehicle relative to the first vehicle can be identified according to the aforementioned at least two predicted travel trajectories and the lane information of the lane where the first vehicle is located, so that the movement of the second vehicle relative to the first vehicle can be monitored
  • the sensitivity to the instantaneous kinematic information of the second vehicle is effectively reduced, and the misrecognition of the motion state of the second vehicle is reduced.
  • the first vehicle may be understood as the self-driving car or the self-driving vehicle
  • the second vehicle may be understood as other vehicles driving on the road relative to the self-vehicle.
  • the determining the motion state of the second vehicle relative to the first vehicle according to the at least two predicted travel trajectories and the first lane information includes: according to the at least two predicted travel trajectories, and each The similarity between the predicted driving trajectory and the historical driving trajectory of the second vehicle is determined, and the target predicted driving trajectory of the second vehicle is determined; according to the target predicted driving trajectory and the first lane information, the movement of the second vehicle relative to the first vehicle is determined state.
  • the target predicted travel trajectory of the second vehicle is determined according to at least two predicted travel trajectories and the similarity between each predicted travel trajectory and the historical travel trajectory of the second vehicle, so that the determined second vehicle
  • the target predicted travel trajectory of the 2nd vehicle is closer to the actual travel trajectory of the second vehicle in the future, thereby improving the accuracy of the subsequent motion state of the second vehicle relative to the first vehicle determined according to the target predicted travel trajectory and the first lane information.
  • the method further includes: acquiring a first lateral coordinate vector of the historical driving trajectory of the second vehicle within the first preset time period; wherein the first lateral coordinate vector is used to indicate the difference between the historical driving trajectory and the lane line of the lane where the second vehicle is located.
  • the first lateral coordinate vector of the historical driving trajectory of the second vehicle within the first preset period includes a plurality of first lateral coordinates of the historical driving trajectory of the second vehicle within the first preset period.
  • the second lateral coordinate vector of the predicted travel trajectory within the second preset period includes a plurality of second lateral coordinates of the predicted travel trajectory within the second preset period.
  • the first preset period may be a period composed of a plurality of consecutive first preset periods, and each first preset period may include at least one first lateral coordinate.
  • the second preset period may be a period composed of multiple consecutive second preset periods, and each second preset period may include at least one second horizontal coordinate.
  • determining the target predicted travel trajectory of the second vehicle according to the at least two predicted travel trajectories and the similarity between each predicted travel trajectory and the historical travel trajectory of the second vehicle including: According to the similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle, predict the similarity between each predicted driving trajectory and the real driving trajectory of the second vehicle; The similarity between the predicted driving trajectory and the real driving trajectory of the second vehicle is determined, and the target predicted driving trajectory of the second vehicle is determined.
  • the similarity between each predicted travel trajectory and the historical travel trajectory of the second vehicle may be normalized to predict the probability of each predicted travel trajectory, which may indicate the similarity between each predicted travel trajectory and the second vehicle.
  • the similarity between the real driving trajectories; the target predicted driving trajectory of the second vehicle is determined according to the at least two predicted driving trajectories and the probability of each predicted driving trajectory.
  • determining the motion state of the second vehicle relative to the first vehicle by predicting the travel trajectory according to the target and the first lane information includes: predicting the travel trajectory according to the target and the first lane information , and determine the minimum lateral distance between the predicted target travel trajectory and the lane line of the lane where the first vehicle is located within a preset longitudinal length. If the minimum lateral distance is greater than the first threshold, it is determined that the motion state of the second vehicle relative to the first vehicle is to keep driving in a different lane from the first vehicle.
  • the motion state of the second vehicle relative to the first vehicle can be determined relative to the magnitude of the first threshold by judging the minimum lateral distance between the target predicted driving trajectory and the lane line of the lane where the first vehicle is located within the preset longitudinal length, relative to the size of the first threshold Whether it is driving in a different lane from the first vehicle.
  • the method further includes: determining, according to the target predicted travel trajectory and the first lane information, a maximum lateral distance between the target predicted travel trajectory and the lane line of the lane where the first vehicle is located within a preset longitudinal length; If the minimum lateral distance is less than the first threshold and the maximum lateral distance is greater than the second threshold, it is determined that the motion state of the second vehicle relative to the first vehicle is to pass through the lane where the first vehicle is located; wherein the second threshold is greater than the first threshold. If the maximum lateral distance is less than the third threshold, it is determined that the motion state of the second vehicle relative to the first vehicle is to keep driving in the same lane as the first vehicle; wherein the third threshold is less than the first threshold.
  • the motion state of the second vehicle relative to the first vehicle is to cut into the lane where the first vehicle is located, or to cut out of the first vehicle the driveway.
  • the relative size of the maximum lateral distance and the second threshold and the third threshold can be further judged. , the motion state of the second vehicle relative to the first vehicle is further refined.
  • the method further includes: acquiring a first longitudinal position corresponding to the minimum lateral distance and a second longitudinal position corresponding to the maximum lateral distance.
  • the minimum lateral distance is less than the first threshold
  • the maximum lateral distance is greater than the third threshold and less than the second threshold
  • a lane where the vehicle is located comprising: if the time when the second longitudinal position appears in the target predicted travel trajectory is earlier than the time when the first longitudinal position occurs, determining that the motion state of the second vehicle relative to the first vehicle is to cut into the lane where the first vehicle is located . If the time when the first longitudinal position appears in the target predicted travel trajectory is earlier than the time when the second longitudinal position appears, it is determined that the motion state of the second vehicle relative to the first vehicle is to cut out of the lane where the first vehicle is located.
  • the motion state of the second vehicle relative to the first vehicle can be distinguished as cut-in Or cut out of the lane where the first vehicle is.
  • the method further includes: acquiring a longitudinal distance between the first longitudinal position and the first end of the preset longitudinal length; wherein the longitudinal distance is the distance between the first longitudinal position and the lane where the first vehicle is located. The distance between the parallel direction of the lane line and the first end of the preset longitudinal length, and the first end of the preset longitudinal length is an end close to the first vehicle. If the longitudinal distance is less than the fourth threshold, it is determined that the motion state of the second vehicle relative to the first vehicle is to cut into the lane of the first vehicle according to the first cut-in state, or cut out of the lane of the first vehicle according to the first cut-out state.
  • the motion state of the second vehicle relative to the first vehicle is to cut into the lane of the first vehicle according to the second cut-in state, or cut out of the lane of the first vehicle according to the second cut-out state.
  • the first in state may be referred to as a tight in state
  • the first out state may be referred to as a tight out state
  • the second switch-in state may be referred to as a normal switch-in state
  • the second switch-out state may be referred to as a normal switch-out state.
  • the first/second cut-in state and the first/second cut-out state may also be referred to by other names.
  • this design can further according to the longitudinal distance between the first longitudinal position and the first end of the preset longitudinal length, relative to the size of the fourth threshold, the motion state of the second vehicle relative to the first vehicle can be changed from cutting into the lane where the first vehicle is located.
  • the refinement is: close entry or normal cut in, or refine the motion state of the second vehicle relative to the first vehicle from cutting out the lane where the first vehicle is located to: close exit or normal cut out.
  • the motion information of the second vehicle includes the lateral speed of the second vehicle; in the said at least two parameters of the second vehicle are determined according to the second lane information and the position information and motion information of the second vehicle Before predicting the travel trajectory, the method further includes: correcting the lateral velocity included in the motion information of the second vehicle according to the average historical lateral velocity of the second vehicle.
  • an embodiment of the present application provides an apparatus for recognizing a motion state of a vehicle.
  • the apparatus includes: an acquisition module configured to acquire first lane information, second lane information, and position information and motion information of a second vehicle; the first lane The information is the lane information of the lane where the first vehicle is located; the second lane information includes the lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the second phase of the lane where the second vehicle is located. At least two of the lane information of adjacent lanes.
  • a prediction module configured to determine at least two predicted travel trajectories of the second vehicle according to the second lane information and the position information and motion information of the second vehicle; each predicted travel trajectory and each lane included in the second lane information information corresponds.
  • the determining module is configured to determine the motion state of the second vehicle relative to the first vehicle according to the at least two predicted travel trajectories and the first lane information.
  • the determining module is specifically configured to determine the target predicted driving of the second vehicle according to the at least two predicted driving trajectories and the similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle Trajectory; determine the motion state of the second vehicle relative to the first vehicle according to the target predicted travel trajectory and the first lane information.
  • the determining module is further configured to obtain a first lateral coordinate vector of the historical driving trajectory of the second vehicle within the first preset period; wherein the first lateral coordinate vector is used to indicate the historical driving trajectory and the The distance vector between the lane lines of the lane where the second vehicle is located; for each predicted driving trajectory: obtain the second lateral coordinate vector of the predicted driving trajectory within the second preset time period, according to the second lateral coordinate vector and the first lateral coordinate vector The coordinate vector determines the similarity between the predicted traveling trajectory and the historical traveling trajectory; wherein, the second lateral coordinate vector is used to indicate the distance vector between the predicted traveling trajectory and the lane line of the lane where the second vehicle is located.
  • the determining module is specifically configured to predict the difference between each predicted driving trajectory and the real driving trajectory of the second vehicle according to the similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle
  • the similarity degree of the second vehicle is determined according to at least two predicted driving trajectories and the similarity between each predicted driving trajectory and the real driving trajectory of the second vehicle, to determine the target predicted driving trajectory of the second vehicle.
  • the determining module is specifically configured to determine, according to the target predicted travel trajectory and the first lane information, the minimum lateral distance between the target predicted travel trajectory and the lane line of the lane where the first vehicle is located within a preset longitudinal length; If the minimum lateral distance is greater than the first threshold, it is determined that the motion state of the second vehicle relative to the first vehicle is to keep driving in a different lane from the first vehicle.
  • the determining module is further configured to determine, according to the target predicted driving trajectory and the first lane information, the maximum lateral distance between the target predicted driving trajectory and the lane line of the lane where the first vehicle is located within a preset longitudinal length; If the minimum lateral distance is less than the first threshold and the maximum lateral distance is greater than the second threshold, the motion state of the second vehicle relative to the first vehicle is determined to be crossing the lane where the first vehicle is located; wherein the second threshold is greater than the first threshold. If the maximum lateral distance is less than the third threshold, it is determined that the motion state of the second vehicle relative to the first vehicle is to keep driving in the same lane as the first vehicle; wherein the third threshold is less than the first threshold.
  • the motion state of the second vehicle relative to the first vehicle is to cut into the lane where the first vehicle is located, or to cut out of the first vehicle the driveway.
  • the determining module is further configured to obtain the first longitudinal position corresponding to the minimum lateral distance and the second longitudinal position corresponding to the maximum lateral distance; when the minimum lateral distance is less than the first threshold, the maximum lateral distance is greater than the third
  • the threshold value is smaller than the second threshold value, if the time when the second longitudinal position appears in the predicted travel trajectory of the target is earlier than the time when the first longitudinal position appears, it is determined that the motion state of the second vehicle relative to the first vehicle is to cut into the first vehicle. Lane; if the first longitudinal position appears earlier than the second longitudinal position in the target predicted travel trajectory, determine that the motion state of the second vehicle relative to the first vehicle is to cut out of the lane where the first vehicle is located.
  • the determining module is further configured to obtain the longitudinal distance between the first longitudinal position and the first end of the preset longitudinal length; wherein the longitudinal distance is the distance between the first longitudinal position and the lane where the first vehicle is located.
  • the distance between the parallel direction of the lane line and the first end of the preset longitudinal length, and the first end of the preset longitudinal length is the end close to the first vehicle; if the longitudinal distance is less than the fourth threshold, determine the second The motion state of the vehicle relative to the first vehicle is to cut into the lane where the first vehicle is located according to the first cut-in state, or cut out of the lane where the first vehicle is located according to the first cut-out state; if the longitudinal distance is greater than the fourth threshold, determine the second The motion state of the vehicle relative to the first vehicle is to cut into the lane where the first vehicle is located according to the second cut-in state, or cut out of the lane where the first vehicle is located according to the second cut-out state.
  • the motion information of the second vehicle includes the lateral speed of the second vehicle; the prediction module is further configured to, according to the average historical lateral speed of the second vehicle, analyze the lateral speed included in the motion information of the second vehicle Make corrections.
  • an embodiment of the present application further provides a vehicle motion state identification device, including: an interface circuit, configured to receive data transmitted by other devices; a processor, connected to the interface circuit and configured to execute the first aspect or any possible possibility thereof method described in the design.
  • an embodiment of the present application provides a vehicle, including: a processor, where the processor is configured to be connected to a memory and call a program stored in the memory to execute the method described in the first aspect or any possible design thereof .
  • an embodiment of the present application provides a server, including: a processor, where the processor is configured to be connected to a memory and call a program stored in the memory to execute the method described in the first aspect or any possible design thereof .
  • the embodiments of the present application provide a vehicle driving system, which may be an automatic driving system or an assisted driving system, including: a processor, where the processor is configured to be connected to a memory and call a program stored in the memory to execute the program as described in the first step.
  • an embodiment of the present application provides a computer-readable storage medium, comprising: computer software instructions; when the computer software instructions are executed in the vehicle motion state identification device or a chip built into the vehicle motion state identification device, the computer software instructions cause the vehicle to move.
  • the state recognition device performs the method as described in the first aspect or any possible design thereof.
  • an embodiment of the present application further provides a computer program product, which can implement the method described in any one of the first aspect or the possible designs of the first aspect when the computer program product is executed.
  • an embodiment of the present application further provides a chip system, where the chip system is applied to a vehicle, or a server, or a driving system, and the chip system includes one or more interface circuits and one or more processors; the interface circuit and The processors are interconnected by wires; the processors receive and execute computer instructions from the memory of the electronic device through the interface circuit to implement the method as described in any one of the first aspect or possible designs of the first aspect.
  • FIG. 1 shows a schematic diagram of an application scenario provided by an embodiment of the present application
  • FIG. 2 shows a schematic diagram of the change of the motion state of the vehicle 2 relative to the vehicle 1;
  • FIG. 3 shows a schematic diagram of the change of the motion state of the vehicle 4 relative to the vehicle 1;
  • FIG. 4 shows a schematic diagram of vehicle A identifying the motion state of vehicle B by predicting the driving trajectory of vehicle B;
  • Fig. 5 shows another schematic diagram of vehicle A identifying the motion state of vehicle B by predicting the running track of vehicle B;
  • Fig. 6 shows a schematic diagram of vehicle A identifying the motion state of vehicle B by comparing the driving trajectories of vehicles that normally keep driving in the lane in the vehicle driving database;
  • FIG. 7 shows another schematic diagram of vehicle A identifying the motion state of vehicle B by comparing the driving trajectories of vehicles that normally keep driving in the lane in the vehicle driving database;
  • FIG. 8 shows a schematic diagram of the composition of a vehicle provided by an embodiment of the present application.
  • FIG. 9 shows a schematic flowchart of a vehicle motion state identification method provided by an embodiment of the present application.
  • FIG. 10 shows another schematic flowchart of the vehicle motion state identification method provided by the embodiment of the present application.
  • FIG. 11 shows a schematic diagram of identifying the motion state of vehicle B by vehicle A according to the target predicted travel trajectory of vehicle B according to an embodiment of the present application
  • FIG. 12 shows another schematic diagram of vehicle A identifying the motion state of vehicle B according to the target predicted travel trajectory of vehicle B according to an embodiment of the present application
  • FIG. 13 shows another schematic diagram of vehicle A identifying the motion state of vehicle B according to the target predicted travel trajectory of vehicle B according to an embodiment of the present application
  • FIG. 14 shows another schematic diagram of vehicle A identifying the motion state of vehicle B according to the target predicted travel trajectory of vehicle B according to an embodiment of the present application
  • FIG. 15 shows another schematic diagram of vehicle A identifying the motion state of vehicle B according to the target predicted travel trajectory of vehicle B according to an embodiment of the present application
  • FIG. 16 shows another schematic diagram of vehicle A identifying the motion state of vehicle B according to the target predicted travel trajectory of vehicle B according to an embodiment of the present application
  • FIG. 17 shows another schematic diagram of vehicle A identifying the motion state of vehicle B according to the target predicted travel trajectory of vehicle B according to an embodiment of the present application
  • FIG. 18 shows a schematic structural diagram of a vehicle motion state identification device provided by an embodiment of the present application.
  • FIG. 1 shows a schematic diagram of an application scenario provided by an embodiment of the present application.
  • the application scenario of the embodiment of the present application may include multiple vehicles driving on the road.
  • Four vehicles are exemplarily shown in FIG. 1 , including: vehicle 1 , vehicle 2 , vehicle 3 and vehicle 4 .
  • Different vehicles may drive in different lanes, for example: vehicle 1 drives in lane 1, vehicle 2 drives in lane 2, vehicle 3 drives in lane 3, and so on.
  • different vehicles may also drive in the same lane, for example, vehicle 1 and vehicle 4 drive together in lane 1.
  • FIG. 2 shows a schematic diagram of the change of the motion state of the vehicle 2 relative to the vehicle 1 .
  • vehicle 2 may cut into the lane where vehicle 1 is located, for example, cut into lane 1 from lane 2 .
  • the vehicle 1 needs to monitor the change of the motion state of the vehicle 2 in time, so as to plan the path of the vehicle and decelerate reasonably.
  • FIG. 3 shows a schematic diagram of the change of the motion state of the vehicle 4 relative to the vehicle 1 .
  • vehicle 4 may cut out from the lane where vehicle 1 is located to other lanes, such as: cut out from lane 1 to lane 2.
  • the vehicle 1 also needs to monitor the change of the motion state of the vehicle 4 in time to plan the path of the vehicle.
  • the methods of monitoring the motion state of other vehicles usually include the following two.
  • the vehicle can collect information such as the turn signals of other vehicles, the lateral distance between the other vehicles and the lane line of the lane where they are located, the speed and acceleration of other vehicles, etc. Driving trajectories; the vehicle can then identify whether other vehicles are changing lanes based on the predicted driving trajectories of other vehicles.
  • FIG. 4 shows a schematic diagram of vehicle A identifying the motion state of vehicle B by predicting the traveling trajectory of vehicle B.
  • vehicle A when vehicle A recognizes that vehicle B will drive out of its lane and enter other lanes according to the predicted travel trajectory of vehicle B, it can be considered that vehicle B may change lanes.
  • FIG. 5 shows another schematic diagram of vehicle A identifying the motion state of vehicle B by predicting the traveling trajectory of vehicle B.
  • vehicle A may recognize that vehicle B will change lanes according to the predicted driving trajectory of vehicle B, but in fact Vehicle B may continue to drive in the original lane, thus causing vehicle A to misidentify the motion state of vehicle B.
  • the vehicle can collect information such as the lane line information of the lane where the other vehicle is located, the lateral distance and the heading angle between the other vehicle and the lane line of the lane where the other vehicle is located through the sensor, and determine the information of the other vehicle according to the collected aforementioned information.
  • the actual driving trajectories, and then, the actual driving trajectories of other vehicles are compared with the driving trajectories of vehicles that normally keep their lanes in the vehicle driving database. When the distance between the two is greater than a set threshold, it is considered that other vehicles are changing lanes. .
  • FIG. 6 shows a schematic diagram of vehicle A identifying the motion state of vehicle B by comparing the driving trajectories of vehicles that normally keep driving in the lane in the vehicle driving database.
  • vehicle A recognizes that the distance between the actual driving trajectory of vehicle B and the driving trajectory of the vehicle that normally keeps its lane in the vehicle driving database exceeds a certain threshold, it can be considered that vehicle B may change lanes.
  • Figure 7 shows another schematic diagram of vehicle A's identification of the motion state of vehicle B by comparing the driving trajectories of vehicles that normally keep the lane in the vehicle driving database .
  • the difference between the actual driving trajectory of vehicle B when it is currently offset and the driving trajectory of the vehicle that normally keeps its lane in the vehicle driving database The distance may exceed a certain threshold, and vehicle A may recognize that vehicle B will change lanes, but in fact, vehicle B may continue to drive in the original lane, which will also cause vehicle A to misidentify the motion state of vehicle B.
  • an embodiment of the present application provides a method for identifying a motion state of a vehicle.
  • the lane information of the lane where the other vehicle is located the lane information of the first adjacent lane (such as the left adjacent lane) of the lane where the other vehicle is located, and the second adjacent lane (such as the right adjacent lane) of the lane where the other vehicle is located can be obtained.
  • At least two of the lane information of the adjacent lane and combined with the position information and motion information of other vehicles, predict the driving trajectories of other vehicles, and obtain at least two predicted driving trajectories corresponding to the aforementioned at least two kinds of lane information one-to-one. .
  • the motion state of other vehicles relative to the vehicle can be identified according to the at least two predicted travel trajectories and the lane information of the lane where the vehicle is located. For example, to identify whether other vehicles are changing lanes into the lane of the vehicle.
  • the vehicle motion state identification method may include: acquiring first lane information, second lane information, and position information and motion information of the second vehicle.
  • the first lane information is the lane information of the lane where the first vehicle is located;
  • the second lane information includes the lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane where the second vehicle is located At least two of the lane information of the lane's second adjacent lane.
  • At least two predicted travel trajectories of the second vehicle are determined according to the second lane information and the position information and motion information of the second vehicle, and each predicted travel trajectory corresponds to each type of lane information contained in the second lane information.
  • a motion state of the second vehicle relative to the first vehicle is determined according to the at least two predicted travel trajectories and the first lane information.
  • the second lane information includes the lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane where the second vehicle is located At least two of the lane information of the second adjacent lane, therefore, the position information and motion information of the second vehicle can be combined to determine at least two lane information one-to-one corresponding to each type of lane information contained in the second lane information Predict driving trajectories.
  • the at least two predicted travel trajectories can play a role of mutual correction to each other, thereby reducing the impact on the second vehicle. Sensitivity of instantaneous kinematic information, thereby avoiding misidentification of the motion state of the second vehicle relative to the first vehicle due to instantaneous changes in the kinematic information of the second vehicle.
  • FIG. 8 shows a schematic diagram of the composition of a vehicle provided by an embodiment of the present application.
  • the vehicle may include various subsystems, such as a travel system 102, a sensor system 104, a control system 106, one or more peripherals 108, a power supply 110, a computer system 112, a user interface 116, and the like.
  • the vehicle may also include more or fewer subsystems, and each subsystem may include multiple elements. Additionally, each subsystem and element of the vehicle may be interconnected by wire or wirelessly.
  • the travel system 102 may include components that provide powered motion for the vehicle.
  • travel system 102 may include engine 118 , energy source 119 , transmission 120 , and wheels/tires 121 .
  • the engine 118 may be an internal combustion engine, an electric motor, an air compression engine, or other types of engine combinations, such as a gasoline engine and electric motor hybrid engine, an internal combustion engine and an air compression engine hybrid engine.
  • Engine 118 converts energy source 119 into mechanical energy.
  • Examples of energy sources 119 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity.
  • the energy source 119 may also provide energy to other systems of the vehicle.
  • Transmission 120 may transmit mechanical power from engine 118 to wheels 121 .
  • Transmission 120 may include a gearbox, differential, and driveshafts.
  • transmission 120 may also include other devices, such as clutches.
  • the drive shaft may include one or more axles that may be coupled to one or more wheels 121 .
  • the sensor system 104 may include several sensors that sense information about the environment surrounding the vehicle.
  • the sensor system 104 may include a positioning system 122 (the positioning system 122 may be a GPS system, a Beidou system or other positioning systems), an inertial measurement unit (IMU) 124, a radar 126, a laser rangefinder 128 , and the camera 130 .
  • the sensor system 104 may also include sensors of the vehicle's interior systems, eg, an in-vehicle air quality monitor, a fuel gauge, an oil temperature gauge, and the like. Sensor data from one or more of these sensors can be used to detect objects and their corresponding characteristics (position, shape, orientation, velocity, etc.).
  • the positioning system 122 may be used to estimate the geographic location of the vehicle.
  • the IMU 124 is used to sense position and orientation changes of the vehicle based on inertial acceleration.
  • IMU 124 may be a combination of an accelerometer and a gyroscope.
  • Radar 126 may utilize radio signals to sense objects within the surrounding environment of the vehicle. In some embodiments, in addition to sensing objects, radar 126 may be used to sense the speed and/or heading of objects.
  • the laser rangefinder 128 may utilize laser light to sense objects in the environment in which the vehicle is located.
  • the laser rangefinder 128 may include one or more laser sources, laser scanners, and one or more detectors, among other system components.
  • the camera 130 may be used to capture multiple images of the surrounding environment of the vehicle.
  • Camera 130 may be a still camera or a video camera.
  • the control system 106 is an operating system that controls the vehicle and its components.
  • Control system 106 may include steering system 132 , throttle 134 , braking unit 136 , computer vision system 138 , route control system 140 , and obstacle avoidance system 142 .
  • the steering system 132 is operable to adjust the heading of the vehicle.
  • it may be a steering wheel system.
  • the throttle 134 is used to control the operating speed of the engine 118 and thus the speed of the vehicle.
  • the braking unit 136 is used to control vehicle deceleration.
  • the braking unit 136 may use friction to slow the wheels 121 .
  • the braking unit 136 may convert the kinetic energy of the wheels 121 into electrical current.
  • the braking unit 136 may also take other forms to slow the wheels 121 to control the speed of the vehicle.
  • Computer vision system 138 is operable to process and analyze images captured by camera 130 in order to identify objects and/or features in the environment surrounding the vehicle.
  • the objects and/or features may include traffic signals, road boundaries and obstacles.
  • Computer vision system 138 may use object recognition algorithms, structure from motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, the computer vision system 138 may be used to map the environment, track objects, estimate the speed of objects, and the like.
  • the route control system 140 is used to determine the travel route of the vehicle.
  • the route control system 140 may combine data from the sensors 104 and one or more predetermined maps to determine a driving route for the vehicle.
  • the obstacle avoidance system 142 is used to identify, evaluate and avoid or otherwise overcome potential obstacles in the environment of the vehicle.
  • control system 106 may additionally or alternatively include components other than those shown and described. Alternatively, some of the components shown above may be reduced.
  • Peripherals 108 may include a wireless communication system 146 , an onboard computer 148 , a microphone 150 and/or a speaker 152 .
  • peripherals 108 provide a means for a user of the vehicle to interact with user interface 116 .
  • the onboard computer 148 may provide information to the user of the vehicle 100 .
  • User interface 116 may also operate on-board computer 148 to receive user input.
  • the onboard computer 148 can be operated via a touch screen.
  • the peripherals 108 may provide a means for the vehicle to communicate with other devices located within the vehicle.
  • the microphone 150 may receive audio (eg, voice commands or other audio input) from a user of the vehicle.
  • speakers 152 may output audio to a user of the vehicle.
  • Wireless communication system 146 may wirelessly communicate with one or more devices, either directly or via a communication network.
  • wireless communication system 146 may use 3G cellular communications, such as code division multiple access (CDMA), EVDO, GSM/GPRS, or 4G cellular communications, such as LTE. Or 5G cellular communications.
  • the wireless communication system 146 may communicate with a wireless local area network (WLAN) using WiFi.
  • WLAN wireless local area network
  • the wireless communication system 146 may communicate directly with the device using an infrared link, Bluetooth, or ZigBee.
  • Other wireless protocols, such as various vehicle communication systems, for example, wireless communication system 146 may include one or more dedicated short range communications (DSRC) devices, which may include communication between vehicles and/or roadside stations public and/or private data communications.
  • DSRC dedicated short range communications
  • the power supply 110 may provide power to various components of the vehicle.
  • the power source 110 may be a rechargeable lithium-ion or lead-acid battery.
  • One or more battery packs of such batteries may be configured as a power source to provide power to various components of the vehicle.
  • power source 110 and energy source 119 may be implemented together, such as in some all-electric vehicles.
  • Computer system 112 may include at least one processor 113 that executes instructions 115 stored in a non-transitory computer-readable medium such as memory 114 .
  • Computer system 112 may also be multiple computing devices that control individual components or subsystems of the vehicle in a distributed fashion.
  • the processor 113 may be any conventional processor, such as a commercially available CPU. Alternatively, the processor may be a dedicated device such as an ASIC or other hardware-based processor.
  • FIG. 8 functionally illustrates a processor, memory, one of ordinary skill in the art will understand that the processor or memory may actually include multiple processors or memories that may or may not be stored within the same physical enclosure.
  • the memory may be a hard drive or other storage medium located within a different physical enclosure.
  • a reference to a processor will be understood to include a reference to a collection of processors or memories that may or may not operate in parallel.
  • some components such as the steering and deceleration components may each have their own processor that only performs computations related to component-specific functions .
  • a processor may be located remotely from the vehicle and in wireless communication with the vehicle. In other aspects, some of the processes described herein are performed on a processor disposed within the vehicle while others are performed by a remote processor, including taking steps necessary to perform a single maneuver.
  • memory 114 may contain instructions 11 (eg, program logic) that may be executed by processor 113 to perform various functions of the vehicle, including those described above.
  • the memory 114 may also contain additional instructions, including sending data to, receiving data from, interacting with, and/or controlling one or more of the propulsion system 102 , the sensor system 104 , the control system 106 , and the peripherals 108 . instruction.
  • memory 114 may store data such as road maps, route information, vehicle location, direction, speed, and other such vehicle data, among other information. Such information may be used by the vehicle and computer system 112 during operation of the vehicle in autonomous, semi-autonomous and/or manual modes.
  • a user interface 116 for providing information to or receiving information from a user of the vehicle.
  • the user interface 116 may include one or more input/output devices within the set of peripheral devices 108 , eg, a wireless communication system 146 , an onboard computer 148 , a microphone 150 and a speaker 152 .
  • Computer system 112 may control the functions of the vehicle based on input received from various subsystems (eg, travel system 102 , sensor system 104 , and control system 106 ) and from user interface 116 .
  • computer system 112 may utilize input from control system 106 in order to control steering unit 132 to avoid obstacles detected by sensor system 104 and obstacle avoidance system 144 .
  • computer system 112 is operable to provide control of various aspects of vehicle 100 and its subsystems.
  • one or more of these components described above may be installed or associated with the vehicle separately.
  • the memory 114 may exist partially or completely separate from the vehicle.
  • the above-described components may be communicatively coupled together in a wired and/or wireless manner.
  • the above component is just an example.
  • components in each of the above modules may be added or deleted according to actual needs, and FIG. 8 should not be construed as a limitation on the embodiments of the present application.
  • a self-driving car traveling on a road can recognize objects in its surroundings to determine adjustments to its current speed.
  • the objects may be other vehicles, traffic control equipment, or other types of objects.
  • each identified object may be considered independently, and based on the object's respective characteristics, such as its current speed, acceleration, distance from the vehicle, etc., may be used to determine the speed at which the autonomous vehicle is to adjust.
  • the vehicle or a computing device associated with the vehicle eg, computer system 112, computer vision system 138, processor 113 of FIG. , ice on the road, etc.
  • each identified object is dependent on the behavior of the other, so it is also possible to predict the behavior of a single identified object by considering all identified objects together.
  • the vehicle can adjust its speed based on the predicted behavior of the identified object. In other words, the vehicle can determine what steady state the vehicle will need to adjust to (eg, accelerate, decelerate, or stop) based on the predicted behavior of the object. In this process, other factors may also be considered to determine the speed of the vehicle, such as the lateral position of other vehicles in the road on which they are traveling, the curvature of the road, the proximity of static and dynamic objects, and the like.
  • the vehicle shown in FIG. 8 may be a car, a truck, a motorcycle, a bus, an amusement park vehicle, etc. that have the ability to drive on public roads and highways with or without a driver. Make special restrictions.
  • the vehicle motion state identification method provided in this embodiment of the present application may be applied to the vehicle shown in FIG. 8 , for example, may be executed by a processor in the vehicle, or executed by a computer system.
  • the vehicle motion state identification method provided in the embodiments of the present application may also be applied to a server communicatively connected to the vehicle shown in FIG. 8 , such as a cloud server, which can remotely control the vehicle Unmanned driving. This application does not limit the application subject of the vehicle motion state identification method.
  • FIG. 9 shows a schematic flowchart of the vehicle motion state identification method provided by the embodiment of the present application.
  • S901-S903 may be executed to obtain first lane information, second lane information, and position information and motion information of the second vehicle.
  • the lane information of the lane where the first vehicle is located refers to the track information of the lane center axis of the lane where the first vehicle is located. Taking the vehicle 1 shown in FIG. 1 as the first vehicle as an example, the lane information of the lane where the vehicle 1 is located refers to the trajectory of the lane center axis of the lane 1 (shown by the dotted line in FIG. 1 ).
  • the following describes the process of acquiring the first lane information.
  • the first lane information can be represented by the following curve expression.
  • y ego,t (x) a 3,t x 3 +a 2,t x 2 +a 1,t x+a 0,t .
  • a 3, t represents one-sixth of the curvature change rate of the trajectory of the lane center axis in the first lane information at time t;
  • a 2, t represents the trajectory of the lane center axis in the first lane information at time t 1
  • t represents the tangent slope of the trajectory of the lane center axis in the first lane information at time t;
  • a 0, t represents the trajectory of the lane center axis in the first lane information at time t lateral offset.
  • the lane information of the lane where the first vehicle is located that is, the first lane information can be obtained.
  • S902 Acquire at least two of the lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane information of the second adjacent lane of the lane where the second vehicle is located, as the first Second lane information.
  • the second lane information may include lane information of a lane where the second vehicle is located, and lane information of a first adjacent lane of the lane where the second vehicle is located.
  • the second lane information may include lane information of a lane where the second vehicle is located, and lane information of a second adjacent lane of the lane where the second vehicle is located.
  • the second lane information may include lane information of a first adjacent lane of the lane where the second vehicle is located, and lane information of a second adjacent lane of the lane where the second vehicle is located.
  • the second lane information may include the lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane information of the second adjacent lane of the lane where the second vehicle is located. All three.
  • the lane information of the lane where the second vehicle is located refers to the trajectory information of the lane center axis of the lane where the second vehicle is located
  • the lane information of the first adjacent lane of the lane where the second vehicle is located refers to the first phase of the lane where the second vehicle is located.
  • the track information of the lane center axis of the adjacent lane, and the lane information of the second adjacent lane of the lane where the second vehicle is located refers to the track information of the lane center axis of the second adjacent lane of the lane where the second vehicle is located.
  • the first adjacent lane of the lane (lane 1) where vehicle 4 is located is lane 2
  • the second adjacent lane is lane 3
  • the first adjacent lane is lane 3.
  • the lane is lane 3 and the second adjacent lane is lane 2. That is, the first adjacent lane and the second adjacent lane are the left and right adjacent lanes, which are the lanes where the vehicle 4 is located, respectively.
  • the lane information of lane 1, lane 2, and lane 3 are the trajectories of the corresponding lane axes, respectively.
  • the following describes the process of acquiring the second lane information.
  • the second lane information can be represented by the following curve expression.
  • the lane where the second vehicle is located does not have the first adjacent lane (such as the left lane)
  • the parameter coefficients of i 2,t , bi 1,t , and bi 0,t are all 255. If there is no second adjacent lane (such as the right lane) in the lane where the second vehicle is located, in the above curve expression of the second lane information, when i is equal to 2, the corresponding bi 3,t , bi 2,t ,
  • the parameter coefficients of b i 1,t and b i 0,t are also 255.
  • the locus of the lane center axis of the lane where the second vehicle is located, the locus of the lane center axis of the first adjacent lane of the lane where the second vehicle is located, and the lane of the second adjacent lane of the lane where the second vehicle is located are calculated.
  • the corresponding lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the second adjacent lane of the lane where the second vehicle is located can be obtained.
  • the sensor system (such as: radar, distance sensor, etc.) and positioning system (such as: GPS, Beidou) on the first vehicle can collect the position information and motion information of the second vehicle according to a fixed period, and upload it to the first vehicle.
  • the position information of the second vehicle refers to the position information (x t , y t , ⁇ t ) of the second vehicle at each cycle time t, where x t represents the abscissa of the second vehicle, and y t represents the second vehicle The ordinate, ⁇ t represents the heading angle of the second vehicle.
  • the position information of the second vehicle may be the relative position of the second vehicle relative to the first vehicle, or may be the absolute position of the second vehicle.
  • the motion information of the second vehicle refers to kinematic information such as the velocity v x,t , the acceleration a x,t , and the trajectory curvature ⁇ t of the second vehicle at each periodic time t.
  • the motion state of the second vehicle relative to the first vehicle can be determined through the following S904-S907.
  • S904 Determine at least two predicted travel trajectories of the second vehicle according to the second lane information and the position information and motion information of the second vehicle, each predicted travel trajectory corresponding to each type of lane information contained in the second lane information .
  • the predicted driving that the second vehicle keeps driving in the current lane may be determined accordingly.
  • the predicted driving that the second vehicle keeps driving in the current lane may be determined accordingly.
  • the second lane information may include the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane information of the second adjacent lane of the lane where the second vehicle is located, it may be determined accordingly that the second vehicle has changed.
  • the second lane information includes the lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane information of the second adjacent lane of the lane where the second vehicle is located.
  • the predicted driving trajectory of the second vehicle staying in the current lane, the predicted driving trajectory of the second vehicle changing to the first adjacent lane of the current lane, and the second vehicle changing to the lane can be determined accordingly.
  • the second lane information includes three of the lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane information of the second adjacent lane of the lane where the second vehicle is located All of them are taken as examples, and the specific determination method of the predicted driving trajectory will be described.
  • polynomial fitting can be used to plan the path that the second vehicle keeps driving in the current lane.
  • the four The following equation (or can be referred to as a polynomial fitting model) is obtained by the second-degree polynomial fitting to represent the predicted travel trajectory of the second vehicle keeping and driving in the current lane.
  • the fourth-order polynomial fitting can also be performed according to the position information, kinematic information and road information of the lane to be transformed to arrive at the second vehicle, and the following equation (or can be called a polynomial fitting model) can be obtained to represent the first 2.
  • the above-mentioned polynomial fitting method may not be used, but other fitting functions such as the Bessel function, or extraction based on the driving database, may be used to obtain the predicted driving trajectory of the second vehicle keeping driving in the current lane. , and the predicted driving trajectory of the second vehicle changing lanes to the first adjacent lane or the second adjacent lane of the current lane, which is not limited in this application.
  • S905 and S906 may be executed first, based on the obtained at least two predicted travel trajectories, the target predicted travel trajectory of the second vehicle is determined, and then S907 is executed to predict travel according to the target The trajectory and the first lane information determine the motion state of the second vehicle relative to the first vehicle.
  • a first lateral coordinate vector of the historical driving trajectory of the second vehicle within the first preset time period may be obtained, and the first lateral coordinate vector is used to indicate the distance between the historical driving trajectory and the lane line of the lane where the second vehicle is located. distance vector.
  • each predicted travel trajectory in the at least two predicted travel trajectories obtain a second lateral coordinate vector of the predicted travel trajectory within a second preset time period, where the second lateral coordinate vector is used to indicate the relationship between the predicted travel trajectory and the second
  • the distance vector between the lane lines of the lane where the vehicle is located, and the similarity between the predicted driving trajectory and the historical driving trajectory is determined according to the second lateral coordinate vector and the above-mentioned first lateral coordinate vector, so as to obtain the relationship between each predicted driving trajectory and the historical driving trajectory.
  • the similarity between the historical travel trajectories of the second vehicle obtain a second lateral coordinate vector of the predicted travel trajectory within a second preset time period, where the second lateral coordinate vector is used to indicate the relationship between the predicted travel trajectory and the second
  • the distance vector between the lane lines of the lane where the vehicle is located and the similarity between the predicted driving trajectory and the historical driving trajectory is determined according to the second lateral coordinate vector and the above-mentioned first lateral coordinate vector, so as
  • the first lateral coordinate vector of the historical driving trajectory of the second vehicle within the first preset period includes a plurality of first lateral coordinates of the historical driving trajectory of the second vehicle within the first preset period.
  • the second lateral coordinate vector of the predicted travel trajectory within the second preset period includes a plurality of second lateral coordinates of the predicted travel trajectory within the second preset period.
  • the first preset period may be a period composed of a plurality of consecutive first preset periods, and each first preset period may include at least one first lateral coordinate.
  • the second preset period may be a period composed of multiple consecutive second preset periods, and each second preset period may include at least one second horizontal coordinate.
  • the present application can first determine a first transverse coordinate time series (ie, the aforementioned first transverse coordinate vector) composed of a plurality of first transverse coordinates within the first preset time period of the historical driving trajectory of the second vehicle, and each A second lateral coordinate time series (ie, the aforementioned second lateral coordinate vector) constituted by a plurality of second lateral coordinates within the second preset time period of the predicted driving trajectory. Then, the similarity between the first lateral coordinate time series and the second lateral coordinate time series can be calculated to obtain the similarity between the historical driving trajectory and the predicted driving trajectory of the second vehicle.
  • a first transverse coordinate time series ie, the aforementioned first transverse coordinate vector
  • a second lateral coordinate time series ie, the aforementioned second lateral coordinate vector
  • the first preset period is (t-M ⁇ T, t-(M-1) ⁇ T, ..., t) and other M+1 first preset periods
  • the second preset period is (M+ N+1 second preset periods such as N, M+N-1, M) are taken as an example.
  • the first transverse coordinate time series formed by the first transverse coordinates of the historical driving trajectory within the first preset time period may be expressed as Y t,h as follows.
  • Y t,h (y t-M ⁇ T ,y t-(M-1) ⁇ T ,...,y t ).
  • Y t,h represents the first horizontal coordinate time series
  • y t-M ⁇ T represents the first horizontal coordinate at the time t-M ⁇ T, and so on.
  • the size of M may be 20; the size of N may be 10; ⁇ T is the sampling period, and the size may be an integer multiple of 0.02s.
  • the second lateral coordinate time series formed by the second lateral coordinates of the predicted driving trajectory within the second preset time period may be expressed as Y i t,p as follows.
  • z i N (t-(Mj) ⁇ T) represents the lateral position of the second vehicle when the predicted longitudinal position of the second vehicle at time t-(Mj) ⁇ T is x t-(Mj) ⁇ T .
  • ⁇ i t can be specifically as follows.
  • the value of a j can be obtained by taking the reciprocal of the time difference between the jth cycle corresponding to each a j and the current time t as the initial value of a j and normalizing it, which will not be detailed here. described.
  • the similarity between each of the at least two predicted driving trajectories and the historical driving trajectory of the second vehicle may also be determined by calculating mathematical methods such as cosine similarity, Mahalanobis distance, and Euclidean distance. degree, which is not limited here.
  • determining the target predicted driving trajectory of the second vehicle may refer to: selecting the historical driving trajectory of the second vehicle from at least two predicted driving trajectories A predicted travel trajectory with the highest similarity between them is used as the target predicted travel trajectory of the second vehicle.
  • the target predicted travel trajectory selected in this way is the highest, it is a predicted travel trajectory that is most likely to be close to the actual travel trajectory of the second vehicle in the future among the at least two predicted travel trajectories. trajectory.
  • the The similarity between the historical driving trajectories of the vehicle predict the similarity between each predicted driving trajectory and the real driving trajectory of the second vehicle, and then calculate the similarity between each predicted driving trajectory and the second vehicle according to at least two predicted driving trajectories and each predicted driving trajectory and the second vehicle.
  • the similarity between the real driving trajectories is determined to determine the target predicted driving trajectory of the second vehicle.
  • the similarity between each predicted travel trajectory and the historical travel trajectory of the second vehicle may be normalized to predict the probability of each predicted travel trajectory, which may indicate the similarity between each predicted travel trajectory and the second vehicle. similarity between real driving trajectories. Then, a comprehensive calculation may be performed in combination with the probability of each predicted driving trajectory and the aforementioned at least two predicted driving trajectories to obtain the target predicted driving trajectory of the second vehicle.
  • the predicted driving trajectory of the second vehicle staying in the current lane the predicted driving trajectory of the second vehicle changing to the left lane of the current lane, and the predicted driving trajectory of the second vehicle changing to the right lane of the current lane are used as follows:
  • the three predicted travel trajectories, including the trajectory, illustrate the process of determining the predicted travel trajectory of the target.
  • the target predicted travel trajectory may also be determined according to any two of the aforementioned three predicted travel trajectories, which will not be repeated here.
  • the probability corresponding to the predicted driving trajectory can be initially obtained, which can be expressed as follows
  • the probability corresponding to the predicted travel trajectory of the second vehicle keeping driving in the current lane may be expressed as the following P 0 t .
  • the probability corresponding to the predicted travel trajectory of the second vehicle changing lanes to the left lane of the current lane may be expressed as the following P 1 t .
  • the probability corresponding to the predicted travel trajectory of the second vehicle changing lanes to the right lane of the current lane may be expressed as the following P 2 t .
  • the target predicted travel trajectories can be comprehensively calculated by combining the three predicted travel trajectories.
  • the three predicted driving trajectories may be The minimum value of the probabilities corresponding to the driving trajectories is corrected to 0, so as to further make the determined target predicted driving trajectory closer to the actual driving trajectory, thereby improving the accuracy of subsequent vehicle motion state recognition.
  • the probability corresponding to the predicted driving trajectory of the second vehicle changing lanes to the left is the smallest, it can be corrected to 0, and only according to the predicted driving trajectory of the second vehicle changing lanes to the right and the predicted driving trajectory of keeping the lane, and their corresponding probabilities to determine the target predicted driving trajectory.
  • the similarity between each predicted driving trajectory and the actual driving trajectory of the second vehicle is predicted according to the similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle Afterwards, a predicted running trajectory with the greatest similarity with the actual running trajectory of the second vehicle may also be directly selected as the target predicted running trajectory of the second vehicle.
  • the predicted driving trajectory with the highest probability may be directly selected.
  • the trajectory is used as the target predicted travel trajectory of the second vehicle.
  • This design is similar to the above-mentioned first method of directly selecting a predicted travel trajectory with the highest similarity as the target predicted travel trajectory of the second vehicle, and the determined predicted travel trajectory is the most likely to be close to the first predicted travel trajectory of the at least two predicted travel trajectories. 2.
  • the present application determines the target prediction of the second vehicle according to the at least two predicted driving trajectories and the similarity between each of the at least two predicted driving trajectories and the historical driving trajectory of the second vehicle.
  • the specific manner of the driving trajectory is not limited.
  • S907 Determine the motion state of the second vehicle relative to the first vehicle according to the target predicted travel trajectory and the first lane information.
  • the first lane information refers to the track information of the lane center axis of the lane where the first vehicle is located.
  • the distance between the target predicted driving trajectory and the center axis of the lane of the lane where the first vehicle is located can be determined by combining the information of the first lane to determine The motion state of the second vehicle relative to the first vehicle, such as whether the second vehicle will cut into the lane where the first vehicle is located from other lanes, whether the second vehicle will cut out from the lane where the first vehicle is located to other lanes, etc.
  • FIG. 10 shows another schematic flowchart of the vehicle motion state identification method provided by the embodiment of the present application.
  • S907 may include: S1001-S1006.
  • the target predicted travel trajectory and the first lane information determine the minimum lateral distance between the target predicted travel trajectory and the lane line of the lane where the first vehicle is located within a preset longitudinal length, and the first longitudinal position corresponding to the minimum lateral distance, and The second longitudinal position corresponding to the maximum lateral distance and the maximum lateral distance.
  • the first lane information may be the lane center axis of the lane where the first vehicle is located.
  • FIG. 11 shows a schematic diagram of vehicle A identifying the motion state of vehicle B according to the target predicted travel trajectory of vehicle B according to an embodiment of the present application.
  • the position of a may be a position close to the vehicle B along the direction of the center axis of the lane, or a position that is the same as the longitudinal coordinate of the vehicle B . Accordingly, the position where b is located is a position away from the vehicle B in the direction along the center axis of the lane. It can be understood that the preset longitudinal lengths [a, b] are only used to define a certain range along the direction of the center axis of the lane.
  • the minimum lateral distance d min between the target predicted travel trajectory z t (x) and the lane center axis y ego,t of the lane where the vehicle A is located within the preset longitudinal length [a, b], can be expressed as
  • the maximum lateral distance d max between the target predicted travel trajectory z t (x) and the lane center axis y ego,t of the lane where the vehicle A is located within the preset longitudinal length [a, b], can be expressed as
  • the first longitudinal position corresponding to the minimum lateral distance refers to the position where d min is located in the predicted target travel trajectory.
  • the second longitudinal position refers to the position where d max is located in the predicted target travel trajectory.
  • the size of the first threshold d 1 may be the width of half of the body of the first vehicle plus 30 cm, or may be a value close to the size.
  • Lane driving such as: can be expressed as
  • FIG. 12 shows another schematic diagram of identifying the motion state of vehicle B by vehicle A according to the target predicted driving trajectory of vehicle B according to an embodiment of the present application.
  • the size of the second threshold d 2 may be the width of the lane where the first vehicle is located plus 30 cm, or may be a value close to the size. It can be clearly seen that the second threshold d 2 is much larger than the first threshold d 1 .
  • the second vehicle When the minimum lateral distance d min is less than the first threshold d 1 and the maximum lateral distance d max is greater than the second threshold d 2 , it can be determined that the second vehicle will enter the lane where the first vehicle is located, and at the same time there will be a large lateral deviation It can be considered that the motion state of the second vehicle relative to the first vehicle is passing through the lane where the first vehicle is located, for example, it can be expressed as
  • FIG. 13 shows another schematic diagram of identifying the motion state of vehicle B by vehicle A according to the target predicted travel trajectory of vehicle B according to the embodiment of the present application.
  • the minimum lateral distance d min between the target predicted travel trajectory of vehicle B and the lane center axis of the lane where vehicle A is located is less than the first threshold d 1
  • the maximum lateral distance d max is greater than the second threshold d 2
  • the size of the third threshold d 3 may be the width of half of the body of the first vehicle minus 30 cm, or may be a value close to the size. It can be clearly seen that the third threshold d 3 is smaller than the first threshold d 1 .
  • the motion state of the second vehicle relative to the first vehicle is to keep driving in the same lane as the first vehicle, for example, it can be expressed as
  • objectState (follow) follow.
  • the second vehicle may follow the first vehicle, or the first vehicle may follow the second vehicle.
  • FIG. 14 shows another schematic diagram of identifying the motion state of vehicle B by vehicle A according to the target predicted travel trajectory of vehicle B according to the embodiment of the present application.
  • the minimum lateral distance d min must be smaller than the third threshold d 3 , and details are not repeated here.
  • the minimum lateral distance is less than the first threshold, the maximum lateral distance is greater than the third threshold and less than the second threshold, and the time when the second longitudinal position appears in the target predicted travel trajectory is earlier than the time when the first longitudinal position appears, then determine the first The motion state of the second vehicle relative to the first vehicle is to cut into the lane where the first vehicle is located.
  • FIG. 15 shows another schematic diagram of identifying the motion state of vehicle B by vehicle A according to the target predicted travel trajectory of vehicle B according to the embodiment of the present application.
  • the minimum lateral distance d min between the target predicted travel trajectory of vehicle B and the lane center axis of the lane where vehicle A is located is less than the first threshold d 1
  • the maximum lateral distance d max is greater than the third threshold d 3
  • the time when the second longitudinal position x max appears in the target predicted travel trajectory is earlier than the time when the first longitudinal position x min appears
  • the minimum lateral distance is less than the first threshold, the maximum lateral distance is greater than the third threshold and less than the second threshold, and the time when the first longitudinal position appears in the target predicted travel trajectory is earlier than the time when the second longitudinal position appears, then determine the first The motion state of the second vehicle relative to the first vehicle is to cut out of the lane where the first vehicle is located.
  • FIG. 16 shows another schematic diagram of identifying the motion state of vehicle B by vehicle A according to the target predicted travel trajectory of vehicle B according to an embodiment of the present application.
  • the minimum lateral distance d min between the target predicted travel trajectory of vehicle B and the lane center axis of the lane where vehicle A is located is less than the first threshold d 1
  • the maximum lateral distance d max is greater than the third threshold d 3
  • the time when the first longitudinal position x min appears in the target predicted travel trajectory is earlier than the time when the second longitudinal position x max appears
  • the motion state of the vehicle B relative to the vehicle A is to cut out the vehicle
  • the method may also be based on the first longitudinal position corresponding to the minimum lateral distance, and the preset Assuming that the longitudinal length is close to the longitudinal distance between one end of the first vehicle, the motion state of the second vehicle relative to the first vehicle is further refined to cut into the lane where the first vehicle is located according to the first cut-in state, or cut into the lane according to the second cut-in state. The state cuts into the lane where the first vehicle is located.
  • the method may also be close to the preset longitudinal length according to the first longitudinal position corresponding to the minimum lateral distance.
  • the longitudinal distance between one end of the first vehicle further refines the motion state of the second vehicle relative to the first vehicle to cut out the lane where the first vehicle is located according to the first cut-out state, or cut out according to the second cut-out state Lane of the first vehicle.
  • the first in state may be referred to as a tight in state, and the first out state may be referred to as a tight out state.
  • the second switch-in state may be referred to as a normal switch-in state, and the second switch-out state may be referred to as a normal switch-out state.
  • the first/second switch-in state and the first/second switch-out state may also be called other names.
  • the first cut-in state is called the tight cut-in state
  • the first cut-out state is called the tight cut-out state
  • the second cut-in state is called the normal cut-in state
  • the second cut-out state is called the normal cut-out state as examples.
  • the motion state of the second vehicle relative to the first vehicle is further refined into tight entry or normal cut in
  • the motion state of the second vehicle relative to the first vehicle is further refined into tight exit or normal cut out
  • FIG. 17 shows another schematic diagram of identifying the motion state of vehicle B by vehicle A according to the target predicted travel trajectory of vehicle B according to an embodiment of the present application.
  • the longitudinal distance between the first longitudinal position corresponding to the minimum lateral distance and the preset longitudinal length a that is, the first longitudinal position is located at a distance from the lane line of the lane where the first vehicle is located.
  • the distance between the parallel direction and the preset longitudinal length a further refines the motion state of the second vehicle relative to the first vehicle.
  • the longitudinal distance is less than the fourth threshold (for example: 1 meter, 2 meters, 3 meters, etc., which is not limited here), then It is determined that the motion state of the second vehicle relative to the first vehicle is close_cut_in to the lane where the first vehicle is located. If the longitudinal distance is greater than the fourth threshold, it is determined that the motion state of the second vehicle relative to the first vehicle is a normal cut (general_cut_in) into the lane where the first vehicle is located.
  • the fourth threshold for example: 1 meter, 2 meters, 3 meters, etc., which is not limited here
  • the longitudinal distance is equal to the fourth threshold, it can be determined that the motion state of the second vehicle relative to the first vehicle is to closely enter the lane where the first vehicle is located, or to normally cut into the lane where the first vehicle is located, which is not limited here.
  • the longitudinal distance between the first longitudinal position corresponding to the minimum lateral distance and the end of the preset longitudinal length a may be The distance between the ends of the longitudinal length a is preset, and the motion state of the second vehicle relative to the first vehicle is further refined into a case of close cutout or normal cutout for illustration. For example, when it is determined that the motion state of the second vehicle relative to the first vehicle is to cut out of the lane where the first vehicle is located, if the longitudinal distance is less than the fourth threshold, it can be determined that the motion state of the second vehicle relative to the first vehicle is tight Close out of the lane of the first vehicle.
  • the longitudinal distance is greater than the fourth threshold, it is determined that the motion state of the second vehicle relative to the first vehicle is to normally cut out of the lane where the first vehicle is located. It is also easy to understand that if the longitudinal distance is equal to the fourth threshold, it can be determined that the motion state of the second vehicle relative to the first vehicle is to closely exit the lane where the first vehicle is located, or, to normally cut out the lane where the first vehicle is located, where There are no restrictions.
  • the vehicle motion state identification method may further include: The steps of correcting the motion information.
  • the lateral speed in several (for example, 6) historical periods may be collected first, and the average value of the lateral speeds in the previous several historical periods may be calculated to obtain the average historical lateral speed of the second vehicle. Then, according to the average historical lateral speed of the second vehicle The historical lateral speed is corrected for the lateral speed included in the motion information of the second vehicle.
  • a time-velocity polynomial fitting can also be performed on the lateral speeds in the aforementioned several historical periods to obtain a fitting coefficient (for the polynomial fitting method, please refer to the predicted driving of the second vehicle keeping lane or changing lanes in the preceding embodiment). The method of performing polynomial fitting on the trajectory will not be repeated here). Then, the current lateral speed of the second vehicle is predicted according to the fitting coefficient to obtain the predicted current lateral speed. Then, the lateral velocity included in the motion information of the second vehicle may be modified according to the predicted current lateral velocity.
  • the collected second The lateral speed of the vehicle is compared with the current lateral speed predicted above, and if the difference between the two is greater than the fifth threshold, the collected lateral speed is corrected to reduce the instantaneous speed due to the collected lateral speed being too large. disturbance caused.
  • the lateral speed can be increased or decreased, or the collected lateral speed can be updated by performing a weighted combination of the collected lateral speed and the predicted current lateral speed according to a preset weight.
  • the magnitude of the fifth threshold is related to the driving stability of the second vehicle.
  • the fifth threshold may be 0.2 meters per second (m/s), 0.4 m/s, etc., which is not limited herein.
  • the gap when the gap is large, it means that the driving intention of the second vehicle is more clear, and the delay effect of the historical driving trajectory of the second vehicle on the predicted driving trajectory can be reduced by reducing the size of the first preset period and the second preset period.
  • the sizes of the first preset period and the second preset period can be increased.
  • the polynomial fitting prediction result of the historical lateral speed that is, the predicted current lateral speed is v
  • the collected current lateral speed is v0
  • the first preset time period is ⁇ m
  • the second preset time period is is ⁇ n ( ⁇ m , ⁇ n is the calibration value, for example: ⁇ m can be 3, ⁇ n can be 2.5)
  • the size of ⁇ m and ⁇ n can be changed as follows.
  • the above ⁇ m may refer to the number of first preset periods included in the first preset period, and adjusting the size of the first preset period refers to the number of first preset periods included in the first preset period. The number of a preset period is adjusted.
  • ⁇ n may refer to the number of second preset periods included in the second preset period
  • adjusting the size of the second preset period refers to the number of second preset periods included in the second preset period. The number of preset cycles can be adjusted.
  • the vehicle or server may include corresponding hardware structures and/or software modules for executing each function.
  • the embodiments of the present application may also provide a vehicle motion state identification device.
  • FIG. 18 shows a schematic structural diagram of a vehicle motion state identification device provided by an embodiment of the present application.
  • the vehicle motion state identification device may include: an acquisition module 1801 for acquiring first lane information, second lane information, and position information and motion information of the second vehicle; the first lane information is the first lane information Lane information of the lane where the vehicle is located; the second lane information includes the lane information of the lane where the second vehicle is located, the lane information of the first adjacent lane of the lane where the second vehicle is located, and the lane of the second adjacent lane of the lane where the second vehicle is located at least two of the information.
  • the prediction module 1802 is configured to determine at least two predicted travel trajectories of the second vehicle according to the second lane information and the position information and motion information of the second vehicle; each predicted travel trajectory and each of the second lane information included corresponding to the lane information.
  • the determining module 1803 is configured to determine the motion state of the second vehicle relative to the first vehicle according to the at least two predicted travel trajectories and the first lane information.
  • the determining module 1803 is specifically configured to determine the target of the second vehicle according to the at least two predicted driving trajectories and the similarity between at least each predicted driving trajectory and the historical driving trajectory of the second vehicle Predicting the travel trajectory; determining the motion state of the second vehicle relative to the first vehicle according to the target predicted travel trajectory and the first lane information.
  • the determining module 1803 is further configured to acquire a first lateral coordinate vector of the historical driving trajectory of the second vehicle within the first preset time period; wherein the first lateral coordinate vector is used to indicate the historical driving trajectory The distance vector from the lane line of the lane where the second vehicle is located; for each predicted travel trajectory: obtain the second lateral coordinate vector of the predicted travel trajectory within the second preset time period, according to the second lateral coordinate vector and the first The horizontal coordinate vector determines the similarity between the predicted driving trajectory and the historical driving trajectory; wherein, the second horizontal coordinate vector is used to indicate the distance vector between the predicted driving trajectory and the lane line of the lane where the second vehicle is located.
  • the determining module 1803 is specifically configured to predict the difference between each predicted driving trajectory and the real driving trajectory of the second vehicle according to the similarity between each predicted driving trajectory and the historical driving trajectory of the second vehicle.
  • the similarity between the at least two predicted travel trajectories and the similarity between each predicted travel trajectory and the real travel trajectory of the second vehicle is determined to determine the target predicted travel trajectory of the second vehicle.
  • the determining module 1803 is specifically configured to determine, according to the predicted target driving trajectory and the first lane information, the minimum lateral distance between the target predicted driving trajectory and the lane line of the lane where the first vehicle is located within a preset longitudinal length ; If the minimum lateral distance is greater than the first threshold, determine that the motion state of the second vehicle relative to the first vehicle is to keep driving in a different lane with the first vehicle.
  • the determining module 1803 is further configured to determine, according to the predicted target driving trajectory and the first lane information, the maximum lateral distance between the target predicted driving trajectory and the lane line of the lane where the first vehicle is located within a preset longitudinal length If the minimum lateral distance is less than the first threshold and the maximum lateral distance is greater than the second threshold, then determine that the motion state of the second vehicle relative to the first vehicle is to pass through the lane where the first vehicle is located; wherein the second threshold is greater than the first threshold . If the maximum lateral distance is less than the third threshold, it is determined that the motion state of the second vehicle relative to the first vehicle is to keep driving in the same lane as the first vehicle; wherein the third threshold is less than the first threshold.
  • the motion state of the second vehicle relative to the first vehicle is to cut into the lane where the first vehicle is located, or to cut out of the first vehicle the driveway.
  • the determining module 1803 is further configured to obtain the first longitudinal position corresponding to the minimum lateral distance and the second longitudinal position corresponding to the maximum lateral distance; when the minimum lateral distance is less than the first threshold, the maximum lateral distance is greater than the When the three thresholds are smaller than the second threshold, if the time when the second longitudinal position appears in the predicted travel trajectory of the target is earlier than the time when the first longitudinal position appears, it is determined that the motion state of the second vehicle relative to the first vehicle is to cut into the first vehicle.
  • the lane where the vehicle is located if the time when the first longitudinal position appears in the target predicted travel trajectory is earlier than the time when the second longitudinal position occurs, the motion state of the second vehicle relative to the first vehicle is determined to be cutting out of the lane where the first vehicle is located.
  • the determining module 1803 is further configured to obtain the longitudinal distance between the first longitudinal position and the first end of the preset longitudinal length; wherein the longitudinal distance is the distance between the first longitudinal position and the lane where the first vehicle is located. The distance between the parallel direction of the lane line and the first end of the preset longitudinal length, and the first end of the preset longitudinal length is the end close to the first vehicle; if the longitudinal distance is less than the fourth threshold, determine the first end of the longitudinal length.
  • the motion state of the second vehicle relative to the first vehicle is to cut into the lane where the first vehicle is located according to the first cut-in state, or cut out of the lane where the first vehicle is located according to the first cut-out state; if the longitudinal distance is greater than the fourth threshold, determine the third The motion state of the second vehicle relative to the first vehicle is to cut into the lane where the first vehicle is located according to the second cut-in state, or cut out of the lane where the first vehicle is located according to the second cut-out state.
  • the motion information of the second vehicle includes the lateral speed of the second vehicle; the prediction module 1802 is further configured to, according to the average historical lateral speed of the second vehicle, analyze the lateral speed included in the motion information of the second vehicle speed is corrected.
  • modules or units in the above apparatus is only a division of logical functions, and may be fully or partially integrated into a physical entity in actual implementation, or may be physically separated.
  • the modules in the device can all be implemented in the form of software calling through the processing element; also can all be implemented in the form of hardware; some units can also be implemented in the form of software calling through the processing element, and some units can be implemented in the form of hardware.
  • each unit can be a separately established processing element, or can be integrated in a certain chip of the device to be implemented, and can also be stored in the memory in the form of a program, which can be called by a certain processing element of the device and execute the unit's processing.
  • All or part of these units can be integrated together, and can also be implemented independently.
  • the processing element described here may also be called a processor, which may be an integrated circuit with signal processing capability.
  • each step of the above method or each of the above units may be implemented by an integrated logic circuit of hardware in the processor element or implemented in the form of software being invoked by the processing element.
  • a unit in any of the above apparatuses may be one or more integrated circuits configured to implement the above methods, eg, one or more application specific integrated circuits (ASICs), or, one or more Multiple microprocessors (digital singnal processors, DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.
  • ASICs application specific integrated circuits
  • DSPs digital singnal processors, DSPs
  • FPGAs field programmable gate arrays
  • the processing element can be a general-purpose processor, such as a central processing unit (central processing unit, CPU) or other processors that can invoke programs.
  • CPU central processing unit
  • these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).
  • an embodiment of the present application may further provide a vehicle motion state identification device, including: an interface circuit for receiving data transmitted by other devices; a processor, connected to the interface circuit and used for executing each step in the above method.
  • the processor may include one or more.
  • a vehicle motion state identification device may include a processing element and a storage element, and the processing element invokes a program stored in the storage element to execute the method described in the above method embodiments.
  • the storage element may be a storage element on the same chip as the processing element, ie, an on-chip storage element.
  • the program for implementing the above method may be in a storage element on a different chip from the processing element, ie, an off-chip storage element.
  • the processing element calls or loads the program from the off-chip storage element to the on-chip storage element, so as to call and execute the methods described in the above method embodiments.
  • an embodiment of the present application may further provide a vehicle including a processor, where the processor is configured to be connected to a memory and call a program stored in the memory to execute the method described in the above method embodiments.
  • an embodiment of the present application may further provide a server including a processor, the server can perform remote communication with the vehicle, and the processor is configured to be connected to a memory and call a program stored in the memory to execute the methods described in the above method embodiments. method.
  • the embodiments of the present application may further provide a vehicle driving system, for example, an automatic driving system or an assisted driving system.
  • the vehicle driving system may consist of a vehicle and a server, or be deployed in the vehicle or the server alone.
  • the vehicle driving system includes: a processor, which is configured to be connected to a memory and call a program stored in the memory to execute the method described in the above method embodiments.
  • the modules used to implement the steps in the above method may be configured as one or more processing elements, and these processing elements may be provided on the terminal, where the processing elements may be integrated circuits, for example: a or ASICs, or one or more DSPs, or one or more FPGAs, or a combination of these types of integrated circuits. These integrated circuits can be integrated together to form chips.
  • the modules for implementing each step in the above method can be integrated together and implemented in the form of an SOC, and the SOC chip is used to implement the corresponding method.
  • At least one processing element and a storage element may be integrated in the chip, and the corresponding method may be implemented in the form of a program stored in the storage element being invoked by the processing element; or, at least one integrated circuit may be integrated in the chip for implementing the corresponding method; or , can be combined with the above implementations, the functions of some units are realized in the form of calling programs by processing elements, and the functions of some units are realized in the form of integrated circuits.
  • the processing elements here are the same as those described above, and may be a general-purpose processor, such as a CPU, or one or more integrated circuits configured to implement the above method, such as: one or more ASICs, or one or more microprocessors DSP, or, one or more FPGAs, etc., or a combination of at least two of these integrated circuit forms.
  • a general-purpose processor such as a CPU
  • one or more integrated circuits configured to implement the above method, such as: one or more ASICs, or one or more microprocessors DSP, or, one or more FPGAs, etc., or a combination of at least two of these integrated circuit forms.
  • the storage element may be one memory or a collective term for multiple storage elements.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are only illustrative.
  • the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be Incorporation may either be integrated into another device, or some features may be omitted, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place, or may be distributed to multiple different places . Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a readable storage medium.
  • the software product is stored in a program product, such as a computer-readable storage medium, and includes several instructions to cause a device (which may be a single-chip microcomputer, a chip, etc.) or a processor (processor) to execute all of the methods described in the various embodiments of the present application. or part of the steps.
  • the aforementioned storage medium includes: a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk and other mediums that can store program codes.
  • the embodiments of the present application may further provide a computer-readable storage medium, including: computer software instructions; when the computer software instructions are executed in the vehicle motion state identification device or a chip built into the vehicle motion state identification device, the computer software instructions cause the vehicle to move.
  • the state identification apparatus executes the method as described in the foregoing method embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

本申请公开了一种车辆运动状态识别方法及装置，涉及自动驾驶领域。该方法可以根据其他车辆的位置信息和运动信息，以及其他车辆的所在车道的车道信息、其他车辆所在车道的第一相邻车道的车道信息和其他车辆所在车道的第二相邻车道的车道信息中的至少两种，对其他车辆的行驶轨迹进行预测，得到与前述至少两种车道信息相对应的至少两条预测行驶轨迹。然后，可以根据前述至少两条预测行驶轨迹和本车所在车道的车道信息，对其他车辆相对于本车的运动状态进行识别，从而可以在监测其他车辆相对于本车的运动状态时，有效降低对其他车辆的瞬时运动学信息的敏感性，减少对其他车辆的运动状态的误识别。

Description

车辆运动状态识别方法及装置
本申请要求于2020年07月31日提交国家知识产权局、申请号为202010762012.3、申请名称为“车辆运动状态识别方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及自动驾驶领域，尤其涉及一种车辆运动状态识别方法及装置。
背景技术
在车辆自动驾驶和辅助驾驶领域，车辆需要及时、准确地获知道路上其他车辆的运动状态，如其他车辆是否进行变道，以根据其他车辆的运动状态进行本车的路径规划、自适应巡航、以及紧急情况下的合理减速等操作。因此，车辆在行驶过程中，需要对道路上其他车辆的运动状态进行监测。
目前，车辆可以通过传感器采集其他车辆的转向灯、其他车辆与其所在车道的车道线之间的横向距离、其他车辆的速度和加速度等信息，并根据所采集的前述信息预测其他车辆的行驶轨迹；然后，车辆可以根据预测的其他车辆的行驶轨迹，识别其他车辆是否进行变道。或者，车辆也可以通过传感器采集其他车辆所在车道的车道线信息、其他车辆与其所在车道的车道线之间的横向距离和航向角等信息，并根据所采集的前述信息确定其他车辆的实际行驶轨迹，然后，将其他车辆的实际行驶轨迹与车辆行驶数据库中正常保持车道行驶的车辆的行驶轨迹进行对比，当两者距离大于一个设定的阈值时，即认为其他车辆正在进行变道。
但是，上述目前对其他车辆的运动状态进行监测的方式中，在预测其他车辆的行驶轨迹时，或者，在将其他车辆的实际行驶轨迹与车辆行驶数据库中正常保持车道行驶的车辆的行驶轨迹进行对比时，均对其他车辆的瞬时运动学信息较为敏感，容易导致对其他车辆的运动状态出现误识别。
发明内容
本申请实施例提供一种车辆运动状态识别方法及装置，可以在监测其他车辆的运动状态时，有效降低对其他车辆的瞬时运动学信息的敏感性，减少对其他车辆的运动状态的误识别。
第一方面，本申请实施例提供一种车辆运动状态识别方法，该方法包括：获取第一车道信息、第二车道信息、以及第二车辆的位置信息和运动信息；第一车道信息为第一车辆所在车道的车道信息；第二车道信息包括所述第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息中的至少两种；根据第二车道信息、以及第二车辆的位置信息和运动信息，确定第二车辆的至少两条预测行驶轨迹；每条预测行驶轨迹与第二车道信息所包含的每种车道信息相对应；根据至少两条预测行驶轨迹、以及第一车道信息，确定第二车辆相对于第一车辆的运动状态。
其中，第二车辆的位置信息可以是第二车辆相对于第一车辆的相对位置，如：相对 位置坐标。或者，第二车辆的位置信息也可以是第二车辆的绝对位置，如：可以根据第一车辆的位置坐标、以及第二车辆相对于第一车辆的相对位置坐标，确定出第二车辆的真实(绝对)位置坐标。
第二车辆的运动信息可以包括：第二车辆的速度、加速度、轨迹曲率等运动学信息。
每条预测行驶轨迹与第二车道信息所包含的每种车道信息相对应是指：当第二车道信息包括两种车道信息时，可以确定出与两种车道信息一一对应的两条预测行驶轨迹。当第二车道信息包括三种车道信息时，可以确定出与三种车道信息一一对应的三条预测行驶轨迹。
例如，当第二车道信息包括第二车辆所在车道的车道信息、以及第二车辆所在车道的第一相邻车道的车道信息时，可以相应确定出第二车辆在当前所在车道保持行驶的预测行驶轨迹、以及第二车辆变道至所在车道的第一相邻车道行驶的预测行驶轨迹。
或者，当第二车道信息包括第二车辆所在车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息时，可以相应确定出第二车辆在当前所在车道保持行驶的预测行驶轨迹、以及第二车辆变道至所在车道的第二相邻车道行驶的预测行驶轨迹。
又或者，当第二车道信息可以包括第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息时，可以相应确定出第二车辆变道至所在车道的第一相邻车道行驶的预测行驶轨迹、以及第二车辆变道至所在车道的第二相邻车道行驶的预测行驶轨迹。
又或者，当第二车道信息包括第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息中的三种全部时，可以相应确定出第二车辆在当前所在车道保持行驶的预测行驶轨迹、第二车辆变道至所在车道的第一相邻车道行驶的预测行驶轨迹、以及第二车辆变道至所在车道的第二相邻车道行驶的预测行驶轨迹。
该方法可以根据第二车辆的位置信息和运动信息，以及第二车辆的所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息和第二车辆所在车道的第二相邻车道的车道信息中的至少两种，对第二车辆的行驶轨迹进行预测，得到与前述至少两种车道信息一一对应的至少两条预测行驶轨迹。然后，可以根据前述至少两条预测行驶轨迹和第一车辆所在车道的车道信息，对第二车辆相对于第一车辆的运动状态进行识别，从而可以在监测第二车辆相对于第一车辆的运动状态时，有效降低对第二车辆的瞬时运动学信息的敏感性，减少对第二车辆的运动状态的误识别。
其中，第一车辆可以理解为自动驾驶或辅助驾驶的本车，第二车辆可以理解相对于本车，在道路上行驶的其他车辆。
在一种可能的设计中，所述根据至少两条预测行驶轨迹、以及第一车道信息，确定第二车辆相对于第一车辆的运动状态，包括：根据至少两条预测行驶轨迹、以及每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹；根据目标预测行驶轨迹、以及第一车道信息，确定第二车辆相对于第一车辆的运动状态。
本设计中，根据至少两条预测行驶轨迹、以及每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹，可以使得所确定的第二车辆的目标预测行驶轨迹更接近第二车辆在未来的真实行驶轨迹，从而提高后续根据目标预测行驶轨迹、以及第一车道信息，所确定的第二车辆相对于第一车辆的运动状态的准 确性。
在一种可能的设计中，在所述根据至少两条预测行驶轨迹、以及每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹之前，该方法还包括：获取第二车辆的历史行驶轨迹在第一预设时段内的第一横向坐标向量；其中，第一横向坐标向量用于指示历史行驶轨迹与第二车辆所在车道的车道线之间的距离向量；针对每条预测行驶轨迹：获取预测行驶轨迹在第二预设时段内的第二横向坐标向量，根据第二横向坐标向量、以及第一横向坐标向量确定预测行驶轨迹与历史行驶轨迹之间的相似度；其中，第二横向坐标向量用于指示预测行驶轨迹与第二车辆所在车道的车道线之间的距离向量。
其中，第二车辆的历史行驶轨迹在第一预设时段内的第一横向坐标向量中包括第二车辆的历史行驶轨迹在第一预设时段内的多个第一横向坐标。预测行驶轨迹在第二预设时段内的第二横向坐标向量包括预测行驶轨迹在第二预设时段内的多个第二横向坐标。
一些实施方式中，第一预设时段可以是多个连续的第一预设周期组成的时段，每个第一预设周期内可以包含有至少一个第一横向坐标。第二预设时段可以是多个连续的第二预设周期组成的时段，每个第二预设周期内可以包含有至少一个第二横向坐标。
或者，在其他一些可能的设计中，也可以采用其他相似度计算方式，确定前述至少两条预测行驶轨迹中每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，在此不作限制。
在一种可能的设计中，所述根据至少两条预测行驶轨迹、以及每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹，包括：根据每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，预测每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度；根据至少两条预测行驶轨迹、以及每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹。
例如，可以对每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度进行归一化，预测每条预测行驶轨迹的概率，该概率可以指示每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度；根据至少两条预测行驶轨迹、以及每条预测行驶轨迹的概率，确定第二车辆的目标预测行驶轨迹。
本设计中，通过预测至少两条预测行驶轨迹中每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度，可以根据每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度，综合考虑前述至少两条预测行驶轨迹，对第二车辆的目标预测行驶轨迹进行确定，能够使得所确定的目标预测行驶轨迹中第二车辆的运动状态的切换或变换具有更好的连续性。
在一种可能的设计中，所述根据目标预测行驶轨迹、以及第一车道信息，确定第二车辆相对于所述第一车辆的运动状态，包括：根据目标预测行驶轨迹、以及第一车道信息，确定目标预测行驶轨迹与第一车辆所在车道的车道线在预设纵向长度内的最小横向距离。若最小横向距离大于第一阈值，则确定第二车辆相对于第一车辆的运动状态为与第一车辆保持在不同车道行驶。
本设计可以通过判断目标预测行驶轨迹与第一车辆所在车道的车道线在预设纵向长度内的最小横向距离，相对于第一阈值的大小，确定出第二车辆相对于第一车辆的运动状态是否为与第一车辆保持在不同车道行驶。
在一种可能的设计中，该方法还包括：根据目标预测行驶轨迹、以及第一车道信息， 确定目标预测行驶轨迹与第一车辆所在车道的车道线在预设纵向长度内的最大横向距离；若最小横向距离小于第一阈值、且最大横向距离大于第二阈值，则确定第二车辆相对于第一车辆的运动状态为穿过第一车辆所在车道；其中，第二阈值大于所述第一阈值。若最大横向距离小于第三阈值，则确定第二车辆相对于第一车辆的运动状态为与第一车辆保持在同一车道行驶；其中，第三阈值小于所述第一阈值。若最小横向距离小于第一阈值，最大横向距离大于第三阈值、且小于第二阈值，则确定第二车辆相对于第一车辆的运动状态为切入第一车辆所在车道、或者切出第一车辆所在车道。
本设计可以在目标预测行驶轨迹与第一车辆所在车道的车道线在预设纵向长度内的最小横向距离小于第一阈值时，进一步通过判断最大横向距离与第二阈值和第三阈值的相对大小，对第二车辆相对于第一车辆的运动状态进一步进行细化。
在一种可能的设计中，该方法还包括：获取最小横向距离对应的第一纵向位置、以及最大横向距离对应的第二纵向位置。当最小横向距离小于第一阈值，最大横向距离大于第三阈值、且小于第二阈值时，所述确定第二车辆相对于第一车辆的运动状态为切入第一车辆所在车道、或者切出第一车辆所在车道，包括：若目标预测行驶轨迹中第二纵向位置出现的时间早于第一纵向位置出现的时间，则确定第二车辆相对于第一车辆的运动状态为切入第一车辆所在车道。若目标预测行驶轨迹中所述第一纵向位置出现的时间早于第二纵向位置出现的时间，则确定第二车辆相对于第一车辆的运动状态为切出第一车辆所在车道。
本设计可以根据最小横向距离对应的第一纵向位置、与最大横向距离对应的第二纵向位置，在目标预测行驶轨迹中出现的先后时间，区分第二车辆相对于第一车辆的运动状态为切入或切出第一车辆所在车道。
在一种可能的设计中，该方法还包括：获取第一纵向位置与预设纵向长度的第一端之间的纵向距离；其中，纵向距离为第一纵向位置在与第一车辆所在车道的车道线的平行方向上与预设纵向长度的第一端之间的距离，且预设纵向长度的第一端是靠近于第一车辆的一端。若纵向距离小于第四阈值，则确定第二车辆相对于第一车辆的运动状态为按照第一切入状态切入第一车辆所在车道、或者按照第一切出状态切出第一车辆所在车道。若纵向距离大于第四阈值，则确定第二车辆相对于第一车辆的运动状态为按照第二切入状态切入第一车辆所在车道、或者按照第二切出状态切出第一车辆所在车道。
例如，第一切入状态可以称为紧密切入状态，第一切出状态可以称为紧密切出状态。第二切入状态可以称为正常切入状态，第二切出状态可以称为正常切出状态。或者，也可以将第一/第二切入状态、第一/第二切出状态称为其他名称。
以第一切入状态称为紧密切入状态，第一切出状态称为紧密切出状态，第二切入状态称为正常切入状态，第二切出状态称为正常切出状态为例，本设计中可以进一步根据第一纵向位置与预设纵向长度的第一端之间的纵向距离，相对于第四阈值的大小，将第二车辆相对于第一车辆的运动状态由切入第一车辆所在车道细化为：紧密切入或正常切入，或者，将第二车辆相对于第一车辆的运动状态由切出第一车辆所在车道细化为：紧密切出或正常切出。
在一种可能的设计中，第二车辆的运动信息包括第二车辆的横向速度；在所述根据第二车道信息、以及第二车辆的位置信息和运动信息，确定第二车辆的至少两条预测行驶轨迹之前，该方法还包括：根据第二车辆的平均历史横向速度，对第二车辆的运动信息中包括的横向速度进行修正。
本设计通过根据第二车辆的平均历史横向速度，对第二车辆的运动信息中包括的横向速度进行修正，可以降低在确定第二车辆的预测行驶轨迹时，由于当前横向速度的瞬时速度过大带来的扰动。
第二方面，本申请实施例提供一种车辆运动状态识别装置，装置包括：获取模块，用于获取第一车道信息、第二车道信息、以及第二车辆的位置信息和运动信息；第一车道信息为第一车辆所在车道的车道信息；第二车道信息包括第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息中的至少两种。预测模块，用于根据第二车道信息、以及第二车辆的位置信息和运动信息，确定第二车辆的至少两条预测行驶轨迹；每条预测行驶轨迹与第二车道信息所包含的每种车道信息相对应。确定模块，用于根据至少两条预测行驶轨迹、以及第一车道信息，确定第二车辆相对于第一车辆的运动状态。
在一种可能的设计中，确定模块，具体用于根据至少两条预测行驶轨迹、以及每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹；根据目标预测行驶轨迹、以及第一车道信息，确定第二车辆相对于第一车辆的运动状态。
在一种可能的设计中，确定模块，还用于获取第二车辆的历史行驶轨迹在第一预设时段内的第一横向坐标向量；其中，第一横向坐标向量用于指示历史行驶轨迹与第二车辆所在车道的车道线之间的距离向量；针对每条预测行驶轨迹：获取预测行驶轨迹在第二预设时段内的第二横向坐标向量，根据第二横向坐标向量、以及第一横向坐标向量确定预测行驶轨迹与历史行驶轨迹之间的相似度；其中，第二横向坐标向量用于指示预测行驶轨迹与第二车辆所在车道的车道线之间的距离向量。
在一种可能的设计中，确定模块，具体用于根据每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，预测每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度；根据至少两条预测行驶轨迹、以及每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹。
在一种可能的设计中，确定模块具体用于根据目标预测行驶轨迹、以及第一车道信息，确定目标预测行驶轨迹与第一车辆所在车道的车道线在预设纵向长度内的最小横向距离；若最小横向距离大于第一阈值，则确定第二车辆相对于第一车辆的运动状态为与第一车辆保持在不同车道行驶。
在一种可能的设计中，确定模块还用于根据目标预测行驶轨迹、以及第一车道信息，确定目标预测行驶轨迹与第一车辆所在车道的车道线在预设纵向长度内的最大横向距离；若最小横向距离小于第一阈值、且最大横向距离大于第二阈值，则确定第二车辆相对于第一车辆的运动状态为穿过第一车辆所在车道；其中，第二阈值大于第一阈值。若最大横向距离小于第三阈值，则确定第二车辆相对于第一车辆的运动状态为与第一车辆保持在同一车道行驶；其中，第三阈值小于第一阈值。若最小横向距离小于第一阈值，最大横向距离大于第三阈值、且小于第二阈值，则确定第二车辆相对于第一车辆的运动状态为切入第一车辆所在车道、或者切出第一车辆所在车道。
在一种可能的设计中，确定模块还用于获取最小横向距离对应的第一纵向位置、以及最大横向距离对应的第二纵向位置；当最小横向距离小于第一阈值，最大横向距离大于第三阈值、且小于第二阈值时，若目标预测行驶轨迹中第二纵向位置出现的时间早于第一纵向位置出现的时间，则确定第二车辆相对于第一车辆的运动状态为切入第一车辆 所在车道；若目标预测行驶轨迹中第一纵向位置出现的时间早于第二纵向位置出现的时间，则确定第二车辆相对于第一车辆的运动状态为切出第一车辆所在车道。
在一种可能的设计中，确定模块还用于获取第一纵向位置与预设纵向长度的第一端之间的纵向距离；其中，纵向距离为第一纵向位置在与第一车辆所在车道的车道线的平行方向上与预设纵向长度的第一端之间的距离，且预设纵向长度的第一端是靠近于第一车辆的一端；若纵向距离小于第四阈值，则确定第二车辆相对于第一车辆的运动状态为按照第一切入状态切入第一车辆所在车道、或者按照第一切出状态切出第一车辆所在车道；若纵向距离大于第四阈值，则确定第二车辆相对于第一车辆的运动状态为按照第二切入状态切入第一车辆所在车道、或者按照第二切出状态切出第一车辆所在车道。
在一种可能的设计中，第二车辆的运动信息包括第二车辆的横向速度；预测模块，还用于根据第二车辆的平均历史横向速度，对第二车辆的运动信息中包括的横向速度进行修正。
第三方面，本申请实施例还提供一种车辆运动状态识别装置，包括：接口电路，用于接收其他装置传输的数据；处理器，连接接口电路并用于执行如第一方面或其任一可能的设计中所述的方法。
第四方面，本申请实施例提供一种车辆，包括：处理器，处理器用于与存储器相连，调用存储器中存储的程序，以执行如第一方面或其任一可能的设计中所述的方法。
第五方面，本申请实施例提供一种服务器，包括：处理器，处理器用于与存储器相连，调用存储器中存储的程序，以执行如第一方面或其任一可能的设计中所述的方法。
第六方面，本申请实施例提供一种车辆驾驶系统，如：可以是自动驾驶系统或辅助驾驶系统，包括：处理器，处理器用于与存储器相连，调用存储器中存储的程序，以执行如第一方面或其任一可能的设计中所述的方法。
第七方面，本申请实施例提供一种计算机可读存储介质，包括：计算机软件指令；当计算机软件指令在车辆运动状态识别装置或内置在车辆运动状态识别装置的芯片中运行时，使得车辆运动状态识别装置执行如第一方面或其任一可能的设计中所述的方法。
第八方面，本申请实施例还提供一种计算机程序产品，该计算机程序产品被执行时可以实现如第一方面或第一方面的可能的设计中任一所述的方法。
第九方面，本申请实施例还提供一种芯片系统，该芯片系统应用于车辆，或者服务器，又或者驾驶系统，芯片系统包括一个或多个接口电路和一个或多个处理器；接口电路和处理器通过线路互联；处理器通过接口电路从电子设备的存储器接收并执行计算机指令，以实现如第一方面或第一方面的可能的设计中任一所述的方法。
可以理解地，上述提供的第二方面至第九方面所能达到的有益效果，可参考第一方面及其任一种可能的设计方式中的有益效果，此处不再赘述。
附图说明
图1示出了本申请实施例提供的一种应用场景的示意图；
图2示出了车辆2相对于车辆1的运动状态变化的示意图；
图3示出了车辆4相对于车辆1的运动状态变化的示意图；
图4示出了车辆A通过预测车辆B的行驶轨迹对车辆B的运动状态进行识别的示意图；
图5示出了车辆A通过预测车辆B的行驶轨迹对车辆B的运动状态进行识别的另一 示意图；
图6示出了车辆A通过对比车辆行驶数据库中正常保持车道行驶的车辆的行驶轨迹对车辆B的运动状态进行识别的示意图；
图7示出了车辆A通过对比车辆行驶数据库中正常保持车道行驶的车辆的行驶轨迹对车辆B的运动状态进行识别的另一示意图；
图8示出了本申请实施例提供的一种车辆的组成示意图；
图9示出了本申请实施例提供的车辆运动状态识别方法的流程示意图；
图10示出了本申请实施例提供的车辆运动状态识别方法的另一流程示意图；
图11示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的示意图；
图12示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的另一示意图；
图13示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的又一示意图；
图14示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的又一示意图；
图15示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的又一示意图；
图16示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的又一示意图；
图17示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的又一示意图；
图18示出了本申请实施例提供的车辆运动状态识别装置的结构示意图。
具体实施方式
图1示出了本申请实施例提供的一种应用场景的示意图。
如图1所示，本申请实施例的应用场景中可以包括在道路上行驶的多个车辆。图1中示例性的给出了四个车辆，包括：车辆1、车辆2、车辆3和车辆4。不同的车辆可能行驶在不同车道，如：车辆1行驶在车道1，车辆2行驶在车道2，车辆3行驶在车道3等。或者，不同的车辆也可能行驶在同一车道，如车辆1和车辆4共同行驶在车道1上。
在车辆自动驾驶和辅助驾驶领域，对于图1所示的应用场景中的某个车辆而言，其需要及时、准确地获知道路上其他车辆的运动状态，如其他车辆是否进行变道，以根据其他车辆的运动状态进行本车的路径规划、自适应巡航、以及紧急情况下的合理减速等操作。
以图1中所示的应用场景中，车辆1监测车辆2的运动状态为例，图2示出了车辆2相对于车辆1的运动状态变化的示意图。如图2所示，车辆1和车辆2在行驶过程中，车辆2可能会切入车辆1所在车道行驶，如：从车道2切入车道1。而车辆1需要及时监测到车辆2的这种运动状态的变化，以进行本车的路径规划、合理减速等。
或者，以图1中所示的应用场景中，车辆1监测车辆4的运动状态为例，图3示出了车辆4相对于车辆1的运动状态变化的示意图。如图3所示，车辆1和车辆4在行驶过程中，车辆4可能会从车辆1所在车道切出至其他车道行驶，如：从车道1切出至车 道2。此时，车辆1同样需要及时监测到车辆4的这种运动状态的变化，以进行本车的路径规划。
目前，对其他车辆的运动状态进行监测的方式通常包括如下两种。
一种方式中，车辆可以通过传感器采集其他车辆的转向灯、其他车辆与其所在车道的车道线之间的横向距离、其他车辆的速度和加速度等信息，并根据所采集的前述信息预测其他车辆的行驶轨迹；然后，车辆可以根据预测的其他车辆的行驶轨迹，识别其他车辆是否进行变道。
以其他车辆为车辆B，本车为车辆A为例：图4示出了车辆A通过预测车辆B的行驶轨迹对车辆B的运动状态进行识别的示意图。如图4所示，当车辆A根据预测的车辆B的行驶轨迹，识别出车辆B会行驶出其所在车道、进入其他车道时，可以认为车辆B可能会进行变道。
但该方式中，在预测其他车辆的行驶轨迹时，对其他车辆的瞬时运动学信息较为敏感，容易导致对其他车辆的运动状态出现误识别。
同样以其他车辆为车辆B，本车为车辆A为例：图5示出了车辆A通过预测车辆B的行驶轨迹对车辆B的运动状态进行识别的另一示意图。如图5所示，当车辆B的驾驶员误操作导致车辆B突然出现偏移时，车辆A根据预测出的车辆B的行驶轨迹，可能会识别出车辆B将会进行变道，但实际上车辆B可能会继续保持在原车道行驶，从而使得车辆A对车辆B的运动状态出现误识别。
另一种方式中，车辆可以通过传感器采集其他车辆所在车道的车道线信息、其他车辆与其所在车道的车道线之间的横向距离和航向角等信息，并根据所采集的前述信息确定其他车辆的实际行驶轨迹，然后，将其他车辆的实际行驶轨迹与车辆行驶数据库中正常保持车道行驶的车辆的行驶轨迹进行对比，当两者距离大于一个设定的阈值时，即认为其他车辆正在进行变道。
继续以其他车辆为车辆B，本车为车辆A为例：图6示出了车辆A通过对比车辆行驶数据库中正常保持车道行驶的车辆的行驶轨迹对车辆B的运动状态进行识别的示意图。如图6所示，当车辆A识别出车辆B的实际行驶轨迹与车辆行驶数据库中正常保持车道行驶的车辆的行驶轨迹之间的距离超过一定阈值时，可以认为车辆B可能会进行变道。
但该方式中，在将其他车辆的实际行驶轨迹与车辆行驶数据库中正常保持车道行驶的车辆的行驶轨迹进行对比时，同样对其他车辆的瞬时运动学信息较为敏感，也容易导致对其他车辆的运动状态出现误识别。
同样以其他车辆为车辆B，本车为车辆A为例：图7示出了车辆A通过对比车辆行驶数据库中正常保持车道行驶的车辆的行驶轨迹对车辆B的运动状态进行识别的另一示意图。如图7所示，当车辆B的驾驶员误操作导致车辆B突然出现偏移时，车辆B当前偏移时的实际行驶轨迹与车辆行驶数据库中正常保持车道行驶的车辆的行驶轨迹之间的距离可能会超过一定阈值，车辆A可能会识别出车辆B将会进行变道，但实际上车辆B可能会继续保持在原车道行驶，从而也会使得车辆A对车辆B的运动状态出现误识别。
由上可知，目前对其他车辆的运动状态识别的方式，均对其他车辆的瞬时运动学信息比较敏感，容易导致对其他车辆的运动状态出现误识别。
基于此，本申请实施例提供一种车辆运动状态识别方法。通过该方法可以根据其他车辆所在车道的车道信息、其他车辆所在车道的第一相邻车道(如左侧相邻车道)的车 道信息和其他车辆所在车道的第二相邻车道(如右侧相邻车道)的车道信息中的至少两种，并结合其他车辆的位置信息和运动信息，对其他车辆的行驶轨迹进行预测，得到与前述至少两种车道信息一一对应的至少两条预测行驶轨迹。然后，可以根据前述至少两条预测行驶轨迹和本车所在车道的车道信息，对其他车辆相对于本车的运动状态进行识别。例如，识别其他车辆是否将变道至本车所在车道。
以本车为第一车辆、其他车辆为第二车辆为例，该车辆运动状态识别方法可以包括：获取第一车道信息、第二车道信息、以及第二车辆的位置信息和运动信息。其中，第一车道信息为第一车辆所在车道的车道信息；第二车道信息包括第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息中的至少两种。根据第二车道信息、以及第二车辆的位置信息和运动信息，确定第二车辆的至少两条预测行驶轨迹，每条预测行驶轨迹与第二车道信息所包含的每种车道信息相对应。根据至少两条预测行驶轨迹、以及第一车道信息，确定第二车辆相对于第一车辆的运动状态。
本申请实施例提供的该车辆运动状态识别方法中，由于第二车道信息包括第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息中的至少两种，所以，可以结合第二车辆的位置信息和运动信息，确定出与第二车道信息所包含的每种车道信息一一对应的至少两条预测行驶轨迹。根据至少两条预测行驶轨迹和第一车道信息，确定第二车辆相对于第一车辆的运动状态时，至少两条预测行驶轨迹可以起到彼此相互修正的作用，从而可以降低对第二车辆的瞬时运动学信息的敏感性，进而避免由于第二车辆的运动学信息发生瞬时变化而导致对第二车辆相对于第一车辆的运动状态出现误识别。
以下对本申请实施例提供的车辆运动状态识别方法进行示例性说明。
需要说明的是，在本申请的描述中，“第一”、“第二”等字样仅仅是为了区分描述，并不用于对某个特征的特别限定。本申请实施例的描述中，“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。本申请中所涉及的至少一个是指一个或多个；多个，是指两个或两个以上。
图8示出了本申请实施例提供的一种车辆的组成示意图。如图8所示，该车辆可以包括各种子系统，例如行进系统102、传感器系统104、控制系统106、一个或多个外围设备108、电源110、计算机系统112、用户接口116等。
可选地，该车辆还可以包括更多或更少的子系统，并且每个子系统可包括多个元件。另外，该车辆的每个子系统和元件可以通过有线或者无线互连。
行进系统102可包括为车辆提供动力运动的组件。在一个实施例中，行进系统102可包括引擎118、能量源119、传动装置120和车轮/轮胎121。引擎118可以是内燃引擎、电动机、空气压缩引擎或其他类型的引擎组合，例如汽油发动机和电动机组成的混动引擎，内燃引擎和空气压缩引擎组成的混动引擎。引擎118将能量源119转换成机械能量。
能量源119的示例包括汽油、柴油、其他基于石油的燃料、丙烷、其他基于压缩气体的燃料、乙醇、太阳能电池板、电池和其他电力来源。能量源119也可以为车辆的其他系统提供能量。
传动装置120可以将来自引擎118的机械动力传送到车轮121。传动装置120可包 括变速箱、差速器和驱动轴。在一个实施例中，传动装置120还可以包括其他器件，比如离合器。其中，驱动轴可包括可耦合到一个或多个车轮121的一个或多个轴。
传感器系统104可以包括感测关于车辆周边的环境的信息的若干个传感器。例如，传感器系统104可包括定位系统122(定位系统122可以是GPS系统，也可以是北斗系统或者其他定位系统)、惯性测量单元(inertial measurement unit，IMU)124、雷达126、激光测距仪128、以及相机130。传感器系统104还可以包括车辆的内部系统的传感器，例如，车内空气质量监测器、燃油量表、机油温度表等。来自这些传感器中的一个或多个的传感器数据可用于检测对象及其相应特性(位置、形状、方向、速度等)。
定位系统122可用于估计车辆的地理位置。IMU 124用于基于惯性加速度来感测车辆的位置和朝向变化。在一个实施例中，IMU 124可以是加速度计和陀螺仪的组合。
雷达126可利用无线电信号来感测车辆的周边环境内的物体。在一些实施例中，除了感测物体以外，雷达126还可用于感测物体的速度和/或前进方向。
激光测距仪128可利用激光来感测车辆所位于的环境中的物体。在一些实施例中，激光测距仪128可包括一个或多个激光源、激光扫描器以及一个或多个检测器，以及其他系统组件。
相机130可用于捕捉车辆的周边环境的多个图像。相机130可以是静态相机或视频相机。
控制系统106为控制车辆及其组件的操作系统。控制系统106可以包括：转向系统132、油门134、制动单元136、计算机视觉系统138、路线控制系统140以及障碍物避免系统142。
转向系统132可操作来调整车辆的前进方向。例如在一个实施例中可以为方向盘系统。
油门134用于控制引擎118的操作速度并进而控制车辆的速度。
制动单元136用于控制车辆减速。制动单元136可使用摩擦力来减慢车轮121。在其他实施例中，制动单元136可将车轮121的动能转换为电流。制动单元136也可采取其他形式来减慢车轮121转速从而控制车辆的速度。
计算机视觉系统138可以操作来处理和分析由相机130捕捉的图像以便识别车辆周边环境中的物体和/或特征。所述物体和/或特征可包括交通信号、道路边界和障碍物。计算机视觉系统138可使用物体识别算法、运动中恢复结构(structure from motion，SFM)算法、视频跟踪和其他计算机视觉技术。在一些实施例中，计算机视觉系统138可以用于为环境绘制地图、跟踪物体、估计物体的速度等等。
路线控制系统140用于确定车辆的行驶路线。在一些实施例中，路线控制系统140可结合来自传感器104和一个或多个预定地图的数据以为车辆确定行驶路线。
障碍物避免系统142用于识别、评估和避免或者以其他方式越过车辆的环境中的潜在障碍物。
当然，在一个实例中，控制系统106可以增加或替换地包括除了所示出和描述的那些以外的组件。或者也可以减少一部分上述示出的组件。
车辆通过外围设备108与外部传感器、其他车辆、其他计算机系统或用户之间进行交互。外围设备108可包括无线通信系统146、车载电脑148、麦克风150和/或扬声器152。
在一些实施例中，外围设备108提供车辆的用户与用户接口116交互的手段。例如， 车载电脑148可向车辆100的用户提供信息。用户接口116还可操作车载电脑148来接收用户的输入。车载电脑148可以通过触摸屏进行操作。在其他情况中，外围设备108可提供用于车辆与位于车内的其它设备通信的手段。例如，麦克风150可从车辆的用户接收音频(例如，语音命令或其他音频输入)。类似地，扬声器152可向车辆的用户输出音频。
无线通信系统146可以直接地或者经由通信网络来与一个或多个设备无线通信。例如，无线通信系统146可使用3G蜂窝通信，例如码分多址系统(code division multiple access，CDMA)、EVD0、GSM/GPRS，或者4G蜂窝通信，例如LTE。或者5G蜂窝通信。无线通信系统146可利用WiFi与无线局域网(wireless local area network，WLAN)通信。在一些实施例中，无线通信系统146可利用红外链路、蓝牙或ZigBee与设备直接通信。其他无线协议，例如各种车辆通信系统，例如，无线通信系统146可包括一个或多个专用短程通信(dedicated short range communications，DSRC)设备，这些设备可包括车辆和/或路边台站之间的公共和/或私有数据通信。
电源110可向车辆的各种组件提供电力。在一个实施例中，电源110可以为可再充电锂离子或铅酸电池。这种电池的一个或多个电池组可被配置为电源为车辆的各种组件提供电力。在一些实施例中，电源110和能量源119可一起实现，例如一些全电动车中那样。
车辆的部分或所有功能受计算机系统112控制。计算机系统112可包括至少一个处理器113，处理器113执行存储在例如存储器114这样的非暂态计算机可读介质中的指令115。计算机系统112还可以是采用分布式方式控制车辆的个体组件或子系统的多个计算设备。
处理器113可以是任何常规的处理器，诸如商业可获得的CPU。替选地，该处理器可以是诸如ASIC或其它基于硬件的处理器的专用设备。尽管图8功能性地图示了处理器、存储器，但是本领域的普通技术人员应该理解该处理器或存储器实际上可以包括可以或者可以不存储在相同的物理外壳内的多个处理器或存储器。例如，存储器可以是硬盘驱动器或位于不同物理外壳内的其它存储介质。因此，对处理器引用将被理解为包括对可以或者可以不并行操作的处理器或存储器的集合的引用。不同于使用单一的处理器来执行此处所描述的步骤，诸如转向组件和减速组件的一些组件每个都可以具有其自己的处理器，所述处理器只执行与特定于组件的功能相关的计算。
在此处所描述的各个方面中，处理器可以位于远离该车辆并且与该车辆进行无线通信。在其它方面中，此处所描述的过程中的一些在布置于车辆内的处理器上执行而其它则由远程处理器执行，包括采取执行单一操纵的必要步骤。
在一些实施例中，存储器114可包含指令11(例如，程序逻辑)，指令115可被处理器113执行来执行车辆的各种功能，包括以上描述的那些功能。存储器114也可包含额外的指令，包括向推进系统102、传感器系统104、控制系统106和外围设备108中的一个或多个发送数据、从其接收数据、与其交互和/或对其进行控制的指令。
除了指令115以外，存储器114还可存储数据，例如道路地图、路线信息，车辆的位置、方向、速度以及其它这样的车辆数据，以及其他信息。这种信息可在车辆在自主、半自主和/或手动模式中操作期间被车辆和计算机系统112使用。
用户接口116，用于向车辆的用户提供信息或从其接收信息。可选地，用户接口116可包括在外围设备108的集合内的一个或多个输入/输出设备，例如，无线通信系统146、 车车在电脑148、麦克风150和扬声器152。
计算机系统112可基于从各种子系统(例如，行进系统102、传感器系统104和控制系统106)以及从用户接口116接收的输入来控制车辆的功能。例如，计算机系统112可利用来自控制系统106的输入以便控制转向单元132来避免由传感器系统104和障碍物避免系统144检测到的障碍物。在一些实施例中，计算机系统112可操作来对车辆100及其子系统的许多方面提供控制。
可选地，上述这些组件中的一个或多个可与车辆分开安装或关联。例如，存储器114可以部分或完全地与车辆分开存在。上述组件可以按有线和/或无线方式来通信地耦合在一起。
可选地，上述组件只是一个示例，实际应用中，上述各个模块中的组件有可能根据实际需要增添或者删除，图8不应理解为对本申请实施例的限制。
在道路行进的自动驾驶汽车，如上面的车辆，可以识别其周围环境内的物体以确定对当前速度的调整。所述物体可以是其它车辆、交通控制设备、或者其它类型的物体。在一些示例中，可以独立地考虑每个识别的物体，并且基于物体的各自的特性，诸如它的当前速度、加速度、与车辆的间距等，可以用来确定自动驾驶汽车所要调整的速度。
可选地，车辆或者与车辆相关联的计算设备(如图8的计算机系统112、计算机视觉系统138、处理器113)可以基于所识别的物体的特性和周围环境的状态(例如，交通、雨、道路上的冰等)来预测所述识别的物体的行为。可选地，每一个所识别的物体都依赖于彼此的行为，因此还可以将所识别的所有物体全部一起考虑来预测单个识别的物体的行为。车辆能够基于预测的所述识别的物体的行为来调整它的速度。换句话说，车辆能够基于所预测的物体的行为来确定车辆将需要调整到(例如，加速、减速、或者停止)什么稳定状态。在这个过程中，也可以考虑其它因素来确定车辆的速度，诸如，其他车辆在行驶的道路中的横向位置、道路的曲率、静态和动态物体的接近度等。
可选地，图8所示的车辆可以是具备有或没有驾驶员时在公共道路和高速公路上行驶的能力的轿车、卡车、摩托车、公共汽车、游乐场车辆等，本申请实施例不做特别的限定。
在示例性实施例中，本申请实施例提供的车辆运动状态识别方法可以应用于前述图8所示的车辆，例如，可以由车辆中的某个处理器执行，或者由计算机系统执行。又或者，在其他示例性实施例中，本申请实施例提供的车辆运动状态识别方法也可以应用于与前述图8所示的车辆通信连接的服务器，如：云服务器，该服务器可以远程操控车辆进行无人驾驶。本申请对车辆运动状态识别方法的应用主体并不作限制。
同样以本车为第一车辆、其他车辆为第二车辆为例，图9示出了本申请实施例提供的车辆运动状态识别方法的流程示意图。
如图9所示，该方法中，首先，可以执行S901-S903，获取第一车道信息、第二车道信息、以及第二车辆的位置信息和运动信息。
S901、获取第一车辆所在车道的车道信息作为第一车道信息。
第一车辆所在车道的车道信息是指第一车辆所在车道的车道中轴线的轨迹信息。以第一车辆为图1中所示的车辆1为例，车辆1所在车道的车道信息是指车道1的车道中轴线的轨迹(图1中虚线所示)。
以下对获取第一车道信息的过程进行说明。
第一车道信息可以通过如下曲线表达式进行表示。
y ego,t(x)＝a 3,tx 3+a 2,tx 2+a 1,tx+a 0,t。
其中，a 3,t表示第一车道信息中的车道中轴线在t时刻的轨迹的曲率变化率的六分之一；a 2,t表示第一车道信息中的车道中轴线在t时刻的轨迹的曲率的二分之一；a 1,t表示第一车道信息中的车道中轴线在t时刻的轨迹的切线斜率；a 0,t表示第一车道信息中的车道中轴线在t时刻的轨迹的横向偏移。
按照上述曲线表达式对第一车辆所在车道的车道中轴线的轨迹进行拟合，即可得到第一车辆所在车道的车道信息，即第一车道信息。
S902、获取第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息中的至少两种，作为第二车道信息。
例如，一种实施方式中，第二车道信息可以包括第二车辆所在车道的车道信息、以及第二车辆所在车道的第一相邻车道的车道信息。另一种实施方式中，第二车道信息可以包括第二车辆所在车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息。又一种实施方式中，第二车道信息可以包括第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息。又或者，第二车道信息可以包括第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息中的三种全部。
其中，第二车辆所在车道的车道信息是指第二车辆所在车道的车道中轴线的轨迹信息，第二车辆所在车道的第一相邻车道的车道信息是指第二车辆所在车道的第一相邻车道的车道中轴线的轨迹信息，第二车辆所在车道的第二相邻车道的车道信息是指第二车辆所在车道的第二相邻车道的车道中轴线的轨迹信息。
请参考图1所示，以第二车辆为车辆4为例，车辆4所在车道(车道1)的第一相邻车道为车道2、第二相邻车道为车道3，或者，第一相邻车道为车道3、第二相邻车道为车道2。也即，第一相邻车道和第二相邻车道为分别为车辆4所在车道的左右相邻车道。车道1、车道2、车道3的车道信息分别是其对应的车道中轴线的轨迹。
以下对获取第二车道信息的过程进行说明。
第二车道信息可以通过如下曲线表达式进行表示。
y i,t(x)＝b i 3,tx 3+b i 2,tx 2+b i 1,tx+b i 0,t，i＝0,1,2。
其中，当i＝0时，y i,t(x)即为y 0,t(x)，表示第二车辆所在车道的车道信息；当i＝1时，y i,t(x)即为y 1,t(x)，表示第二车辆所在车道的第一相邻车道的车道信息；当i＝2时，y i,t(x)即为y 2,t(x)，表示第二车辆所在车道的第二相邻车道的车道信息；b i 3,t表示i对应的车道信息中的车道中轴线在t时刻的轨迹的曲率变化率的六分之一；b i 2,t表示i对应的车道信息中的车道中轴线在t时刻的轨迹的曲率的二分之一；b i 1,t表示i对应的车道信息中的车道中轴线在t时刻的轨迹的切线斜率；b i 0,t表示i对应的车道信息中的车道中轴线在t时刻的轨迹的横向偏移。
需要说明的是，若第二车辆所在车道不存在第一相邻车道(如左侧车道)，则上述第二车道信息的曲线表达式中，i等于1时对应的b i 3,t、b i 2,t、b i 1,t、b i 0,t等参数系数均为255。若第二车辆所在车道不存在第二相邻车道(如右侧车道)，则上述第二车道信息的曲线表达式中，i等于2时对应的b i 3,t、b i 2,t、b i 1,t、b i 0,t等参数系数也均为255。
按照上述曲线表达式对第二车辆所在车道的车道中轴线的轨迹、第二车辆所在车道的第一相邻车道的车道中轴线的轨迹、以及第二车辆所在车道的第二相邻车道的车道中 轴线的轨迹进行拟合，即可得到与之对应的第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息。
S903、获取第二车辆的位置信息和运动信息。
可选地，第一车辆上的传感器系统(如：雷达、距离传感器等)和定位系统(如：GPS、北斗)可以按照固定的周期采集第二车辆的位置信息和运动信息，并上传给第一车辆。第二车辆的位置信息则是指第二车辆在每个周期时刻t的位置信息(x t,y t,θ t)，其中，x t表示第二车辆的横坐标，y t表示第二车辆的纵坐标，θ t表示第二车辆的航向角。第二车辆的位置信息可以是第二车辆相对于第一车辆的相对位置，也可以是第二车辆的绝对位置。第二车辆的运动信息则是指第二车辆在每个周期时刻t的速度v x,t、加速度a x,t、轨迹曲率γ t等运动学信息。
需要说明的是，本申请对S901、S902及S903之间的执行顺序并不作限制，可以是并行执行，也可以是某个步骤先执行或后执行。
在通过上述S901-S903获取到第一车道信息、第二车道信息、以及第二车辆的位置信息和运动信息后，可以通过下述S904-S907确定第二车辆相对于第一车辆的运动状态。
S904、根据第二车道信息、以及第二车辆的位置信息和运动信息，确定第二车辆的至少两条预测行驶轨迹，每条预测行驶轨迹与第二车道信息所包含的每种车道信息相对应。
例如，当第二车道信息包括第二车辆所在车道的车道信息、以及第二车辆所在车道的第一相邻车道的车道信息时，可以相应确定出第二车辆在当前所在车道保持行驶的预测行驶轨迹、以及第二车辆变道至所在车道的第一相邻车道行驶的预测行驶轨迹。
或者，当第二车道信息包括第二车辆所在车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息时，可以相应确定出第二车辆在当前所在车道保持行驶的预测行驶轨迹、以及第二车辆变道至所在车道的第二相邻车道行驶的预测行驶轨迹。
又或者，当第二车道信息可以包括第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息时，可以相应确定出第二车辆变道至所在车道的第一相邻车道行驶的预测行驶轨迹、以及第二车辆变道至所在车道的第二相邻车道行驶的预测行驶轨迹。
又或者，当第二车道信息包括第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息中的三种全部时，可以相应确定出第二车辆在当前所在车道保持行驶的预测行驶轨迹、第二车辆变道至所在车道的第一相邻车道行驶的预测行驶轨迹、以及第二车辆变道至所在车道的第二相邻车道行驶的预测行驶轨迹。
下面以第二车道信息包括第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息中的三种全部为例，对预测行驶轨迹的具体确定方式进行说明。
1)关于第二车辆在当前所在车道保持行驶的预测行驶轨迹。
假设第二车辆会由当前位置调整方向盘和速度回归到其所在车道的车道中轴线附近，则可以采用多项式拟合对第二车辆在当前所在车道保持行驶的路径进行规划。
例如，根据第二车辆的当前位置、航向角、路径曲率、以及第二车辆回到其所在车道的车道中轴线满足的横向位置、一阶和二阶相容性等6个条件，可以进行四次多项式拟合得到如下方程(或可称之为多项式拟合模型)来表示第二车辆在当前所在车道保持行 驶的预测行驶轨迹。
z 0,t(x)＝c 0 4,tx 4+c 0 3,tx 3+c 0 2,tx 2+c 0 1,tx+c 0 0,t。
该多项式满足条件
Figure PCTCN2021107918-appb-000001
上述方程中，c 0 4,t、c 0 3,t、c 0 2,t、c 0 1,t以及c 0 0,t等五个参数可通过上述相容性条件拟合得到，在此不表示特别含义。
2)关于第二车辆变道至所在车道的第一相邻车道或第二相邻车道行驶的预测行驶轨迹。
以第一相邻车道为第二车辆所在车道的左侧车道、第二相邻车道为第二车辆所在车道的右侧车道为例，假设第二车辆会由当前位置变道至左侧车道或右侧车道，则同样可以根据第二车辆的位置信息、运动学信息以及所要变换到达车道的道路信息进行四次多项式拟合，得到如下方程(或可称之为多项式拟合模型)来表示第二车辆变道至所在车道的第一相邻车道或第二相邻车道行驶的预测行驶轨迹。
z i,t(x)＝c i 4,tx 4+c i 3,tx 3+c i 2,tx 2+c i 1,tx+c i 0,t,i＝1,2。
其中，i＝1表示变道至左侧车道；i＝2表示变道至右侧车道。
该多项式满足条件
Figure PCTCN2021107918-appb-000002
上述方程中，c i 4,t、c i 3,t、c i 2,t、c i 1,t以及c i 0,t等五个参数可通过上述相容性条件拟合得到，在此不表示特别含义。
或者，也有一些实施例中，也可以不采用上述多项式拟合的方式，而是采用Bessel函数等其他拟合函数、或者基于驾驶数据库提取，获取第二车辆在当前所在车道保持行驶的预测行驶轨迹、以及第二车辆变道至所在车道的第一相邻车道或第二相邻车道行驶的预测行驶轨迹，本申请在此不作限制。
在执行S904获取到至少两条预测行驶轨迹后，可以先执行S905和S906，基于所获取的至少两条预测行驶轨迹，确定出第二车辆的目标预测行驶轨迹，然后执行S907，根据目标预测行驶轨迹、以及第一车道信息，确定第二车辆相对于第一车辆的运动状态。
S905、确定每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度。
一些实施例中，可以获取第二车辆的历史行驶轨迹在第一预设时段内的第一横向坐标向量，第一横向坐标向量用于指示历史行驶轨迹与第二车辆所在车道的车道线之间的距离向量。然后，针对至少两条预测行驶轨迹中每条预测行驶轨迹：获取该预测行驶轨迹在第二预设时段内的第二横向坐标向量，第二横向坐标向量用于指示该预测行驶轨迹与第二车辆所在车道的车道线之间的距离向量，并根据第二横向坐标向量、以及上述第一横向坐标向量确定该预测行驶轨迹与历史行驶轨迹之间的相似度，从而得到每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度。
其中，第二车辆的历史行驶轨迹在第一预设时段内的第一横向坐标向量中包括第二车辆的历史行驶轨迹在第一预设时段内的多个第一横向坐标。预测行驶轨迹在第二预设时段内的第二横向坐标向量包括预测行驶轨迹在第二预设时段内的多个第二横向坐标。
一些实施方式中，第一预设时段可以是多个连续的第一预设周期组成的时段，每个 第一预设周期内可以包含有至少一个第一横向坐标。第二预设时段可以是多个连续的第二预设周期组成的时段，每个第二预设周期内可以包含有至少一个第二横向坐标。
举例说明，由于驾驶员保持或者变换道路是一个持续过程(假设第二车辆为某个驾驶员驾驶的车辆)，在相应场景出现明显特征之前驾驶员会有相应的调整。鉴于此，本申请可以先确定第二车辆的历史行驶轨迹在第一预设时段内的多个第一横向坐标构成的第一横向坐标时间序列(即前述第一横向坐标向量)，以及每条预测行驶轨迹在第二预设时段内的多个第二横向坐标构成的第二横向坐标时间序列(即前述第二横向坐标向量)。然后，可以计算第一横向坐标时间序列和第二横向坐标时间序列之间的相似度，得到第二车辆的历史行驶轨迹与预测行驶轨迹之间的相似度。
以当前时刻为t，第一预设时段为(t-MΔT、t-(M-1)ΔT、…、t)等M+1个第一预设周期，第二预设时段为(M+N、M+N-1、M)等N+1个第二预设周期为例。
历史行驶轨迹在第一预设时段内的第一横向坐标构成的第一横向坐标时间序列可以表示为如下Y t,h。
Y t,h＝(y t-MΔT,y t-(M-1)ΔT,…,y t)。
其中，Y t,h表示第一横向坐标时间序列；y t-MΔT表示在t-MΔT时刻的第一横向坐标，以此类推。
在示例性实施例中，M大小可以为20；N大小可以为10；ΔT为采样周期，大小可以为0.02s的整数倍。
预测行驶轨迹在第二预设时段内的第二横向坐标构成的第二横向坐标时间序列可以表示为如下Y i t,p。
Y i t,p＝(z i N(t-MΔT),z i N(t-(M-1)ΔT),…,z i N(t)),i＝0,1,2。
z i N(t-(M-j)ΔT)＝z i,t-(M+N-j)(x t-(M-j)ΔT),j＝0,1,2…,M。
其中，i＝0表示保持车道；i＝1表示变道至左侧车道；i＝2表示变道至右侧车道；Y i t,p表示第二横向坐标时间序列。z i N(t-(M-j)ΔT)表示为在t-(M-j)ΔT时刻预测的第二车辆的纵向位置为x t-(M-j)ΔT时，其所在的横向位置。
进一步，第一横向坐标时间序列Y t,h和第二横向坐标时间序列Y i t,p(i＝0,1,2)之间的相似度可以表示为
Figure PCTCN2021107918-appb-000003
ρ i t具体可以如下。
Figure PCTCN2021107918-appb-000004
其中，i＝0表示保持车道；i＝1表示变道至左侧车道；i＝2表示变道至右侧车道；
Figure PCTCN2021107918-appb-000005
则可以理解为i＝0,1,2时对应的预测行驶轨迹与历史行驶轨迹之间的相似度
Figure PCTCN2021107918-appb-000006
Y t,h(j)表示Y t,h的第j个分量；Y i t,p(j)表示Y i t,p的第j个分量；a j(j＝0,..M)分别代表从当前时刻往前j个周期中预测行驶轨迹和历史行驶轨迹之间差异的权重，满足下述条件。
Figure PCTCN2021107918-appb-000007
需要说明的是，a j的值可以是将每个a j对应的第j个周期与当前时刻t的时间差的倒数作为a j的初始值，并进行归一化后得到，在此不再详述。
另外一些实施例中，也可以通过计算余弦相似度、马氏距离、欧氏距离等数学方法，确定至少两条预测行驶轨迹中每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，在此不作限制。
S906、根据至少两条预测行驶轨迹、以及每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹。
基于通过上述S905所确定出的至少两条预测行驶轨迹中每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，在一种可能的设计中，根据至少两条预测行驶轨迹、 以及每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹可以是指：从至少两条预测行驶轨迹中选择与第二车辆的历史行驶轨迹之间的相似度最高的一条预测行驶轨迹作为第二车辆的目标预测行驶轨迹。由于这样选取的目标预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度最高，所以，是前述至少两条预测行驶轨迹中最可能接近于第二车辆未来的实际行驶轨迹的一条预测行驶轨迹。
在另外一种可能的设计中，在得到至少两条预测行驶轨迹中每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度后，也可以先根据每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，预测每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度，然后根据至少两条预测行驶轨迹、以及每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹。
例如，可以对每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度进行归一化，预测每条预测行驶轨迹的概率，该概率可以指示每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度。然后，可以结合每条预测行驶轨迹的概率，以及前述至少两条预测行驶轨迹进行综合计算，得到第二车辆的目标预测行驶轨迹。
下面以第二车辆在当前所在车道保持行驶的预测行驶轨迹、第二车辆变道至所在车道的左侧车道行驶的预测行驶轨迹、第二车辆变道至所在车道的右侧车道行驶的预测行驶轨迹等三条预测行驶轨迹对确定目标预测行驶轨迹的过程进行举例说明。但需要说明的是，实际上也可以是根据前述三条预测行驶轨迹中的任意两条确定目标预测行驶轨迹，在此不再赘述。
以上述相似度
Figure PCTCN2021107918-appb-000008
为例，通过对每条预测行驶轨迹对应的ρ i t进行归一化，可以初步得到预测行驶轨迹对应的概率，可以表示为如下
Figure PCTCN2021107918-appb-000009
Figure PCTCN2021107918-appb-000010
其中，i＝0表示保持车道；i＝1表示变道至左侧车道；i＝2表示变道至右侧车道。
进一步，第二车辆在当前所在车道保持行驶的预测行驶轨迹对应的概率可以表示为如下P 0 t。
Figure PCTCN2021107918-appb-000011
第二车辆变道至所在车道的左侧车道行驶的预测行驶轨迹对应的概率可以表示为如下P 1 t。
Figure PCTCN2021107918-appb-000012
第二车辆变道至所在车道的右侧车道行驶的预测行驶轨迹对应的概率可以表示为如下P 2 t。
Figure PCTCN2021107918-appb-000013
在得到预测行驶轨迹对应的上述概率P 0 t、P 1 t和P 2 t后，可以结合三条预测行驶轨迹，综合计算目标预测行驶轨迹。
如前述实施例中所述，假设用z i,t(x)表示预测行驶轨迹，其中，i＝0表示保持车道；i＝1表示变道至左侧车道；i＝2表示变道至右侧车道，则目标预测行驶轨迹可以通过下述z t(x)来进行表示。
Figure PCTCN2021107918-appb-000014
可选地，由于第二车辆进行向左变道或者向右变道不会同时出现，所以，本申请一些实施例中，在根据前述三条预测行驶轨迹确定目标预测行驶轨迹时，可以将三条预测行驶轨迹分别对应的概率中的最小值修正为0，以进一步使得所确定的目标预测行驶轨迹更接近实际行驶轨迹，从而提高后续车辆运动状态识别的准确性。例如，若第二车辆进行向左变道的预测行驶轨迹对应的概率最小，则可以将其修正为0，只根据第二车辆进行向右变道的预测行驶轨迹和保持车道的预测行驶轨迹，及其分别对应的概率，确定目标预测行驶轨迹。
在又一种可能的设计中，在根据每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，预测出每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度后，也可以直接选择与第二车辆的真实行驶轨迹之间的相似度最大的一条预测行驶轨迹作为第二车辆的目标预测行驶轨迹。
例如，根据至少两条预测行驶轨迹中每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，分别确定出每条预测行驶轨迹的概率后，可以直接选择概率最大的一条预测行驶轨迹作为第二车辆的目标预测行驶轨迹。
该设计与前述第一种直接选择相似度最高的一条预测行驶轨迹作为第二车辆的目标预测行驶轨迹的方式相似，所确定的预测行驶轨迹为前述至少两条预测行驶轨迹中最可能接近于第二车辆未来的实际行驶轨迹的一条预测行驶轨迹。
需要说明的是，本申请对根据至少两条预测行驶轨迹、以及至少两条预测行驶轨迹中每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹的具体方式并不作限制。
S907、根据目标预测行驶轨迹、以及第一车道信息，确定第二车辆相对于第一车辆的运动状态。
如上所述，第一车道信息是指第一车辆所在车道的车道中轴线的轨迹信息。在得到目标预测行驶轨迹后，可以结合第一车道信息，通过判断目标预测行驶轨迹与第一车辆所在车道的车道中轴线之间的距离(如：最小横向距离、最大横向距离)的大小，确定第二车辆相对于第一车辆的运动状态，如：第二车辆是否会从其他车道切入第一车辆所在车道、第二车辆是否会从第一车辆所在车道切出至其他车道等。
例如，图10示出了本申请实施例提供的车辆运动状态识别方法的另一流程示意图。
如图10所示，S907可以包括：S1001-S1006。
S1001、根据目标预测行驶轨迹、以及第一车道信息，确定目标预测行驶轨迹与第一车辆所在车道的车道线在预设纵向长度内的最小横向距离、最小横向距离对应的第一纵向位置，以及最大横向距离、最大横向距离对应的第二纵向位置。
如上所述，第一车道信息可以是第一车辆所在车道的车道中轴线。
以第一车辆为车辆A，第二车辆为车辆B为例，图11示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的示意图。
如图11所示，假设预设纵向长度为[a,b]，则a所在的位置可以是沿着车道中轴线的方向上靠近于车辆B的位置，或者与车辆B的纵向坐标相同的位置。相应地，b所在的位置是沿着车道中轴线的方向上远离车辆B的位置。可以理解的，预设纵向长度[a,b]仅仅用于限定沿着车道中轴线的方向上的一定范围。
目标预测行驶轨迹z t(x)与车辆A所在车道的车道中轴线y ego,t在预设纵向长度[a,b]内的最小横向距离d min，可以表示为
Figure PCTCN2021107918-appb-000015
目标预测行驶轨迹z t(x)与车辆A所在车道的车道中轴线y ego,t在预设纵向长度[a,b]内的最大横向距离d max，可以表示为
Figure PCTCN2021107918-appb-000016
最小横向距离对应的第一纵向位置是指目标预测行驶轨迹中d min所在的位置。第二纵向位置是指目标预测行驶轨迹中d max所在的位置。
S1002、若最小横向距离大于第一阈值，则确定第二车辆相对于第一车辆的运动状态为与第一车辆保持在不同车道行驶。
可选地，第一阈值d 1的大小可以为第一车辆的车身一半的宽度加30厘米，或者，也可以是大小与其接近的值。
当最小横向距离d min大于第一阈值d 1时，可以确定第二车辆不会进入第一车辆所在的车道，可以认为第二车辆相对于第一车辆的运动状态为与第一车辆保持在不同车道行驶，如：可以表示为
相对状态(objectState)＝通过(passby)。
举例说明：图12示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的另一示意图。如图12所示，若车辆B的目标预测行驶轨迹距离车辆A所在车道的车道中轴线之间的最小横向距离d min大于第一阈值d 1，则确定车辆B相对于车辆A的运动状态为objectState＝passby。
S1003、若最小横向距离小于第一阈值、且最大横向距离大于第二阈值，则确定第二车辆相对于第一车辆的运动状态为穿过第一车辆所在车道；其中，第二阈值大于第一阈值。
可选地，第二阈值d 2的大小可以为第一车辆所在车道的宽度加30厘米，或者，也可以是大小与其接近的值。可以明显得知，第二阈值d 2远大于第一阈值d 1。
当最小横向距离d min小于第一阈值d 1，且最大横向距离d max又大于第二阈值d 2时，可以确定第二车辆会进入第一车辆所在的车道，同时会有较大的横向偏移，可以认为第二车辆相对于第一车辆的运动状态为穿过第一车辆所在车道，如：可以表示为
objectState＝穿过(cross)。
举例说明：图13示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的又一示意图。如图13所示，若车辆B的目标预测行驶轨迹距离车辆A所在车道的车道中轴线之间的最小横向距离d min小于第一阈值d 1，且最大横向距离d max又大于第二阈值d 2时，可以确定车辆B会进入车辆A所在的车道，同时会有较大的横向偏移，可以认为车辆B相对于车辆A的运动状态为穿过车辆A所在车道，如：可以表示为objectState＝cross。
S1004、若最大横向距离小于第三阈值，则确定第二车辆相对于第一车辆的运动状态为与第一车辆保持在同一车道行驶；其中，第三阈值小于第一阈值。
可选地，第三阈值d 3的大小可以为第一车辆的车身一半的宽度减去30厘米，或者，也可以是大小与其接近的值。可以明显得知，第三阈值d 3小于第一阈值d 1。
当最大横向距离d max小于第三阈值d 3时，可以确定第二车辆相对于第一车辆的运动状态为与第一车辆保持在同一车道行驶，如：可以表示为
objectState＝(跟随)follow。
当然，可以理解的，S1004中，可能是第二车辆跟随第一车辆行驶，也可能是第一车 辆跟随第二车辆行驶。
举例说明：图14示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的又一示意图。如图14所示，若车辆B的目标预测行驶轨迹距离车辆A所在车道的车道中轴线之间的最大横向距离d max小于第三阈值d 3时，可以确定车辆B相对于车辆A的运动状态为与车辆A保持在同一车道行驶，如：可以表示为objectState＝follow。此时，最小横向距离d min一定小于第三阈值d 3，不再赘述。
S1005、若最小横向距离小于第一阈值，最大横向距离大于第三阈值、小于第二阈值，且目标预测行驶轨迹中第二纵向位置出现的时间早于第一纵向位置出现的时间，则确定第二车辆相对于第一车辆的运动状态为切入第一车辆所在车道。
举例说明：图15示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的又一示意图。如图15所示，若车辆B的目标预测行驶轨迹距离车辆A所在车道的车道中轴线之间的最小横向距离d min小于第一阈值d 1，最大横向距离d max大于第三阈值d 3、小于第二阈值d 2，且目标预测行驶轨迹中第二纵向位置x max出现的时间早于第一纵向位置x min出现的时间，则可以确定车辆B相对于车辆A的运动状态为切入车辆A所在车道，如：可以表示为objectState＝切入(cut_in)。
S1006、若最小横向距离小于第一阈值，最大横向距离大于第三阈值、小于第二阈值，且目标预测行驶轨迹中第一纵向位置出现的时间早于第二纵向位置出现的时间，则确定第二车辆相对于第一车辆的运动状态为切出第一车辆所在车道。
举例说明：图16示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的又一示意图。如图16所示，若车辆B的目标预测行驶轨迹距离车辆A所在车道的车道中轴线之间的最小横向距离d min小于第一阈值d 1，最大横向距离d max大于第三阈值d 3、小于第二阈值d 2，且目标预测行驶轨迹中第一纵向位置x min出现的时间早于第二纵向位置x max出现的时间，则可以确定车辆B相对于车辆A的运动状态为切出车辆A所在车道，如：可以表示为objectState＝切出(cut_out)。
需要说明的，上述S1002-S1006的示例性说明中，虽然均是以大于或小于某个阈值的场景对第二车辆相对于第一车辆的运动状态进行划分，但是在实际实施时，可能还需要考虑到等于某个阈值的场景，如：一些实施方式中，可以将最小横向距离d min等于第一阈值d 1的场景与大于第一阈值d 1的场景划分到一起，或者，另外一些实施方式中，也可以将最小横向距离d min等于第一阈值d 1的场景与小于第一阈值d 1的场景划分到一起等，本申请在此并不作限制。与其他阈值的比较均与此类似，不再一一赘述。
在一种可能的设计中，当S1005中确定出第二车辆相对于第一车辆的运动状态为切入第一车辆所在车道时，该方法还可以根据最小横向距离对应的第一纵向位置，与预设纵向长度靠近于第一车辆的一端之间的纵向距离，将第二车辆相对于第一车辆的运动状态进一步细化为按照第一切入状态切入第一车辆所在车道，或按照第二切入状态切入第一车辆所在车道。
或者，当S1006中确定出第二车辆相对于第一车辆的运动状态为切出第一车辆所在车道时，该方法还可以根据最小横向距离对应的第一纵向位置，与预设纵向长度靠近于第一车辆的一端之间的纵向距离，将第二车辆相对于第一车辆的运动状态进一步细化为按照第一切出状态切出第一车辆所在车道，或按照第二切出状态切出第一车辆所在车道。
例如，第一切入状态可以称为紧密切入状态，第一切出状态可以称为紧密切出状态。第二切入状态可以称为正常切入状态，第二切出状态可以称为正常切出状态。或者，也 可以将第一/第二切入状态、第一/第二切出状态称为其他名称。
以下以第一切入状态称为紧密切入状态，第一切出状态称为紧密切出状态，第二切入状态称为正常切入状态，第二切出状态称为正常切出状态为例，分别对将第二车辆相对于第一车辆的运动状态进一步细化为紧密切入或正常切入的情况，以及将第二车辆相对于第一车辆的运动状态进一步细化为紧密切出或正常切出的情况进行举例说明。
图17示出了本申请实施例提供的车辆A根据车辆B的目标预测行驶轨迹对车辆B的运动状态进行识别的又一示意图。
以图17所示为例，可以根据最小横向距离对应的第一纵向位置与预设纵向长度a端之间的纵向距离，也即，第一纵向位置在与第一车辆所在车道的车道线的平行方向上与预设纵向长度a端之间的距离，对第二车辆相对于第一车辆的运动状态进一步细化。当确定出第二车辆相对于第一车辆的运动状态为切入第一车辆所在车道时，若纵向距离小于第四阈值(如：1米、2米、3米等，在此不作限制)，则确定第二车辆相对于第一车辆的运动状态为紧密切入(close_cut_in)第一车辆所在车道。若纵向距离大于第四阈值，则确定第二车辆相对于第一车辆的运动状态为正常切入(general_cut_in)第一车辆所在车道。
容易理解的，若纵向距离等于第四阈值，则可以确定第二车辆相对于第一车辆的运动状态为紧密切入第一车辆所在车道，或者，正常切入第一车辆所在车道，在此不作限制。
类似地，也可以根据最小横向距离对应的第一纵向位置与预设纵向长度a端之间的纵向距离，也即，第一纵向位置在与第一车辆所在车道的车道线的平行方向上与预设纵向长度a端之间的距离，将第二车辆相对于第一车辆的运动状态进一步细化为紧密切出或正常切出的情况进行举例说明。如：当确定出第二车辆相对于第一车辆的运动状态为切出第一车辆所在车道时，若纵向距离小于第四阈值，则可以确定第二车辆相对于第一车辆的运动状态为紧密切出第一车辆所在车道。若纵向距离大于第四阈值，则确定第二车辆相对于第一车辆的运动状态为正常切出第一车辆所在车道。同样容易理解的，若纵向距离等于第四阈值，则可以确定第二车辆相对于第一车辆的运动状态为紧密切出第一车辆所在车道，或者，正常切出第一车辆所在车道，在此亦不作限制。
在一些实施例中，在上述S904中根据第二车道信息、以及第二车辆的位置信息和运动信息，确定第二车辆的预测行驶轨迹之前，该车辆运动状态识别方法还可以包括对第二车辆的运动信息进行修正的步骤。
例如，可以先采集若干(比如6个)历史周期内的横向速度，并计算前述若干历史周期内的横向速度的平均值，得到第二车辆的平均历史横向速度，然后，根据第二车辆的平均历史横向速度，对第二车辆的运动信息中包括的横向速度进行修正。
或者，也可以对前述若干历史周期内的横向速度进行时间-速度的多项式拟合，得到拟合系数(多项式拟合的方式可以参考前述实施例中对第二车辆保持车道或变道的预测行驶轨迹进行多项式拟合的方式，在此不再赘述)。然后，根据拟合系数对第二车辆在当前的横向速度进行预测，得到预测的当前横向速度。然后，可以根据预测的当前横向速度，对第二车辆的运动信息中包括的横向速度进行修正。
以根据预测的当前横向速度，对第二车辆的运动信息中包括的横向速度进行修正为例(根据第二车辆的平均历史横向速度进行修正的方式与此相同)：可以将采集到的第二车辆的横向速度与前述预测的当前横向速度进行对比，如果二者之间的差距大于第五 阈值时，则对采集到的横向速度进行修正，以降低由于采集到的横向速度的瞬时速度过大带来的扰动。如：可以增大或降低横向速度，或者，按照预设的权重对采集到的横向速度和预测的当前横向速度进行加权组合对采集到的横向速度进行更新等。
可选地，第五阈值的大小与第二车辆的驾驶平稳性相关，第二车辆的驾驶平稳性越高，第五阈值越小，反之，则第五阈值越大。例如，第五阈值可以是0.2米每秒(m/s)、0.4m/s等，在此不作限制。
还有一些实施例中，在上述S905中确定至少两条预测行驶轨迹中每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度时，若采取先确定第二车辆的历史行驶轨迹在第一预设时段内的第一横向坐标构成的第一横向坐标时间序列，以及每条预测行驶轨迹在第二预设时段内的第二横向坐标构成的第二横向坐标时间序列，然后，计算第一横向坐标时间序列和第二横向坐标时间序列之间的相似度，得到第二车辆的历史行驶轨迹与预测行驶轨迹之间的相似度的方式，则在该方式中，还可以根据采集到的第二车辆的横向速度与前述预测的当前横向速度之间的差距，对第一预设时段和第二预设时段的大小进行调整。
例如，当差距较大时说明第二车辆驾驶意图更加明确，可以通过减少第一预设时段和第二预设时段的大小，降低第二车辆的历史行驶轨迹对预测行驶轨迹的延迟效应。相反，当差距较小时，则可以增大第一预设时段和第二预设时段的大小。
假设对第二车辆而言，历史横向速度的多项式拟合预测结果，即前述预测的当前横向速度为v，采集的当前横向速度为v0，第一预设时段为δ m，第二预设时段为δ n(δ m，δ n为标定值，如：δ m可以是3，δ n可以是2.5)，则δ m和δ n的大小改变方式可以如下。
Δ m＝[v-v0]*δ m；Δ n＝[v-v0]*δ n。
可选地，上述δ m可以是指第一预设时段中包括的第一预设周期的个数，对第一预设时段的大小进行调整，是指对第一预设时段中包括的第一预设周期的个数进行调整。
类似地，上述δ n可以是指第二预设时段中包括的第二预设周期的个数，对第二预设时段的大小进行调整，是指对第二预设时段中包括的第二预设周期的个数进行调整。
上述主要从车辆或服务器的角度对本申请实施例提供的方案进行了介绍。可以理解的是，为了实现上述功能，该车辆或服务器可以包含执行各个功能相应的硬件结构和/或软件模块。
如：本申请实施例还可以提供一种车辆运动状态识别装置。图18示出了本申请实施例提供的车辆运动状态识别装置的结构示意图。如图18所示，该车辆运动状态识别装置可以包括：获取模块1801，用于获取第一车道信息、第二车道信息、以及第二车辆的位置信息和运动信息；第一车道信息为第一车辆所在车道的车道信息；第二车道信息包括第二车辆所在车道的车道信息、第二车辆所在车道的第一相邻车道的车道信息、以及第二车辆所在车道的第二相邻车道的车道信息中的至少两种。预测模块1802，用于根据第二车道信息、以及第二车辆的位置信息和运动信息，确定第二车辆的至少两条预测行驶轨迹；每条预测行驶轨迹与第二车道信息所包含的每种车道信息相对应。确定模块1803，用于根据至少两条预测行驶轨迹、以及第一车道信息，确定第二车辆相对于第一车辆的运动状态。
在一种可能的设计中，确定模块1803，具体用于根据至少两条预测行驶轨迹、以及至少每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹；根据目标预测行驶轨迹、以及第一车道信息，确定第二车辆相对于第一 车辆的运动状态。
在一种可能的设计中，确定模块1803，还用于获取第二车辆的历史行驶轨迹在第一预设时段内的第一横向坐标向量；其中，第一横向坐标向量用于指示历史行驶轨迹与第二车辆所在车道的车道线之间的距离向量；针对每条预测行驶轨迹：获取预测行驶轨迹在第二预设时段内的第二横向坐标向量，根据第二横向坐标向量、以及第一横向坐标向量确定预测行驶轨迹与历史行驶轨迹之间的相似度；其中，第二横向坐标向量用于指示预测行驶轨迹与第二车辆所在车道的车道线之间的距离向量。
在一种可能的设计中，确定模块1803，具体用于根据每条预测行驶轨迹与第二车辆的历史行驶轨迹之间的相似度，预测每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度；根据至少两条预测行驶轨迹、以及每条预测行驶轨迹与第二车辆的真实行驶轨迹之间的相似度，确定第二车辆的目标预测行驶轨迹。
在一种可能的设计中，确定模块1803具体用于根据目标预测行驶轨迹、以及第一车道信息，确定目标预测行驶轨迹与第一车辆所在车道的车道线在预设纵向长度内的最小横向距离；若最小横向距离大于第一阈值，则确定第二车辆相对于第一车辆的运动状态为与第一车辆保持在不同车道行驶。
在一种可能的设计中，确定模块1803还用于根据目标预测行驶轨迹、以及第一车道信息，确定目标预测行驶轨迹与第一车辆所在车道的车道线在预设纵向长度内的最大横向距离；若最小横向距离小于第一阈值、且最大横向距离大于第二阈值，则确定第二车辆相对于第一车辆的运动状态为穿过第一车辆所在车道；其中，第二阈值大于第一阈值。若最大横向距离小于第三阈值，则确定第二车辆相对于第一车辆的运动状态为与第一车辆保持在同一车道行驶；其中，第三阈值小于第一阈值。若最小横向距离小于第一阈值，最大横向距离大于第三阈值、且小于第二阈值，则确定第二车辆相对于第一车辆的运动状态为切入第一车辆所在车道、或者切出第一车辆所在车道。
在一种可能的设计中，确定模块1803还用于获取最小横向距离对应的第一纵向位置、以及最大横向距离对应的第二纵向位置；当最小横向距离小于第一阈值，最大横向距离大于第三阈值、且小于第二阈值时，若目标预测行驶轨迹中第二纵向位置出现的时间早于第一纵向位置出现的时间，则确定第二车辆相对于第一车辆的运动状态为切入第一车辆所在车道；若目标预测行驶轨迹中第一纵向位置出现的时间早于第二纵向位置出现的时间，则确定第二车辆相对于第一车辆的运动状态为切出第一车辆所在车道。
在一种可能的设计中，确定模块1803还用于获取第一纵向位置与预设纵向长度的第一端之间的纵向距离；其中，纵向距离为第一纵向位置在与第一车辆所在车道的车道线的平行方向上与预设纵向长度的第一端之间的距离，且预设纵向长度的第一端是靠近于第一车辆的一端；若纵向距离小于第四阈值，则确定第二车辆相对于第一车辆的运动状态为按照第一切入状态切入第一车辆所在车道、或者按照第一切出状态切出第一车辆所在车道；若纵向距离大于第四阈值，则确定第二车辆相对于第一车辆的运动状态为按照第二切入状态切入第一车辆所在车道、或者按照第二切出状态切出第一车辆所在车道。
在一种可能的设计中，第二车辆的运动信息包括第二车辆的横向速度；预测模块1802，还用于根据第二车辆的平均历史横向速度，对第二车辆的运动信息中包括的横向速度进行修正。
应理解以上装置中模块或单元的划分仅仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。且装置中的模块可以全部以软 件通过处理元件调用的形式实现；也可以全部以硬件的形式实现；还可以部分单元以软件通过处理元件调用的形式实现，部分单元以硬件的形式实现。
例如，各个单元可以为单独设立的处理元件，也可以集成在装置的某一个芯片中实现，此外，也可以以程序的形式存储于存储器中，由装置的某一个处理元件调用并执行该单元的功能。此外这些单元全部或部分可以集成在一起，也可以独立实现。这里所述的处理元件又可以称为处理器，可以是一种具有信号的处理能力的集成电路。在实现过程中，上述方法的各步骤或以上各个单元可以通过处理器元件中的硬件的集成逻辑电路实现或者以软件通过处理元件调用的形式实现。
在一个例子中，以上任一装置中的单元可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个特定集成电路(application specific integrated circuit，ASIC)，或，一个或多个微处理器(digital singnal processor，DSP)，或，一个或者多个现场可编程门阵列(field programmable gate array，FPGA)，或这些集成电路形式中至少两种的组合。
再如，当装置中的单元可以通过处理元件调度程序的形式实现时，该处理元件可以是通用处理器，例如中央处理器(central processing unit，CPU)或其它可以调用程序的处理器。再如，这些单元可以集成在一起，以片上系统(system-on-a-chip，SOC)的形式实现。
例如，本申请实施例还可以提供一种车辆运动状态识别装置，包括：接口电路，用于接收其他装置传输的数据；处理器，连接接口电路并用于执行以上方法中所述的各个步骤。该处理器可以包括一个或多个。
在一种实现中，分别实现以上方法中各个对应步骤的模块可以通过处理元件调度程序的形式实现。例如，车辆运动状态识别装置可以包括处理元件和存储元件，处理元件调用存储元件存储的程序，以执行以上方法实施例中所述的方法。存储元件可以为与处理元件处于同一芯片上的存储元件，即片内存储元件。
在另一种实现中，用于实现以上方法的程序可以在与处理元件处于不同芯片上的存储元件，即片外存储元件。此时，处理元件从片外存储元件调用或加载程序于片内存储元件上，以调用并执行以上方法实施例中所述的方法。
例如，本申请实施例还可以提供一种包括处理器的车辆，处理器用于与存储器相连，调用存储器中存储的程序，以执行以上方法实施例中所述的方法。
或者，本申请实施例还可以提供一种包括处理器的服务器，该服务器可以与车辆进行远程通信，处理器用于与存储器相连，调用存储器中存储的程序，以执行以上方法实施例中所述的方法。
又或者，本申请实施例还可以提供一种车辆驾驶系统，如：可以是自动驾驶系统或辅助驾驶系统。该车辆驾驶系统可以由车辆和服务器组成，或者单独部署于车辆或服务器中。该车辆驾驶系统包括：处理器，处理器用于与存储器相连，调用存储器中存储的程序，以执行以上方法实施例中所述的方法。
在又一种实现中，用于实现以上方法中各个步骤的模块可以是被配置成一个或多个处理元件，这些处理元件可以设置于终端上，这里的处理元件可以为集成电路，例如：一个或多个ASIC，或，一个或多个DSP，或，一个或者多个FPGA，或者这些类集成电路的组合。这些集成电路可以集成在一起，构成芯片。
在又一种实现中，用于实现以上方法中各个步骤的模块可以集成在一起，以SOC的 形式实现，该SOC芯片，用于实现对应的方法。该芯片内可以集成至少一个处理元件和存储元件，由处理元件调用存储元件的存储的程序的形式实现对应的方法；或者，该芯片内可以集成至少一个集成电路，用于实现对应的方法；或者，可以结合以上实现方式，部分单元的功能通过处理元件调用程序的形式实现，部分单元的功能通过集成电路的形式实现。
这里的处理元件同以上描述，可以是通用处理器，例如CPU，还可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个ASIC，或，一个或多个微处理器DSP，或，一个或者多个FPGA等，或这些集成电路形式中至少两种的组合。
存储元件可以是一个存储器，也可以是多个存储元件的统称。
通过以上的实施方式的描述，所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个装置，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是一个物理单元或多个物理单元，即可以位于一个地方，或者也可以分布到多个不同地方。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个可读取存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，如：程序。该软件产品存储在一个程序产品，如计算机可读存储介质中，包括若干指令用以使得一个设备(可以是单片机，芯片等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
例如，本申请实施例还可以提供一种计算机可读存储介质，包括：计算机软件指令；当计算机软件指令在车辆运动状态识别装置或内置在车辆运动状态识别装置的芯片中运行时，使得车辆运动状态识别装置执行如前述方法实施例中所述的方法。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何在本申请揭露的技术范围内的变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (23)

  1. 一种车辆运动状态识别方法，其特征在于，所述方法包括：
    获取第一车道信息、第二车道信息、以及第二车辆的位置信息和运动信息；所述第一车道信息为第一车辆所在车道的车道信息；所述第二车道信息包括所述第二车辆所在车道的车道信息、所述第二车辆所在车道的第一相邻车道的车道信息、以及所述第二车辆所在车道的第二相邻车道的车道信息中的至少两种；
    根据所述第二车道信息、以及所述第二车辆的位置信息和运动信息，确定所述第二车辆的至少两条预测行驶轨迹；每条所述预测行驶轨迹与所述第二车道信息所包含的每种车道信息相对应；
    根据所述至少两条预测行驶轨迹、以及所述第一车道信息，确定所述第二车辆相对于所述第一车辆的运动状态。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述至少两条预测行驶轨迹、以及所述第一车道信息，确定所述第二车辆相对于所述第一车辆的运动状态，包括：
    根据所述至少两条预测行驶轨迹、以及每条所述预测行驶轨迹与所述第二车辆的历史行驶轨迹之间的相似度，确定所述第二车辆的目标预测行驶轨迹；
    根据所述目标预测行驶轨迹、以及所述第一车道信息，确定所述第二车辆相对于所述第一车辆的运动状态。
  3. 根据权利要求2所述的方法，其特征在于，在所述根据所述至少两条预测行驶轨迹、以及每条所述预测行驶轨迹与所述第二车辆的历史行驶轨迹之间的相似度，确定所述第二车辆的目标预测行驶轨迹之前，所述方法还包括：
    获取所述第二车辆的历史行驶轨迹在第一预设时段内的第一横向坐标向量；其中，所述第一横向坐标向量用于指示所述历史行驶轨迹与所述第二车辆所在车道的车道线之间的距离向量；
    针对每条所述预测行驶轨迹：获取所述预测行驶轨迹在第二预设时段内的第二横向坐标向量，根据所述第二横向坐标向量、以及所述第一横向坐标向量确定所述预测行驶轨迹与所述历史行驶轨迹之间的相似度；其中，所述第二横向坐标向量用于指示所述预测行驶轨迹与所述第二车辆所在车道的车道线之间的距离向量。
  4. 根据权利要求2或3所述的方法，其特征在于，所述根据所述至少两条预测行驶轨迹、以及每条所述预测行驶轨迹与所述第二车辆的历史行驶轨迹之间的相似度，确定所述第二车辆的目标预测行驶轨迹，包括：
    根据每条所述预测行驶轨迹与所述第二车辆的历史行驶轨迹之间的相似度，预测每条所述预测行驶轨迹与所述第二车辆的真实行驶轨迹之间的相似度；
    根据所述至少两条预测行驶轨迹、以及每条所述预测行驶轨迹与所述第二车辆的真实行驶轨迹之间的相似度，确定所述第二车辆的目标预测行驶轨迹。
  5. 根据权利要求2-4任一项所述的方法，其特征在于，所述根据所述目标预测行驶轨迹、以及所述第一车道信息，确定所述第二车辆相对于所述第一车辆的运动状态，包括：
    根据所述目标预测行驶轨迹、以及所述第一车道信息，确定所述目标预测行驶轨迹与所述第一车辆所在车道的车道线在预设纵向长度内的最小横向距离；
    若所述最小横向距离大于第一阈值，则确定所述第二车辆相对于所述第一车辆的运 动状态为与所述第一车辆保持在不同车道行驶。
  6. 根据权利要求5所述的方法，其特征在于，所述方法还包括：
    根据所述目标预测行驶轨迹、以及所述第一车道信息，确定所述目标预测行驶轨迹与所述第一车辆所在车道的车道线在所述预设纵向长度内的最大横向距离；
    若所述最小横向距离小于所述第一阈值、且所述最大横向距离大于第二阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为穿过所述第一车辆所在车道；其中，所述第二阈值大于所述第一阈值；
    若所述最大横向距离小于第三阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为与所述第一车辆保持在同一车道行驶；其中，所述第三阈值小于所述第一阈值；
    若所述最小横向距离小于第一阈值，所述最大横向距离大于所述第三阈值、且小于所述第二阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为切入所述第一车辆所在车道、或者切出所述第一车辆所在车道。
  7. 根据权利要求6所述的方法，其特征在于，所述方法还包括：
    获取所述最小横向距离对应的第一纵向位置、以及所述最大横向距离对应的第二纵向位置；
    当所述最小横向距离小于第一阈值，所述最大横向距离大于所述第三阈值、且小于所述第二阈值时，所述确定所述第二车辆相对于所述第一车辆的运动状态为切入所述第一车辆所在车道、或者切出所述第一车辆所在车道，包括：
    若所述目标预测行驶轨迹中所述第二纵向位置出现的时间早于所述第一纵向位置出现的时间，则确定所述第二车辆相对于所述第一车辆的运动状态为切入所述第一车辆所在车道；
    若所述目标预测行驶轨迹中所述第一纵向位置出现的时间早于所述第二纵向位置出现的时间，则确定所述第二车辆相对于所述第一车辆的运动状态为切出所述第一车辆所在车道。
  8. 根据权利要求7所述的方法，其特征在于，所述方法还包括：
    获取所述第一纵向位置与所述预设纵向长度的第一端之间的纵向距离；其中，所述纵向距离为所述第一纵向位置在与所述第一车辆所在车道的车道线的平行方向上与所述预设纵向长度的第一端之间的距离，且所述预设纵向长度的第一端是靠近于所述第一车辆的一端；
    若所述纵向距离小于第四阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为按照第一切入状态切入所述第一车辆所在车道、或者按照第一切出状态切出所述第一车辆所在车道；
    若所述纵向距离大于第四阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为按照第二切入状态切入所述第一车辆所在车道、或者按照第二切出状态切出所述第一车辆所在车道。
  9. 根据权利要求1-8任一项所述的方法，其特征在于，所述第二车辆的运动信息包括所述第二车辆的横向速度；在所述根据所述第二车道信息、以及所述第二车辆的位置信息和运动信息，确定所述第二车辆的至少两条预测行驶轨迹之前，所述方法还包括：
    根据所述第二车辆的平均历史横向速度，对所述第二车辆的运动信息中包括的所述横向速度进行修正。
  10. 一种车辆运动状态识别装置，其特征在于，所述装置包括：
    获取模块，用于获取第一车道信息、第二车道信息、以及第二车辆的位置信息和运动信息；所述第一车道信息为第一车辆所在车道的车道信息；所述第二车道信息包括所述第二车辆所在车道的车道信息、所述第二车辆所在车道的第一相邻车道的车道信息、以及所述第二车辆所在车道的第二相邻车道的车道信息中的至少两种；
    预测模块，用于根据所述第二车道信息、以及所述第二车辆的位置信息和运动信息，确定所述第二车辆的至少两条预测行驶轨迹；每条所述预测行驶轨迹与所述第二车道信息所包含的每种车道信息相对应；
    确定模块，用于根据所述至少两条预测行驶轨迹、以及所述第一车道信息，确定所述第二车辆相对于所述第一车辆的运动状态。
  11. 根据权利要求10所述的装置，其特征在于，所述确定模块，具体用于根据所述至少两条预测行驶轨迹、以及每条所述预测行驶轨迹与所述第二车辆的历史行驶轨迹之间的相似度，确定所述第二车辆的目标预测行驶轨迹；
    根据所述目标预测行驶轨迹、以及所述第一车道信息，确定所述第二车辆相对于所述第一车辆的运动状态。
  12. 根据权利要求11所述的装置，其特征在于，所述确定模块，还用于获取所述第二车辆的历史行驶轨迹在第一预设时段内的第一横向坐标向量；其中，所述第一横向坐标向量用于指示所述历史行驶轨迹与所述第二车辆所在车道的车道线之间的距离向量；
    针对每条所述预测行驶轨迹：获取所述预测行驶轨迹在第二预设时段内的第二横向坐标向量，根据所述第二横向坐标向量、以及所述第一横向坐标向量确定所述预测行驶轨迹与所述历史行驶轨迹之间的相似度；其中，所述第二横向坐标向量用于指示所述预测行驶轨迹与所述第二车辆所在车道的车道线之间的距离向量。
  13. 根据权利要求11或12所述的装置，其特征在于，所述确定模块，具体用于根据每条所述预测行驶轨迹与所述第二车辆的历史行驶轨迹之间的相似度，预测每条所述预测行驶轨迹与所述第二车辆的真实行驶轨迹之间的相似度；
    根据所述至少两条预测行驶轨迹、以及每条所述预测行驶轨迹与所述第二车辆的真实行驶轨迹之间的相似度，确定所述第二车辆的目标预测行驶轨迹。
  14. 根据权利要求11-13任一项所述的装置，其特征在于，所述确定模块具体用于根据所述目标预测行驶轨迹、以及所述第一车道信息，确定所述目标预测行驶轨迹与所述第一车辆所在车道的车道线在预设纵向长度内的最小横向距离；
    若所述最小横向距离大于第一阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为与所述第一车辆保持在不同车道行驶。
  15. 根据权利要求14所述的装置，其特征在于，所述确定模块还用于根据所述目标预测行驶轨迹、以及所述第一车道信息，确定所述目标预测行驶轨迹与所述第一车辆所在车道的车道线在所述预设纵向长度内的最大横向距离；
    若所述最小横向距离小于所述第一阈值、且所述最大横向距离大于第二阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为穿过所述第一车辆所在车道；其中，所述第二阈值大于所述第一阈值；
    若所述最大横向距离小于第三阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为与所述第一车辆保持在同一车道行驶；其中，所述第三阈值小于所述第一阈值；
    若所述最小横向距离小于第一阈值，所述最大横向距离大于所述第三阈值、且小于所述第二阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为切入所述第一车 辆所在车道、或者切出所述第一车辆所在车道。
  16. 根据权利要求15所述的装置，其特征在于，所述确定模块还用于获取所述最小横向距离对应的第一纵向位置、以及所述最大横向距离对应的第二纵向位置；
    当所述最小横向距离小于第一阈值，所述最大横向距离大于所述第三阈值、且小于所述第二阈值时，若所述目标预测行驶轨迹中所述第二纵向位置出现的时间早于所述第一纵向位置出现的时间，则确定所述第二车辆相对于所述第一车辆的运动状态为切入所述第一车辆所在车道；
    若所述目标预测行驶轨迹中所述第一纵向位置出现的时间早于所述第二纵向位置出现的时间，则确定所述第二车辆相对于所述第一车辆的运动状态为切出所述第一车辆所在车道。
  17. 根据权利要求16所述的装置，其特征在于，所述确定模块还用于获取所述第一纵向位置与所述预设纵向长度的第一端之间的纵向距离；其中，所述纵向距离为所述第一纵向位置在与所述第一车辆所在车道的车道线的平行方向上与所述预设纵向长度的第一端之间的距离，且所述预设纵向长度的第一端是靠近于所述第一车辆的一端；
    若所述纵向距离小于第四阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为按照第一切入状态切入所述第一车辆所在车道、或者按照第一切出状态切出所述第一车辆所在车道；
    若所述纵向距离大于第四阈值，则确定所述第二车辆相对于所述第一车辆的运动状态为按照第二切入状态切入所述第一车辆所在车道、或者按照第二切出状态切出所述第一车辆所在车道。
  18. 根据权利要求10-17任一项所述的装置，其特征在于，所述第二车辆的运动信息包括所述第二车辆的横向速度；
    所述预测模块，还用于根据所述第二车辆的平均历史横向速度，对所述第二车辆的运动信息中包括的横向速度进行修正。
  19. 一种车辆运动状态识别装置，其特征在于，包括：
    接口电路，用于接收其他装置传输的数据；
    处理器，连接所述接口电路并用于执行权利要求1至9中任一项所述的方法。
  20. 一种车辆，其特征在于，包括：处理器，所述处理器用于与存储器相连，调用所述存储器中存储的程序，以执行权利要求1至9中任一项所述的方法。
  21. 一种服务器，其特征在于，包括：处理器，所述处理器用于与存储器相连，调用所述存储器中存储的程序，以执行权利要求1至9中任一项所述的方法。
  22. 一种车辆驾驶系统，其特征在于，包括：处理器，所述处理器用于与存储器相连，调用所述存储器中存储的程序，以执行权利要求1至9中任一项所述的方法。
  23. 一种计算机可读存储介质，其特征在于，包括：计算机软件指令；
    当所述计算机软件指令在车辆运动状态识别装置或内置在所述车辆运动状态识别装置的芯片中运行时，使得所述车辆运动状态识别装置执行如权利要求1至9中任一项所述的方法。
PCT/CN2021/107918 2020-07-31 2021-07-22 车辆运动状态识别方法及装置 WO2022022384A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21849900.2A EP4180295A4 (en) 2020-07-31 2021-07-22 METHOD AND DEVICE FOR DETECTING A VEHICLE MOTION STATE
JP2023506149A JP2023536483A (ja) 2020-07-31 2021-07-22 車両の動き状態認識方法及び機器

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010762012.3 2020-07-31
CN202010762012.3A CN114056347A (zh) 2020-07-31 2020-07-31 车辆运动状态识别方法及装置

Publications (1)

Publication Number Publication Date
WO2022022384A1 true WO2022022384A1 (zh) 2022-02-03

Family

ID=80037130

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/107918 WO2022022384A1 (zh) 2020-07-31 2021-07-22 车辆运动状态识别方法及装置

Country Status (4)

Country Link
EP (1) EP4180295A4 (zh)
JP (1) JP2023536483A (zh)
CN (1) CN114056347A (zh)
WO (1) WO2022022384A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114973160A (zh) * 2022-05-18 2022-08-30 南京感动科技有限公司 基于数字孪生模型的车辆状态判断方法及系统
CN115817515A (zh) * 2023-01-18 2023-03-21 禾多科技（北京）有限公司 车辆控制方法、装置、电子设备和计算机可读介质
CN117622147A (zh) * 2023-12-29 2024-03-01 上海保隆汽车科技股份有限公司 智能驾驶变道轨迹的生成方法、系统、电子设备及介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115123252B (zh) * 2022-07-05 2023-03-31 小米汽车科技有限公司 车辆控制方法、装置、车辆及存储介质
CN116110216B (zh) * 2022-10-21 2024-04-12 中国第一汽车股份有限公司 车辆跨线时间确定方法、装置、存储介质及电子装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109552333A (zh) * 2017-09-26 2019-04-02 三星电子株式会社 车辆运动预测方法和设备
WO2019195187A1 (en) * 2018-04-06 2019-10-10 Zoox, Inc. Feature-based prediction
CN110400490A (zh) * 2019-08-08 2019-11-01 腾讯科技（深圳）有限公司 轨迹预测方法和装置
CN110789528A (zh) * 2019-08-29 2020-02-14 腾讯科技（深圳）有限公司 一种车辆行驶轨迹预测方法、装置、设备及存储介质
CN111114554A (zh) * 2019-12-16 2020-05-08 苏州智加科技有限公司 行驶轨迹预测方法、装置、终端及存储介质
CN111169476A (zh) * 2020-01-18 2020-05-19 重庆长安汽车股份有限公司 一种目标车辆相对于主车辆的运动趋势预测方法、装置、控制器及汽车

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015155833A1 (ja) * 2014-04-08 2015-10-15 三菱電機株式会社 衝突防止装置
DE102014212700B4 (de) * 2014-07-01 2022-02-10 Honda Motor Co., Ltd. Adaptives Geschwindigkeits-Regelungs-/Steuerungssystem
US10152882B2 (en) * 2015-11-30 2018-12-11 Nissan North America, Inc. Host vehicle operation using remote vehicle intention prediction
DE102016009763A1 (de) * 2016-08-11 2018-02-15 Trw Automotive Gmbh Steuerungssystem und Steuerungsverfahren zum Bestimmen einer Trajektorie und zum Erzeugen von zugehörigen Signalen oder Steuerbefehlen
JP6935813B2 (ja) * 2017-03-02 2021-09-22 日産自動車株式会社 運転支援方法及び運転支援装置
US10324469B2 (en) * 2017-03-28 2019-06-18 Mitsubishi Electric Research Laboratories, Inc. System and method for controlling motion of vehicle in shared environment
CN113243029B (zh) * 2018-12-11 2022-07-05 日产自动车株式会社 其他车辆动作预测方法及其他车辆动作预测装置
CN109739246B (zh) * 2019-02-19 2022-10-11 阿波罗智能技术(北京)有限公司 一种变换车道过程中的决策方法、装置、设备及存储介质
CN109583151B (zh) * 2019-02-20 2023-07-21 阿波罗智能技术(北京)有限公司 车辆的行驶轨迹预测方法及装置
CN110758382B (zh) * 2019-10-21 2021-04-20 南京航空航天大学 一种基于驾驶意图的周围车辆运动状态预测系统及方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109552333A (zh) * 2017-09-26 2019-04-02 三星电子株式会社 车辆运动预测方法和设备
WO2019195187A1 (en) * 2018-04-06 2019-10-10 Zoox, Inc. Feature-based prediction
CN110400490A (zh) * 2019-08-08 2019-11-01 腾讯科技（深圳）有限公司 轨迹预测方法和装置
CN110789528A (zh) * 2019-08-29 2020-02-14 腾讯科技（深圳）有限公司 一种车辆行驶轨迹预测方法、装置、设备及存储介质
CN111114554A (zh) * 2019-12-16 2020-05-08 苏州智加科技有限公司 行驶轨迹预测方法、装置、终端及存储介质
CN111169476A (zh) * 2020-01-18 2020-05-19 重庆长安汽车股份有限公司 一种目标车辆相对于主车辆的运动趋势预测方法、装置、控制器及汽车

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4180295A4

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114973160A (zh) * 2022-05-18 2022-08-30 南京感动科技有限公司 基于数字孪生模型的车辆状态判断方法及系统
CN114973160B (zh) * 2022-05-18 2023-08-11 南京感动科技有限公司 基于数字孪生模型的车辆状态判断方法及系统
CN115817515A (zh) * 2023-01-18 2023-03-21 禾多科技（北京）有限公司 车辆控制方法、装置、电子设备和计算机可读介质
CN115817515B (zh) * 2023-01-18 2023-05-26 禾多科技（北京）有限公司 车辆控制方法、装置、电子设备和计算机可读介质
CN117622147A (zh) * 2023-12-29 2024-03-01 上海保隆汽车科技股份有限公司 智能驾驶变道轨迹的生成方法、系统、电子设备及介质

Also Published As

Publication number Publication date
CN114056347A (zh) 2022-02-18
EP4180295A1 (en) 2023-05-17
EP4180295A4 (en) 2024-01-10
JP2023536483A (ja) 2023-08-25

Similar Documents

Publication Publication Date Title
JP7540641B2 (ja) 自動運転方法、関連装置及びコンピュータ読み取り可能記憶媒体
WO2022022384A1 (zh) 车辆运动状态识别方法及装置
WO2021196879A1 (zh) 车辆驾驶行为的识别方法以及识别装置
WO2021102955A1 (zh) 车辆的路径规划方法以及车辆的路径规划装置
CN112519575B (zh) 调整油门踏板特性的方法和装置
CN113879295B (zh) 轨迹预测方法及装置
WO2021000800A1 (zh) 道路可行驶区域推理方法及装置
WO2022016351A1 (zh) 一种行驶决策选择方法以及装置
CN113460033B (zh) 一种自动泊车方法以及装置
CN114440908B (zh) 一种规划车辆驾驶路径的方法、装置、智能车以及存储介质
US20230222914A1 (en) Vehicle reminding method and system, and related device
US20230048680A1 (en) Method and apparatus for passing through barrier gate crossbar by vehicle
WO2022051951A1 (zh) 车道线检测方法、相关设备及计算机可读存储介质
CN112534483A (zh) 预测车辆驶出口的方法和装置
WO2022062825A1 (zh) 车辆的控制方法、装置及车辆
CN114056346B (zh) 一种自动驾驶行车控制方法及装置
CN112585045A (zh) 电子机械制动方法和电子机械制动装置
WO2022127502A1 (zh) 控制方法和装置
EP4159564A1 (en) Method and device for planning vehicle longitudinal motion parameters
WO2022061702A1 (zh) 驾驶提醒的方法、装置及系统
WO2023102827A1 (zh) 一种路径约束方法及装置
WO2020164121A1 (zh) 一种雷达以及增益控制方法
WO2022061725A1 (zh) 交通元素的观测方法和装置
CN114103950B (zh) 换道轨迹的规划方法及装置
WO2022001432A1 (zh) 推理车道的方法、训练车道推理模型的方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21849900

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023506149

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2021849900

Country of ref document: EP

Effective date: 20230208

NENP Non-entry into the national phase

Ref country code: DE