WO2022151369A1 - 一种信息处理方法及相关装置 - Google Patents

一种信息处理方法及相关装置 Download PDF

Info

Publication number
WO2022151369A1
WO2022151369A1 PCT/CN2021/072211 CN2021072211W WO2022151369A1 WO 2022151369 A1 WO2022151369 A1 WO 2022151369A1 CN 2021072211 W CN2021072211 W CN 2021072211W WO 2022151369 A1 WO2022151369 A1 WO 2022151369A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
vehicle
lane
identification information
lane change
Prior art date
Application number
PCT/CN2021/072211
Other languages
English (en)
French (fr)
Inventor
周斌
沈佩尧
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 CN202180000263.0A priority Critical patent/CN112839854B/zh
Priority to PCT/CN2021/072211 priority patent/WO2022151369A1/zh
Publication of WO2022151369A1 publication Critical patent/WO2022151369A1/zh

Links

Images

Classifications

    • 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
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/18—Propelling the vehicle
    • B60W30/18009—Propelling the vehicle related to particular drive situations
    • B60W30/18163—Lane change; Overtaking manoeuvres
    • 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
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/14—Yaw
    • 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
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/18—Steering angle
    • 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
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/30—Road curve radius
    • 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
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/53—Road markings, e.g. lane marker or crosswalk
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/801—Lateral distance
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance
    • 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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/806—Relative heading
    • 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
    • B60W2556/00—Input parameters relating to data
    • B60W2556/10—Historical data
    • 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
    • B60W2556/00—Input parameters relating to data
    • B60W2556/40—High definition maps

Definitions

  • the present application relates to the field of sensor technology, and in particular, to an information processing method and a related device.
  • ADAS advanced driver-assistance system
  • AD autonomous driving
  • ADAS autonomous driving
  • lane change warning LKA
  • LKA lane keeping assist
  • survey data about 50% of the lane changes occurred when the driver did not turn on the turn signal as required.
  • the recognition and judgment of the driver's intention to change lanes can make up for the normal operation of various intelligent driving algorithm functions when the driver does not manually turn on the turn signal, thereby improving safety.
  • the self-vehicle lane-change intention recognition technologies use sensor data such as cameras and lidars to extract lane line information from the image domain, and at the same time, according to the positional relationship between the self-vehicle and the lane line, determine the self-vehicle's lane-change intention.
  • Commonly used identification methods include designing logic threshold judgment method or selecting lane line information, self-vehicle attitude information, etc. as feature quantities, and using machine learning method to judge and identify. Due to the different advantages and disadvantages of different sensors, environmental factors such as rain and fog weather, complex road conditions, and different lane-changing styles of drivers, it is difficult for the traditional method of recognizing self-vehicle lane-changing intention to ensure high recognition accuracy.
  • the embodiments of the present application disclose an information processing method and a related device, which can more accurately determine the lane-changing behavior of the first vehicle, activate a corresponding response strategy or an alarm mechanism, and improve security.
  • a first aspect of the embodiments of the present application discloses an information processing apparatus, the apparatus includes: an acquisition module configured to acquire lane line information corresponding to a lane where a first vehicle is located, vehicle posture information of the first vehicle, and road edge at least two of information, target vehicle information, or map information; a processing module, configured to At least two, controlling the first vehicle to perform processing corresponding to a lane change behavior, the lane change behavior being determined according to at least one lane change identification information and at least one confidence probability corresponding to the at least one lane change identification information , at least two of the lane line information, the vehicle attitude information, the road edge information, the target vehicle information and the map information are used to indicate the at least one lane change identification information and the at least one at least one confidence probability corresponding to the lane-change identification information; the lane-change identification information is used to indicate the category of the lane-change behavior of the first vehicle.
  • At least one lane change identification information and at least one confidence level may be determined according to at least two of lane line information, the vehicle attitude information, the road edge information, the target vehicle information and the map information probability, and then control the first vehicle to perform processing corresponding to the lane-changing behavior according to at least one lane-changing identification information and at least one confidence probability, for example, determine that the lane-changing behavior of the first vehicle is in a left-lane-changing state, because the first vehicle is moving towards the left lane.
  • controlling the first vehicle to perform the processing corresponding to the lane changing behavior may be controlling the first vehicle to turn on the turn signal, or starting an alarm mechanism, such as the first vehicle.
  • the vehicle emits an alarm sound, etc., by determining the lane-changing behavior of the first vehicle, and starting a corresponding coping strategy or an alarm mechanism, thereby improving driving safety.
  • the lighting conditions are poor in rainy and foggy weather, etc.
  • the lane-changing behavior of the first vehicle can still be determined, and the lane-changing behavior of the first vehicle can be determined with the help of map information and road information, which improves the recognition accuracy.
  • a second aspect of the embodiments of the present application discloses an information processing method, the method includes: acquiring lane line information corresponding to a lane where a first vehicle is located, vehicle attitude information, road edge information, and target vehicle information of the first vehicle Or at least two of the map information; control the first vehicle according to at least two of the lane line information, the vehicle attitude information, the road edge information, the target vehicle information and the map information performing processing corresponding to a lane change behavior determined according to at least one lane change identification information and at least one confidence probability corresponding to the at least one lane change identification information, the lane line information, the vehicle At least two of the attitude information, the road edge information, the target vehicle information and the map information, used to indicate at least one confidence corresponding to the at least one lane change identification information and the at least one lane change identification information degree probability; the lane change identification information is used to indicate the category of the lane change behavior of the first vehicle.
  • a third aspect of the embodiments of the present application discloses an information processing apparatus, including at least one processor and an interface circuit, and optionally, a memory, where the memory, the interface circuit, and the at least one processor are interconnected through a line , a computer program or instruction is stored in the at least one memory, and the processor is configured to read the computer program or instruction stored in the memory, and perform the following operations:
  • the vehicle posture information of the first vehicle is located, the vehicle posture information of the first vehicle, road edge information, target vehicle information or map information; according to the lane line information, the vehicle posture at least two of the information, the road edge information, the target vehicle information, and the map information, controlling the first vehicle to perform processing corresponding to a lane change behavior, the lane change behavior being based on at least one lane change
  • the identification information and at least one confidence probability corresponding to the at least one lane change identification information are determined, the lane line information, the vehicle attitude information, the road edge information, the target vehicle information and the map information are determined. At least two kinds of at least two are used to indicate the at least one lane change identification information and at least one confidence probability corresponding to the at least one lane change identification information; the lane change identification information is used to indicate the lane change behavior of the first vehicle category.
  • the at least one lane change identification information includes first lane change identification information, second lane change identification information , the third lane change identification information and the fourth lane change identification information
  • the at least one confidence probability corresponding to the at least one lane change identification information includes the first confidence probability, the second confidence probability, the third confidence probability and the first confidence probability
  • the lane line information and the vehicle attitude information are used to indicate the first lane change identification information of the first vehicle and the first confidence probability corresponding to the first lane change identification information; the The road edge information and the vehicle attitude information are used to indicate the second lane change identification information of the first vehicle and the second confidence probability corresponding to the second lane change identification information; the target vehicle information and the vehicle The attitude information is used to indicate the third lane change identification information of the first vehicle and the third confidence probability corresponding to the third lane change identification information; the map information and the vehicle attitude information are used to indicate the first vehicle.
  • the fourth lane change identification information of a vehicle and the fourth confidence probability corresponding to the fourth lane change identification information are used to indicate the first vehicle.
  • the lane line information and the vehicle attitude information are used to indicate the first confidence probability;
  • the first lane change identification information is determined according to the first confidence probability.
  • the first lane change identification information is based on the A confidence probability is determined by the number of times that the probability is greater than the first threshold.
  • the second confidence probability is based on the difference value, the road edge information divided by the first It is determined by the information beyond the distance from a vehicle to the curb and the vehicle attitude information; the difference is the sum of the real-time value of the distance from the first vehicle to the curb in the curb information and the mean value corresponding to the real-time value The average value corresponding to the real-time value is the average value of the distance from the first vehicle to the road edge in the road edge information within the second preset time length; the second lane change identification information is based on the The second confidence probability is determined.
  • the characteristics of the lane-changing behavior of the first vehicle can be indirectly reflected, so as to determine the lane-changing behavior of the first vehicle.
  • the behavior in addition to using the vehicle attitude information, it also combines the road edge information to determine the lane-changing behavior of the first vehicle, which improves the accuracy of the recognition.
  • the third confidence probability is based on the number of lane-change voters and the The vehicle attitude information is determined, and the number of lane-change voters is determined according to the target heading angle in the target vehicle information and the horizontal and vertical distances in the target vehicle information; the number of lane-change voters refers to: the number of target vehicles that support the lane-changing behavior of the first category of the first vehicle; the first category is one of the categories of the lane-changing behavior of the first vehicle; the third lane-changing identification information is determined according to the third confidence probability.
  • the number of voters changing lanes within the third preset time period is determined by the following manner: Within the third preset time length, when the target heading angle in the target vehicle information is greater than a third threshold, and the horizontal and vertical distances in the target vehicle information are greater than a fourth threshold, the number of lane-changing voters increases ; within the third preset time length, when the target heading angle in the target vehicle information is less than or equal to the third threshold, and/or the horizontal and vertical distance in the target vehicle information is less than or equal to the fourth Threshold, the number of lane-changing voters remains unchanged.
  • the characteristics of the lane-changing behavior of the first vehicle can be indirectly reflected through the heading angle and the horizontal and vertical distances in the target vehicle information, so as to achieve the purpose of determining the lane-changing behavior of the first vehicle.
  • the lane changing behavior of the first vehicle is determined in combination with the target vehicle information, which improves the recognition accuracy.
  • the fourth lane change identification information and the fourth confidence probability are based on the lane line
  • the distance between the first vehicle and the lane line in the information, the vehicle posture information, the semantic information in the map information, and whether the first vehicle is in the lane-change collision accident-prone area are determined, and the map information is determined by for indicating whether the first vehicle is in the lane-change collision prone area.
  • whether the first vehicle is in a lane-change collision accident-prone zone is determined by the following manner: if all The lane-change collision accident-prone area is marked in the map information, and whether the first vehicle is currently in the lane-change collision-prone area is determined according to the lane-change collision accident-prone area marked in the map information; if the map information is not marked In the lane-change collision-prone area, whether the first vehicle is currently in the lane-change collision-prone area is determined according to the map information; the lane-change accident-prone area includes intersections, ramps, and areas where the number of lanes changes.
  • the lane-changing behavior of the first vehicle can be determined by taking into account the prone area of lane-change collision accidents and different road structures, so that the accuracy of identification can be improved.
  • the lane change behavior is based on at least one lane change identification information and the at least one lane change identification information.
  • the corresponding at least one confidence probability is determined, including: the lane change behavior is determined according to the classification information corresponding to the confidence probability of the maximum value, and the confidence probability of the maximum value is for each of the plurality of classification information.
  • the classification information is obtained by performing classification learning, and the classification information is used to indicate the type of the lane changing behavior of the first vehicle.
  • the vehicle attitude information includes: one of a yaw rate, a steering wheel angle, a steering wheel angle speed, and a vehicle speed. item or items;
  • the lane line information includes: one or more items of the distance from the first vehicle to the lane line, the heading angle of the first vehicle relative to the lane line, the curvature of the lane line, and the derivative of the curvature of the lane line;
  • the road edge information includes: one or more of the distance from the first vehicle to the road edge, the heading angle of the first vehicle relative to the road edge, the curvature of the road edge, and the derivative of the road edge curvature;
  • the target vehicle information includes: One or more items of a target heading angle of the target vehicle relative to the first vehicle and a lateral and longitudinal distance of the target vehicle relative to the first vehicle.
  • a fourth aspect of the embodiments of the present application discloses a chip system, where the chip system includes at least one processor and an interface circuit.
  • the chip system includes at least one memory or is connected to at least one external memory.
  • a computer program is stored in the at least one memory; when the computer program is executed by the processor, the method described in the second aspect and the possible implementation manner of the second aspect is implemented.
  • a fifth aspect of the embodiments of the present application discloses a computer-readable storage medium, where computer programs or instructions are stored in the storage medium, and when the computer programs or instructions are executed by a processor, the second aspect or the second aspect described above is implemented.
  • FIG. 1 is a schematic structural diagram of an information processing system provided by an embodiment of the present application.
  • FIG. 2 is a schematic diagram of a straight track application scenario provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of a curve application scenario provided by an embodiment of the present application.
  • FIG. 4 is a schematic diagram of a method for identifying a lane change intention provided by an embodiment of the present application
  • FIG. 5 is a schematic diagram of a method for identifying a lane change intention provided by an embodiment of the present application.
  • FIG. 6 is a flowchart of an information processing method provided by an embodiment of the present application.
  • FIG. 7 is a schematic diagram of the distance from the first vehicle to the lane line without preprocessing provided by an embodiment of the present application.
  • FIG. 8 is a schematic diagram of a preprocessed first vehicle distance from a lane line provided by an embodiment of the present application.
  • FIG. 9 is a schematic diagram of a logical mapping function provided by an embodiment of the present application.
  • FIG. 10 is a graph of a real-time value of the distance from the first vehicle to the curb and the corresponding mean value provided by an embodiment of the present application;
  • FIG. 11 is a schematic diagram of becoming a lane change voter provided by an embodiment of the present application.
  • FIG. 13 is a schematic structural diagram of an information processing apparatus provided by an embodiment of the present application.
  • FIG. 14 is a schematic structural diagram of an information processing apparatus provided by an embodiment of the present application.
  • FIG. 1 is a schematic structural diagram of an information processing system 1000 provided by an embodiment of the present application.
  • the system includes an acquisition module 1001, a lane change recognition module 1002 based on lane line information and vehicle attitude information, and a lane change recognition module 1002 based on road edge information.
  • Lane change recognition module 1003 based on vehicle attitude information
  • lane change recognition module 1004 based on target vehicle information and vehicle attitude information
  • lane change recognition module 1005 based on map information and vehicle attitude information
  • lane change recognition result arbitration module 1006 and control module 1007 modules 1002-1007 can all be called processing modules, wherein, the acquisition module 1001 is used to acquire input information, and preprocess the input information, such as data interpolation, smoothing filtering, removing abnormal signals, etc.
  • the input information is input to the lane change recognition module 1002 based on lane line information and vehicle attitude information, the lane change recognition module 1003 based on road edge information and vehicle attitude information, the lane change recognition module 1004 based on target vehicle information and vehicle attitude information, and the In the lane change recognition module 1005 of map information and vehicle attitude information, the above four modules obtain at least one lane change identification information and at least one confidence probability corresponding to the at least one lane change identification information according to the input information, and then identify the at least one lane change identification information.
  • the information and at least one confidence probability corresponding to the at least one lane change identification information are input to the lane change identification result arbitration module 1006 to obtain the classification information and the confidence probability corresponding to the classification information, and the control module 1007 according to the classification information and the corresponding confidence probability of the classification information Determine the lane-changing behavior of the first vehicle, and control the first vehicle to perform processing corresponding to the lane-changing behavior. For example, it is determined that the lane-changing behavior of the first vehicle is in a left-lane-changing state.
  • controlling the first vehicle to perform the processing corresponding to the lane changing behavior may be controlling the first vehicle to turn on the turn signal, or starting an alarm mechanism, for example, the first vehicle emits an alarm sound, etc. , which is not limited here.
  • the acquisition module 1001 acquires the input information through sensors, and the required sensors include an inertial measurement unit (IMU), a steering angle sensor (SAS), and a wheel speed sensor. , WSS), optional sensors include cameras, lidar, radar, maps, and global positioning system (GPS).
  • IMU inertial measurement unit
  • SAS steering angle sensor
  • WSS wheel speed sensor
  • optional sensors include cameras, lidar, radar, maps, and global positioning system (GPS).
  • GPS global positioning system
  • the embodiments of the present application can be applied to the scene of changing lanes when driving on a straight road as shown in FIG. 2 , and also to the scene of changing lanes when driving on a curved road as shown in FIG. 3 .
  • Own vehicle refers to the vehicle where the sensor is located.
  • the first vehicle is the own vehicle.
  • Target vehicle a vehicle around the own vehicle.
  • the target vehicle is a vehicle around the first vehicle.
  • the lane-changing behavior of the vehicle has 7 states and 24 logical conditions for jumping between states, as shown in Figure 4.
  • the 7 states are not enabled (passive), lane keeping (LK), left deviation (left departure), left lane change (LCL), right deviation (right departure), right change Lane change (LCR), and end of lane change (after lane change, ALC).
  • the vehicle can only be in a single state, and can only jump to the next state when the jump logic condition in a certain state is satisfied.
  • the jump logic condition 11 is satisfied, the vehicle jumps from the lane keeping state to the left deviation state.
  • three states are taken for description.
  • the lane-changing behavior of the first vehicle includes that the first vehicle is in a left lane-changing state, in a lane-changing state, and in a right-lane state.
  • the lane line information may include: one or more of the distance from the first vehicle to the lane line, the heading angle of the first vehicle relative to the lane line, the curvature of the lane line, and the derivative of the curvature of the lane line.
  • the vehicle attitude information of the first vehicle may include one or more of: a yaw rate, a steering wheel angle, a steering wheel angle speed, and a vehicle speed.
  • the curb information may include: one or more items of the distance from the first vehicle to the curb, the heading angle of the first vehicle relative to the curb, the curb curvature, and the curb curvature derivative.
  • the target vehicle information may include one or more of: a target heading angle of the target vehicle relative to the first vehicle, and a lateral and longitudinal distance of the target vehicle relative to the first vehicle.
  • a lane change intention recognition method is shown in Figure 4.
  • the lane line information and vehicle attitude information are obtained through sensors such as cameras and lidars, and then the lane line information corresponding to the lane where the vehicle is located is used, such as the distance from the vehicle on both sides of the vehicle.
  • Information such as lane line position and road curvature, as well as vehicle attitude information, such as steering wheel angle, yaw rate, lateral velocity, lateral displacement, etc., are used as input quantities.
  • a fixed threshold is used to detect the positions of peaks and valleys, and the input is compared with the fixed threshold to determine the lane-changing behavior of the vehicle.
  • the method of obtaining lane line information and vehicle attitude information through sensors such as cameras and lidars to determine the lane-changing behavior of the vehicle also has the following disadvantages: the lane line information depends on the acquisition of sensors such as cameras and lidars. When it is not good or the sensor transmission fails, the lane line information cannot be clearly obtained, which may easily lead to missed identification or misidentification of whether the vehicle has changed lanes; The recognition accuracy is reduced, so this method is not suitable for vehicles without cameras or lidar sensors. For example, vehicles only equipped with millimeter-wave radar cannot use this method to identify the intention of changing lanes.
  • FIG. 5 Another method of lane change intention recognition is shown in Figure 5.
  • this method has the following disadvantages: it needs to record a large amount of historical trajectory data to determine the preset trajectory, which requires a lot of storage space, and consumes a lot of computing power. When the actual road conditions are complex and the driving styles of drivers are different, it cannot be guaranteed. The accuracy of the preset trajectory and the uncertainty of the current driving trajectory of the vehicle are also relatively large, which is easy to cause misidentification.
  • FIG. 6 is an information processing method provided by an embodiment of the present application. The method includes but is not limited to the following steps:
  • Step S601 Acquire at least two of lane line information corresponding to the lane where the first vehicle is located, vehicle posture information of the first vehicle, road edge information, target vehicle information and map information.
  • the input information is obtained through sensors.
  • the sensors include mandatory sensors and optional sensors.
  • the mandatory sensors include IMU, SAS, and WSS.
  • the mandatory sensors are used to obtain vehicle attitude information; optional sensors include cameras. , lidar, radar, map and GPS, among which, camera can be used to obtain lane line information, road edge information and target vehicle information, lidar can be used to obtain road edge information and target vehicle information, map and GPS are used to obtain map information.
  • the lane line information corresponding to the lane where the first vehicle is located may include: one or more of the distance from the first vehicle to the lane line, the heading angle of the first vehicle relative to the lane line, the curvature of the lane line, and the derivative of the curvature of the lane line;
  • the vehicle attitude information of the first vehicle may include one or more of: yaw rate, steering wheel angle, steering wheel angular velocity and vehicle speed;
  • the road edge information may include: the distance from the first vehicle to the curb, the first vehicle relative to the curb
  • target vehicle information may include: target heading angle of the target vehicle relative to the first vehicle, and one of the horizontal and vertical distances of the target vehicle relative to the first vehicle or multiple.
  • the lane line information, vehicle attitude information, road edge information, target vehicle information, and map information are obtained through preprocessing, rather than unprocessed raw data.
  • the preprocessing includes data interpolation, Smoothing filtering, removing abnormal signals, etc.
  • FIG. 8 The data after the distance data is smoothed and filtered is shown in Figure 8.
  • Step S602 Determine at least one confidence probability corresponding to at least one lane change identification information and at least one lane change identification information according to at least two of lane line information, vehicle attitude information, road edge information, target vehicle information and map information.
  • At least two of lane line information, vehicle attitude information, road edge information, target vehicle information and map information are used to indicate at least one lane change identification information and at least one confidence probability corresponding to the at least one lane change identification information , that is to say, at least one lane change identification information and at least one lane change identification information corresponding to the first vehicle can be determined according to at least two of lane line information, vehicle attitude information, road edge information, target vehicle information and map information The corresponding at least one confidence probability.
  • the lane change identification information is used to indicate the category of the lane change behavior of the first vehicle
  • the lane change behavior of the first vehicle may include 7 states of the vehicle lane change process, which are as follows: Disabled, Lane Keeping, Leftward Departure, Lane Change Left, Departure Right, Lane Change Right, and End of Lane Change.
  • the lane-changing behavior of the first vehicle includes the first vehicle being in a left lane-changing state, in a lane-changing state, and in a right-lane state.
  • the confidence probability corresponding to the lane change identification information represents the possibility corresponding to the lane change behavior of the first vehicle.
  • the lane change identification information may be 1, 0, -1, where 1 indicates that the first vehicle is in a left lane change state, 0 indicates that the first vehicle does not change lanes, and -1 indicates that the first vehicle is in a right lane state
  • the confidence probability represents the probability that the lane change identification information is 1, 0, or -1. In an example, assuming that the first lane change identification information is 1 and the first confidence probability corresponding to the first lane change identification information is 80%, then the probability that the first vehicle is in a left lane change state is 80%.
  • the at least one lane change identification information may include first lane change identification information, second lane change identification information, third lane change identification information, and fourth lane change identification information, and at least one confidence information corresponding to the at least one lane change identification information
  • the degree probabilities may include a first confidence degree probability, a second confidence degree probability, a third confidence degree probability, and a fourth confidence degree probability.
  • the lane line information and the vehicle attitude information are used to indicate the first lane change identification information of the first vehicle and the first confidence probability corresponding to the first lane change identification information; the road edge information and the vehicle attitude information are used to indicate the first vehicle The second lane change identification information and the second confidence probability corresponding to the second lane change identification information; the target vehicle information and vehicle attitude information are used to indicate that the third lane change identification information of the first vehicle corresponds to the third lane change identification information
  • the third confidence probability of and the vehicle attitude information to determine the first lane change identification information and the first confidence probability, determine the second lane change identification information and the second confidence probability according to the road edge information and the vehicle attitude information, and determine the first lane change identification information and the second confidence probability according to the target vehicle information and the vehicle attitude information.
  • the third lane change identification information and the fourth confidence probability are determined, and the fourth lane change identification information and the fourth confidence probability are determined according to the map information and the vehicle attitude information.
  • determining the first lane change identification information of the first vehicle and the first confidence probability corresponding to the first lane change identification information according to the lane line information and the vehicle attitude information including:
  • the first confidence probability is determined according to the lane line information and the vehicle attitude information, and the first lane change identification information is determined according to the first confidence probability. That is to say, the lane line information and the vehicle attitude information are used to indicate the first confidence probability, and the first lane change identification information is determined according to the first confidence probability.
  • determining the first confidence probability according to the lane line information and the vehicle attitude information may be by using a logical mapping function to map the lane line information and the vehicle attitude information to determine multiple first mapping values; and then weighting the multiple first mapping values The summation determines the first confidence probability.
  • a plurality of first mapping values are determined by mapping the lane line information and the vehicle attitude information through a logical mapping function, including mapping the lane line information, the vehicle attitude information, the logical threshold corresponding to the lane line information and the logical threshold corresponding to the vehicle attitude information through the logical function. Mapping is performed to determine a plurality of first mapping values.
  • the logic threshold corresponding to the lane line information and the logic threshold corresponding to the vehicle attitude information may be calibrated according to experience, or obtained by learning a large amount of lane line information and vehicle attitude information data, which is not limited in detail. .
  • the logical mapping function can be a standard logistic function, as shown in Figure 9, and its expression is as follows:
  • the logical function is used to map v i and v′ i to obtain a plurality of first mapping values, and the specific representation is as follows:
  • the weighted summation of the multiple first mapping values obtains the first confidence probability p 1 , and the specific representation is as follows;
  • w 1 , w 2 ,...,w n represent the weight values corresponding to the lane line and the vehicle attitude information, which can be different or the same value according to the influence degree of the lane line and the vehicle attitude information.
  • the weight of the corresponding distance between the first vehicle and the lane line for example, the value of w 1 can be larger.
  • the vehicle attitude information The yaw rate is not very related to the vehicle lane change, so the weight of the yaw rate in the corresponding vehicle attitude information, for example, the value of w 2 can be smaller.
  • determining the first lane change identification information according to the first confidence probability includes:
  • the first lane change identification information is determined according to the number of times that the first confidence probability is greater than the first threshold within the first preset time length.
  • the first threshold may be calibrated according to experience, or may be obtained by learning a large amount of data of the first confidence probability, which is not specifically limited. Determining the first lane change identification information according to the number of times means that the first lane change identification information can be determined only when the number of times meets a certain condition.
  • the lane change identification information corresponding to the left lane change state is 1, the lane change identification information corresponding to the lane keeping state is 0, and the lane change identification information corresponding to the right lane change state is -1;
  • the first preset time The length is 6 cycles, and the time length of each cycle is 20ms, then the value of the first confidence probability p corresponding to the 6 cycles is 0.7, 0.8, 0.4, 0.5, 0.9, 0.8, and the value of the first threshold ⁇ is The value is 0.6, where the number of times the first confidence probability p is greater than the first threshold ⁇ is 4 times, assuming that the second threshold N is 3, because the 4 times are greater than the second threshold N is 3, the first vehicle satisfies the jump logic condition, Jump to the corresponding state to determine the first lane change identification information.
  • the first vehicle jumps to the left lane change state, then determine that the lane change identification information corresponding to the left lane change state is 1, that is, the first lane change identification information is
  • determining the second lane change identification information of the first vehicle and the second confidence probability corresponding to the second lane change identification information according to the road edge information and the vehicle attitude information including:
  • the second confidence probability is determined according to the difference value, the information in the road edge information except the distance from the first vehicle to the road edge, and the vehicle attitude information; the second lane change identification information is determined according to the second confidence probability.
  • the difference value may be the difference between the real-time value d of the distance from the first vehicle to the road edge in the road edge information and the average value d avg corresponding to the real-time value, and the average value d avg corresponding to the real-time value is the second preset time length The average value of the distance from the first vehicle to the curb in the curb information within .
  • the mean value davg corresponding to the real-time value d of the distance from the first vehicle to the roadside in the roadside information may be within the second preset time length before the time corresponding to the real-time value d (including the time corresponding to the real-time value d).
  • the mean of the distance from the first vehicle to the curb In an example, assuming that the second preset time length is 3 seconds, the real-time value d of the distance between the first vehicle and the curb at the 36th second is 2 meters, and at the 34th, 35th, and 36th seconds, the distance between the first vehicle and the curb is 2 meters. They are 2.3 meters, 2.6 meters, and 2 meters respectively.
  • the average d avg of the distance from the first vehicle to the curb at the 34th, 35th, and 36th seconds is 2.3 meters
  • the mean d avg corresponding to 2 meters is 2.3.
  • FIG. 10 shows a graph of the real-time value of the distance from the first vehicle to the curb and the corresponding mean value.
  • curve 1 represents the real-time value of the distance from the first vehicle to the left side of the road
  • curve 2 represents the mean value corresponding to the real-time value of the distance from the first vehicle to the left side of the road
  • curve 3 represents the real-time value of the distance from the first vehicle to the right side of the road.
  • curve 4 represents the mean value corresponding to the real-time value of the distance between the first vehicle and the right side of the road;
  • the information other than the distance from the first vehicle to the curb in the curb information may refer to one or more items of the first vehicle relative curb heading angle, curb curvature, and curb curvature derivative.
  • Determine the second confidence probability according to the difference value, the information other than the distance from the first vehicle to the road edge in the road edge information, and the vehicle attitude information The other information and the vehicle attitude information are mapped to determine multiple first mapping values; and then the multiple first mapping values are weighted and summed to determine the second confidence probability.
  • Mapping the difference value, the information in the road edge information except the distance from the first vehicle to the road edge, and the vehicle attitude information through a logical mapping function to determine a plurality of first mapping values may refer to mapping the difference value, the road edge information except the first vehicle Information other than the distance from the vehicle to the curb and vehicle attitude information, and the logical threshold corresponding to the difference, the logical threshold corresponding to the information other than the distance from the first vehicle to the curb in the road edge information, and the logic corresponding to the vehicle attitude information Threshold mapping determines a plurality of first mapping values.
  • the logical threshold value corresponding to the difference, the logical threshold value corresponding to the information other than the distance from the first vehicle to the road edge in the road edge information, and the logical threshold value corresponding to the vehicle attitude information can be calibrated based on experience, or can be calibrated based on the data set. It is obtained by the way of learning, which is not specifically limited.
  • the difference value, the real-time value of the road edge information except the distance from the first vehicle to the road edge information and the vehicle attitude information can be recorded as v i
  • the second lane change identification information is determined according to the second confidence probability, that is to say, the second lane change identification information is determined according to the second confidence probability.
  • the degree probability determines the first lane change identification information, which will not be repeated here.
  • determining the third lane change identification information of the first vehicle and the third confidence probability corresponding to the third lane change identification information according to the target vehicle information and the vehicle attitude information including:
  • the third confidence probability is determined according to the number of voters changing lanes and the vehicle attitude information within the third preset time length; the third lane change identification information is determined according to the third confidence probability, that is to say, the third confidence probability is based on the The number of voters changing lanes and the vehicle attitude information within the third preset time length are determined.
  • the number of lane-changing voters is determined according to the target heading angle in the target vehicle information and the horizontal and vertical distances in the target vehicle information, that is to say, it can be determined according to the target heading angle in the target vehicle information and the horizontal and vertical distances in the target vehicle information.
  • the longitudinal distance determines the number of voters changing lanes within a third predetermined length of time.
  • the number of lane-change voters within the third preset time length is determined according to the target heading angle in the target vehicle information and the horizontal and vertical distances in the target vehicle information, which can be understood as counting the number of lane-change voters within the third preset time length. process.
  • the number of lane-changing voters refers to the number of target vehicles that support a first category of lane-changing behavior of a first vehicle; the first category is one of the categories of lane-changing behavior of the first vehicle.
  • the number of lane change voters may refer to the number of target vehicles that support the first vehicle in a left lane change state.
  • determining the number of lane-change voters within the third time period may be as follows: within a third preset time period, when the target heading angle in the target vehicle information is greater than a third threshold, and the target vehicle information When the horizontal and vertical distance in the target vehicle information is greater than the fourth threshold, the number of lane-change voters increases; when the target heading angle in the target vehicle information is less than or equal to the third threshold, and/or the horizontal and vertical distances in the target vehicle information When the distance is less than or equal to the fourth threshold, the number of voters who change lanes remains unchanged. In an example, if the number of lane-change voters from the 0th millisecond to the 100th millisecond is counted as shown in FIG.
  • the target vehicle ahead becomes the lane-change voters to the left.
  • the third preset time length is 100ms
  • the third threshold is 55°
  • the fourth threshold is 3 meters.
  • the target vehicles are respectively target vehicle 1 and target vehicle 2, wherein the target heading angle of target vehicle 1 relative to the first vehicle is 60°, the horizontal and vertical distance of target vehicle 1 relative to the first vehicle is 3.1 meters, and the target vehicle 2 relative to the first vehicle is 3.1 meters.
  • the target heading angle of the vehicle is 61°, and the horizontal and vertical distance of the target vehicle 2 relative to the first vehicle is 3.2 meters.
  • the target vehicle 1 is the first vehicle changing lanes to the left.
  • the target vehicle 2 is a voter whose first vehicle changes lanes to the left.
  • the number of lane-changing voters increases from 0 to 2, and it is determined that within the third preset time length, the lane-changing voters are The number is 2.
  • determining the third confidence probability according to the number of lane-change voters and the vehicle attitude information within the third preset time length may be by using a logical mapping function to map the number of lane-change voters, vehicle attitude information, and the number of lane-change voters corresponding to the number of lane-change voters.
  • the logical threshold and the logical threshold corresponding to the vehicle attitude information are mapped to obtain a plurality of first mapping values, and then a weighted summation of the plurality of first mapping values is performed to obtain a third confidence probability.
  • v i and v′ i are mapped to obtain a plurality of first mapping values, as shown in the above formula (2), and then the weighted summation of the plurality of first mapping values to determine the second confidence probability can refer to the above process Formula (3) is not repeated here.
  • the third lane change identification information is determined according to the third confidence probability.
  • the third confidence probability For details, reference may be made to the above-mentioned determination of the first lane change identification information according to the first confidence probability, which will not be repeated here.
  • determining the fourth lane change identification information of the first vehicle and the fourth confidence probability corresponding to the fourth lane change identification information according to the map information and the vehicle attitude information including:
  • the fourth lane change identification information and the fourth confidence probability are determined according to the distance between the first vehicle and the lane line in the lane line information, the vehicle posture information, the semantic information in the map information, and whether the first vehicle is in a lane-change collision accident prone area . That is to say, the fourth lane change identification information and the fourth confidence probability are based on the distance between the first vehicle and the lane line in the lane line information, the vehicle attitude information, the semantic information in the map information and whether the first vehicle is in a lane change collision
  • the accident-prone area is determined, wherein the map information is used to indicate whether the first vehicle is in a lane-change collision accident-prone area.
  • determining whether the first vehicle is in a lane-change collision-prone zone according to the map information can be divided into two situations: the first case: if the map information contains Mark the lane-change collision-prone area, and determine whether the current first vehicle is in the lane-change collision-prone area according to the lane-change collision-prone area marked in the map information; the second case: if the lane-change collision accident-prone area is not marked in the map information
  • the map information it is determined whether the current first vehicle is in a lane-change collision accident-prone zone; the lane-change accident-prone zone includes intersections, ramps, and areas where the number of lanes changes, as shown in Figure 12.
  • the first vehicle in the lane-change collision accident-prone area may be marked as 2, and the first vehicle not in the lane-change collision accident-prone area may be marked as -2.
  • other marking methods are also possible.
  • This embodiment of the present application does not Do limit.
  • the semantic information in the map information may include current lane line dotted and solid line information, information on whether traffic rules allow lane changes, etc., which are not limited here.
  • the current lane line is solid line as 3, the lane line is dashed as -3, traffic rules allow lane change as 4, traffic rules do not allow lane change as -4, of course, there can be other marking methods,
  • the embodiments of the present application are not limited.
  • the fourth lane change identification information and the fourth lane change identification information and the fourth lane change identification information are determined according to the distance between the first vehicle and the lane line in the lane line information, vehicle attitude information, semantic information in the map information, and whether the first vehicle is in an area prone to lane change collision accidents.
  • the confidence probability can be understood as taking the distance of the first vehicle from the lane line, vehicle attitude information, semantic information in the map information, and whether the first vehicle is in a lane-change collision accident-prone area as feature quantities, using a learning algorithm, such as a support vector machine. (support vector machines, SVM), hidden Markov model (hidden markov model, HMM), back propagation (back propagation, BP) neural network, etc. for classification and learning output to obtain the fourth lane change identification information and the fourth confidence level probability.
  • Step S603 Determine the lane change behavior of the first vehicle according to the at least one lane change identification information and at least one confidence probability corresponding to the at least one lane change identification information, and control the first vehicle to perform processing corresponding to the lane change behavior.
  • the processing corresponding to the lane change behavior performed by the first vehicle may include turning on a turn signal, activating a warning mechanism, and the like. For example, it is determined that the lane changing behavior of the first vehicle is in the state of changing lanes to the left. Since the driver of the first vehicle does not turn on the turn signal according to regulations when the first vehicle changes lanes to the left, the first vehicle is controlled to execute the corresponding lane change.
  • the processing of the road behavior may be controlling the first vehicle to turn on a turn signal, or starting an alarm mechanism, for example, the first vehicle emits an alarm sound, etc., which is not limited here.
  • determining the lane-changing behavior of the first vehicle according to the at least one lane-change identification information and at least one confidence probability corresponding to the at least one lane-change identification information may include:
  • Perform classification learning on at least one lane change identification information and at least one confidence probability output multiple classification information and multiple confidence probabilities corresponding to the multiple classification information, compare the confidence probability corresponding to each classification information, and determine the maximum The confidence probability of the value; the lane changing behavior of the first vehicle is determined according to the classification information corresponding to the confidence probability of the maximum value. That is to say, the lane-changing behavior of the first vehicle is determined according to the confidence probability of the maximum value, and the confidence probability of the maximum value is obtained by comparing the confidence probability corresponding to each classification information in the plurality of classification information, The plurality of classification information and the confidence probability corresponding to the plurality of classification information are obtained by classifying and learning at least one lane change identification information and at least one confidence probability.
  • each classification information corresponds to a confidence probability; the classification information is used to indicate the category of the lane changing behavior of the first vehicle.
  • the lane change identification information is 1 and the classification information is 1, indicating that the first vehicle is in a left lane change state, and the lane change identification information is 0 and the classification information is 0, indicating that the first vehicle is in a lane-changing state , the lane change identification information is -1, and the classification information is -1, both indicate that the first vehicle is in a right lane change state.
  • the at least one lane change identification information includes first lane change identification information, second lane change identification information, third lane change identification information, and fourth lane change identification information
  • the at least one confidence probability includes the first confidence probability, the second The confidence probability, the third confidence probability and the fourth confidence probability
  • L 41 corresponds to p 41
  • L 42 corresponds to p 42
  • L 43 corresponds to p 43
  • the at least one lane change identification information and at least one confidence probability are used as feature quantities, and a classification learning algorithm is used for classification
  • FIG. 13 is a schematic structural diagram of an information processing apparatus 1300 provided by an embodiment of the present application.
  • the information processing apparatus 1300 may include an acquisition module 1301 and a processing module 1302 , wherein the detailed description of each module is as follows.
  • the obtaining module 1301 is configured to obtain at least two of the lane line information corresponding to the lane where the first vehicle is located, the vehicle posture information of the first vehicle, the road edge information, the target vehicle information or the map information;
  • the processing module 1302 is configured to, according to at least two of the lane line information, the vehicle attitude information, the road edge information, the target vehicle information and the map information, control the first vehicle to execute the corresponding Processing of lane change behavior, the lane change behavior is determined according to at least one lane change identification information and at least one confidence probability corresponding to the at least one lane change identification information, the lane line information, the vehicle attitude information, At least two of the road edge information, the target vehicle information and the map information are used to indicate at least one confidence probability corresponding to the at least one lane change identification information and the at least one lane change identification information;
  • the lane change identification information is used to indicate the type of lane change behavior of the first vehicle.
  • the at least one lane change identification information includes first lane change identification information, second lane change identification information, third lane change identification information, and fourth lane change identification information
  • the at least one lane change identification information includes a first confidence probability, a second confidence probability, a third confidence probability and a fourth confidence probability
  • the lane line information and the vehicle attitude information are used to indicate The first lane change identification information of the first vehicle and the first confidence probability corresponding to the first lane change identification information; the road edge information and the vehicle attitude information are used to indicate the first lane change identification information of the first vehicle.
  • the second confidence probability corresponding to the second lane change identification information and the second lane change identification information; the target vehicle information and the vehicle attitude information are used to indicate the third lane change identification information of the first vehicle and all the third confidence probability corresponding to the third lane change identification information; the map information and the vehicle attitude information are used to indicate that the fourth lane change identification information of the first vehicle corresponds to the fourth lane change identification information
  • the fourth confidence probability of is used to indicate that the fourth lane change identification information of the first vehicle corresponds to the fourth lane change identification information.
  • the lane line information and the vehicle attitude information are used to indicate the first confidence probability; the first lane change identification information is determined according to the first confidence probability of.
  • the first lane change identification information is determined according to the number of times that the first confidence probability is greater than a first threshold within a first preset time period.
  • the second confidence probability is determined according to the difference value, the information in the road edge information except the distance from the first vehicle to the road edge, and the vehicle attitude information ;
  • the difference value is the difference between the real-time value of the distance from the first vehicle to the road edge in the road edge information and the mean value corresponding to the real-time value, and the mean value corresponding to the real-time value is the second preset time length
  • the average value of the distance from the first vehicle to the road edge in the road edge information in the data; the second lane change identification information is determined according to the second confidence probability.
  • the third confidence probability is determined according to the number of lane-change voters and the vehicle attitude information within a third preset time length, and the number of lane-change voters is determined according to the is determined by the target heading angle in the target vehicle information and the horizontal and vertical distances in the target vehicle information; the number of lane-change voters refers to the number of target vehicles that support the first category of lane-changing behavior of the first vehicle. number; the first category is one of the categories of lane-changing behaviors of the first vehicle; the third lane-changing identification information is determined according to the third confidence probability.
  • the number of lane-change voters within the third preset time period is determined by the following manner: within the third preset time period, when the target vehicle information in the If the target heading angle is greater than a third threshold, and the horizontal and vertical distances in the target vehicle information are greater than a fourth threshold, the number of lane-changing voters increases; within the third preset time length, when the target vehicle information The target heading angle in is less than or equal to the third threshold, and/or the horizontal and vertical distance in the target vehicle information is less than or equal to the fourth threshold, and the number of lane-changing voters remains unchanged.
  • the fourth lane change identification information and the fourth confidence probability are based on the distance between the first vehicle and the lane line in the lane line information, the vehicle attitude information, It is determined by the semantic information in the map information and whether the first vehicle is in the lane-change collision-prone area, and the map information is used to indicate whether the first vehicle is in the lane-change collision-prone area.
  • whether the first vehicle is in a lane-change collision-prone area is determined by the following method: if the map information is marked with a lane-change collision-prone area, according to the map information The marked lane-change collision-prone area determines whether the current first vehicle is in the lane-change collision-prone area; if the lane-change collision-prone area is not marked in the map information, the current first vehicle is determined according to the map information. Whether the vehicle is in the lane-change collision accident-prone area; the lane-change accident-prone area includes intersections, ramps, and areas where the number of lanes changes.
  • the lane change behavior is determined according to at least one piece of lane change identification information and at least one confidence probability corresponding to the at least one lane change identification information, including: the lane change behavior is It is determined according to the classification information corresponding to the confidence probability of the maximum value, and the confidence probability of the maximum value is obtained by comparing the confidence probability corresponding to each classification information in the plurality of classification information.
  • the confidence probability corresponding to the plurality of classification information is obtained by classifying and learning the at least one of the lane change identification information and the at least one confidence probability, and the classification information is used to represent the first vehicle category of lane changing behavior.
  • the vehicle attitude information includes one or more of: yaw rate, steering wheel angle, steering wheel angular velocity and vehicle speed;
  • the lane line information includes: the first vehicle distance One or more items of the distance to the lane line, the heading angle of the first vehicle relative to the lane line, the curvature of the lane line, and the derivative of the curvature of the lane line;
  • the road edge information includes: the distance from the first vehicle to the road edge, the One or more of the heading angle of the first vehicle relative to the road edge, the curvature of the road edge, and the derivative of the curvature of the road edge;
  • the target vehicle information includes: the target heading angle of the target vehicle relative to the first vehicle, the target One or more of the lateral and longitudinal distances of the vehicle relative to the first vehicle.
  • each module may also correspond to the corresponding description with reference to the method embodiment shown in FIG. 6 .
  • FIG. 14 is an apparatus 1400 provided by an embodiment of the present application.
  • the apparatus 1400 includes a processor 1401 , a memory 1402 , and an interface circuit 1403 .
  • the processor 1401 , the memory 1402 , and the interface circuit 1403 communicate with each other through a bus 1404 connect.
  • the memory 1402 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM), or A portable read-only memory (compact disc read-only memory, CD-ROM), the memory 1402 is used for related instructions and data.
  • the interface circuit 1403 is used to receive and transmit data.
  • the processor 1401 may be one or more central processing units (central processing units, CPUs). In the case where the processor 1401 is a CPU, the CPU may be a single-core CPU or a multi-core CPU.
  • the processor 1401 in the device 1400 is configured to read computer programs or instructions stored in the memory 1402, and perform the following operations:
  • the lane change behavior is determined according to at least one lane change identification information and at least one confidence probability corresponding to the at least one lane change identification information, the lane line information, the vehicle attitude information, the road edge information, At least two of the target vehicle information and the map information are used to indicate at least one confidence probability corresponding to the at least one lane change identification information and the at least one lane change identification information; the lane change identification information A category used to represent the lane changing behavior of the first vehicle.
  • the at least one lane change identification information includes first lane change identification information, second lane change identification information, third lane change identification information, and fourth lane change identification information
  • the at least one lane change identification information includes a first confidence probability, a second confidence probability, a third confidence probability and a fourth confidence probability
  • the lane line information and the vehicle attitude information are used to indicate The first lane change identification information of the first vehicle and the first confidence probability corresponding to the first lane change identification information; the road edge information and the vehicle attitude information are used to indicate the first lane change identification information of the first vehicle.
  • the second confidence probability corresponding to the second lane change identification information and the second lane change identification information; the target vehicle information and the vehicle attitude information are used to indicate the third lane change identification information of the first vehicle and all the third confidence probability corresponding to the third lane change identification information; the map information and the vehicle attitude information are used to indicate that the fourth lane change identification information of the first vehicle corresponds to the fourth lane change identification information
  • the fourth confidence probability of is used to indicate that the fourth lane change identification information of the first vehicle corresponds to the fourth lane change identification information.
  • the lane line information and the vehicle attitude information are used to indicate the first confidence probability; the first lane change identification information is determined according to the first confidence probability of.
  • the first lane change identification information is determined according to the number of times that the first confidence probability is greater than a first threshold within a first preset time period.
  • the second confidence probability is determined according to the difference value, the information in the road edge information except the distance from the first vehicle to the road edge, and the vehicle attitude information ;
  • the difference value is the difference between the real-time value of the distance from the first vehicle to the road edge in the road edge information and the mean value corresponding to the real-time value, and the mean value corresponding to the real-time value is the second preset time length
  • the average value of the distance from the first vehicle to the road edge in the road edge information in the data; the second lane change identification information is determined according to the second confidence probability.
  • the third confidence probability is determined according to the number of lane-change voters and the vehicle attitude information within a third preset time length, and the number of lane-change voters is determined according to the is determined by the target heading angle in the target vehicle information and the horizontal and vertical distances in the target vehicle information; the number of lane-change voters refers to the number of target vehicles that support the first category of lane-changing behavior of the first vehicle. number; the first category is one of the categories of lane-changing behaviors of the first vehicle; the third lane-changing identification information is determined according to the third confidence probability.
  • the number of lane-change voters within the third preset time period is determined by the following manner: within the third preset time period, when the target vehicle information in the If the target heading angle is greater than a third threshold, and the horizontal and vertical distances in the target vehicle information are greater than a fourth threshold, the number of lane-changing voters increases; within the third preset time length, when the target vehicle information The target heading angle in is less than or equal to the third threshold, and/or the horizontal and vertical distance in the target vehicle information is less than or equal to the fourth threshold, and the number of lane-changing voters remains unchanged.
  • the fourth lane change identification information and the fourth confidence probability are based on the distance between the first vehicle and the lane line in the lane line information, the vehicle attitude information, It is determined by the semantic information in the map information and whether the first vehicle is in the lane-change collision-prone area, and the map information is used to indicate whether the first vehicle is in the lane-change collision-prone area.
  • whether the first vehicle is in a lane-change collision-prone area is determined by the following method: if the map information is marked with a lane-change collision-prone area, according to the map information The marked lane-change collision-prone area determines whether the current first vehicle is in the lane-change collision-prone area; if the lane-change collision-prone area is not marked in the map information, the current first vehicle is determined according to the map information. Whether the vehicle is in the lane-change collision accident-prone area; the lane-change accident-prone area includes intersections, ramps, and areas where the number of lanes changes.
  • the lane change behavior is determined according to at least one piece of lane change identification information and at least one confidence probability corresponding to the at least one lane change identification information, including: the lane change behavior is It is determined according to the classification information corresponding to the confidence probability of the maximum value, and the confidence probability of the maximum value is obtained by comparing the confidence probability corresponding to each classification information in the plurality of classification information.
  • the confidence probability corresponding to the plurality of classification information is obtained by classifying and learning the at least one of the lane change identification information and the at least one confidence probability, and the classification information is used to represent the first vehicle category of lane changing behavior.
  • the vehicle attitude information includes one or more of: yaw rate, steering wheel angle, steering wheel angular velocity and vehicle speed;
  • the lane line information includes: the first vehicle distance One or more items of the distance to the lane line, the heading angle of the first vehicle relative to the lane line, the curvature of the lane line, and the derivative of the curvature of the lane line;
  • the road edge information includes: the distance from the first vehicle to the road edge, the One or more of the heading angle of the first vehicle relative to the road edge, the curvature of the road edge, and the derivative of the curvature of the road edge;
  • the target vehicle information includes: the target heading angle of the target vehicle relative to the first vehicle, the target One or more of the lateral and longitudinal distances of the vehicle relative to the first vehicle.
  • Embodiments of the present application further provide a chip system, where the chip system includes at least one processor and an interface circuit. Further optionally, the chip system includes at least one memory or is connected to at least one external memory. A computer program is stored in the at least one memory; when the computer program is executed by the processor, the method flow shown in FIG. 6 is realized.
  • Embodiments of the present application further provide a computer-readable storage medium, where computer programs or instructions are stored in the computer-readable storage medium, and when the computer-readable storage medium runs on a processor, the method flow shown in FIG. 6 is implemented.
  • the embodiment of the present application further provides a computer program product, when the computer program product runs on a processor, the method flow shown in FIG. 6 is implemented.
  • An embodiment of the present application further provides a terminal, including at least one processor and an interface circuit, and optionally, at least one memory or connected to at least one external memory.
  • a computer program is stored in the at least one memory; when the computer program is executed by the processor, the method flow shown in FIG. 6 is realized.
  • the terminals include but are not limited to: vehicles, vehicle-mounted terminals, vehicle-mounted controllers, vehicle-mounted modules, vehicle-mounted modules, vehicle-mounted components, vehicle-mounted chips, vehicle-mounted units, vehicle-mounted radars or vehicle-mounted cameras and other sensors.
  • a controller implements the method provided in this application.
  • the process can be completed by instructing the relevant hardware by a computer program, and the program can be stored in a computer-readable storage medium.
  • the program When the program is executed , which may include the processes of the foregoing method embodiments.
  • the aforementioned storage medium includes: ROM or random storage memory RAM, magnetic disk or optical disk and other mediums that can store program codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)

Abstract

本申请实施例提供一种信息处理方法及相关装置，可以应用于自动驾驶、无人驾驶或者智能驾驶领域。该装置包括：获取模块，用于获取第一车辆所在的车道对应的车道线信息、第一车辆的车姿信息、路沿信息、目标车辆信息或者地图信息中的至少两种；处理模块，用于根据车道线信息、车姿信息、路沿信息、目标车辆信息和地图信息中的至少两种、控制第一车辆执行对应于变道行为的处理，变道行为是根据至少一个变道识别信息和至少一个变道识别信息对应的至少一个置信度概率确定的，采用本申请实施例能更准确确定第一车辆的变道行为，启动相应应对策略或告警机制，提高安全保障。

Description

一种信息处理方法及相关装置 技术领域
本申请涉及传感器技术领域，尤其涉及一种信息处理方法及相关装置。
背景技术
随着高级辅助驾驶系统(advanced driver-assistance system，ADAS)技术的发展以及自动驾驶(autonomous driving,AD)感知技术的进步，依赖于摄像头、雷达、激光雷达等传感器感知数据的一些智能驾驶算法，如变道预警(lane change warning，LCW)，车道保持辅助(lane keeping assist，LKA)等，需要及时准确的对驾驶员变道意图进行预测和判断，并在成功识别出变道意图后，启动相应应对策略或告警机制。根据调查数据，约50％的变道行为发生时，驾驶员没有按规定开启转向灯。对于驾驶员变道意图的识别与判断，可以弥补驾驶员没有手动开启转向灯场景下，各智能驾驶算法功能的正常运行，提高安全保障。
目前大多数自车变道意图识别技术采用摄像头、激光雷达等传感器数据，从图像域提取车道线信息，同时根据自车与车道线的位置关系，判断自车变道意图。常用的识别方法有设计逻辑阈值判断法或选取车道线信息、自车车姿信息等作为特征量，采用机器学习的方法判断识别。因不同传感器优缺点特性不同、雨雾天气等环境因素、复杂道路情况、驾驶员不同变道风格等因素，传统的自车变道意图识别方法很难保证较高的识别准确率。
发明内容
本申请实施例公开了一种信息处理方法及相关装置，能够更加准确的确定第一车辆的变道行为，启动相应应对策略或告警机制，提高安全保障。
本申请实施例第一方面公开了一种信息处理装置，所述装置包括：获取模块，用于获取第一车辆所在的车道对应的车道线信息、所述第一车辆的车姿信息、路沿信息、目标车辆信息或者地图信息中的至少两种；处理模块，用于根据所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种、控制所述第一车辆执行对应于变道行为的处理，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种用于指示所述至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率；所述变道识别信息用于表示所述第一车辆的变道行为的类别。
在上述装置中，可以根据车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种确定至少一个变道识别信息和至少一个置信度概率，然后根据至少一个变道识别信息和至少一个置信度概率控制第一车辆执行对应于变道行为的处理，例如确定第一车辆的变道行为处于左变道状态，由于该第一车辆向左变道时，第一车辆的驾驶员并没有按照规定开启转向灯，则控制第一车辆执行对应于变道行为的处理可以为控制第一车辆开启转向灯，或者启动告警机制，例如第一车辆发出报警声等等，可以 通过确定第一车辆的变道行为，启动相应的应对策略或告警机制，从而提高驾驶的安全性。而且当遇到雨雾天气光照条件不佳时等，仍然可以确定第一车辆的变道行为，同时能够借助地图信息和道路信息确定第一车辆的变道行为，提高了识别的准确率。
本申请实施例第二方面公开了一种信息处理方法，所述方法包括：获取第一车辆所在的车道对应的车道线信息、所述第一车辆的车姿信息、路沿信息、目标车辆信息或者地图信息中的至少两种；根据所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种、控制所述第一车辆执行对应于变道行为的处理，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种、用于指示所述至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率；所述变道识别信息用于表示所述第一车辆的变道行为的类别。
关于第二方面或可能的实现方式所带来的技术效果，可参考对于第一方面或相应的实施方式的技术效果的介绍。
本申请实施例第三方面公开了一种信息处理装置，包括至少一个处理器和接口电路，可选的，还包括存储器，所述存储器、所述接口电路和所述至少一个处理器通过线路互联，所述至少一个存储器中存储有计算机程序或指令，所述处理器用于读取所述存储器中存储的计算机程序或指令，执行以下操作：
获取第一车辆所在的车道对应的车道线信息、所述第一车辆的车姿信息、路沿信息、目标车辆信息或者地图信息中的至少两种；根据所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种、控制所述第一车辆执行对应于变道行为的处理，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种用于指示所述至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率；所述变道识别信息用于表示所述第一车辆的变道行为的类别。
关于第三方面或可能的实现方式所带来的技术效果，可参考对于第一方面或相应的实施方式的技术效果的介绍。
结合上述任意一个方面或者任意一个方面的任意一种可能的实现方式，在又一种可能的实现方式中，所述至少一个变道识别信息包括第一变道识别信息、第二变道识别信息、第三变道识别信息和第四变道识别信息，所述至少一个变道识别信息对应的至少一个置信度概率包括第一置信度概率、第二置信度概率、第三置信度概率和第四置信度概率，所述车道线信息和所述车姿信息用于指示所述第一车辆的第一变道识别信息和所述第一变道识别信息对应的第一置信度概率；所述路沿信息和所述车姿信息用于指示所述第一车辆的第二变道识别信息和所述第二变道识别信息对应的第二置信度概率；所述目标车辆信息和所述车姿信息用于指示所述第一车辆的第三变道识别信息和所述第三变道识别信息对应的第三置信度概率；所述地图信息和所述车姿信息用于指示所述第一车辆的第四变道识别信息 和所述第四变道识别信息对应的第四置信度概率。
结合上述任意一个方面或者任意一个方面的任意一种可能的实现方式，在又一种可能的实现方式中，所述车道线信息和所述车姿信息用于指示所述第一置信度概率；所述第一变道识别信息是根据所述第一置信度概率确定的。
结合上述任意一个方面或者任意一个方面的任意一种可能的实现方式，在又一种可能的实现方式中，所述第一变道识别信息是根据在第一预设时间长度内，所述第一置信度概率大于第一阈值的次数确定的。
结合上述任意一个方面或者任意一个方面的任意一种可能的实现方式，在又一种可能的实现方式中，所述第二置信度概率是根据差值、所述路沿信息中除所述第一车辆距路沿距离之外的信息和所述车姿信息确定的；所述差值为所述路沿信息中的第一车辆距路沿距离的实时值和所述实时值对应的均值之间的差，所述实时值对应的均值为第二预设时间长度内的所述路沿信息中的第一车辆距路沿距离的平均值；所述第二变道识别信息是根据所述第二置信度概率确定的。
在上述方法中，通过计算第一车辆距路沿距离的实时值和是市值对应的均值之间的差值可以间接的反映第一车辆的变道行为的特征，达到确定第一车辆的变道行为的目的，除了采用车姿信息，还结合了路沿信息确定第一车辆的变道行为，提高了识别的准确率。
结合上述任意一个方面或者任意一个方面的任意一种可能的实现方式，在又一种可能的实现方式中，所述第三置信度概率是根据第三预设时间长度内变道投票者数量和所述车姿信息确定的，所述变道投票者数量是根据所述目标车辆信息中的目标航向角和所述目标车辆信息中的横纵向距离确定的；所述变道投票者数量是指支持所述第一车辆的第一类别的变道行为的目标车辆的数量；所述第一类别为所述第一车辆的变道行为的类别中的一种；所述第三变道识别信息是根据所述第三置信度概率确定的。
结合上述任意一个方面或者任意一个方面的任意一种可能的实现方式，在又一种可能的实现方式中，所述第三预设时间长度内变道投票者数量是通过如下方式确定的：在所述第三预设时间长度内，当所述目标车辆信息中的目标航向角大于第三阈值、且所述目标车辆信息中的横纵向距离大于第四阈值，所述变道投票者数量增加；在所述第三预设时间长度内，当所述目标车辆信息中的目标航向角小于等于所述第三阈值、和/或所述目标车辆信息中的横纵向距离小于等于所述第四阈值，所述变道投票者数量不变。
在上述方法中，通过目标车辆信息中的航向角和横纵向距离可以间接的反映第一车辆的变道行为的特征，达到确定第一车辆的变道行为的目的，除了采用车姿信息，还结合了目标车辆信息确定第一车辆的变道行为，提高了识别的准确率。
结合上述任意一个方面或者任意一个方面的任意一种可能的实现方式，在又一种可能的实现方式中，所述第四变道识别信息和所述第四置信度概率是根据所述车道线信息中的第一车辆距车道线的距离、所述车姿信息、所述地图信息中的语义信息和所述第一车辆是否处于所述变道碰撞事故多发区确定的，所述地图信息用于指示所述第一车辆是否处于所述变道碰撞事故多发区。
结合上述任意一个方面或者任意一个方面的任意一种可能的实现方式，在又一种可能 的实现方式中，所述第一车辆是否处于变道碰撞事故多发区是通过如下方式确定的：若所述地图信息中标注变道碰撞事故多发区，根据所述地图信息中标注的变道碰撞事故多发区确定当前所述第一车辆是否处于变道碰撞事故多发区；若所述地图信息中未标注变道碰撞事故多发区，根据所述地图信息确定当前所述第一车辆是否处于所述变道碰撞事故多发区；所述变道事故多发区包括十字路口、匝道上下口和车道数量变化区域。
在上述方法中，通过考虑变道碰撞事故多发区和不同道路结构确定第一车辆的变道行为，能够提高识别的准确性。
结合上述任意一个方面或者任意一个方面的任意一种可能的实现方式，在又一种可能的实现方式中，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，包括：所述变道行为是根据最大值的置信度概率对应的分类信息确定的，所述最大值的置信度概率是对多个分类信息中的每个分类信息对应的置信度概率进行比较得到的，所述多个分类信息和所述多个分类信息对应的置信度概率是对所述至少一个所述变道识别信息和所述至少一个置信度概率进行分类学习得到的，所述分类信息用于表示所述第一车辆的变道行为的类别。
结合上述任意一个方面或者任意一个方面的任意一种可能的实现方式，在又一种可能的实现方式中，所述车姿信息包括：偏转角速率、方向盘转角、方向盘转角速度和车速中的一项或者多项；所述车道线信息包括：所述第一车辆距车道线距离、所述第一车辆相对车道线航向角、车道线曲率、车道线曲率导数中的一项或者多项；所述路沿信息包括：所述第一车辆距路沿距离、所述第一车辆相对路沿航向角、路沿曲率、路沿曲率导数中的一项或者多项；所述目标车辆信息包括：所述目标车辆相对所述第一车辆的目标航向角、所述目标车辆相对所述第一车辆的横纵向距离中的一项或者多项。
本申请实施例第四方面公开了一种芯片系统，所述芯片系统包括至少一个处理器和接口电路。可选的，所述芯片系统包含至少一个存储器或者连接至少一个外部存储器。所述至少一个存储器中存储有计算机程序；所述计算机程序被所述处理器执行时，实现上述第二方面、第二方面的可能的实现方式所描述的方法。
本申请实施例第五方面公开了一种计算机可读存储介质，所述存储介质中存储有计算机程序或指令，当所述计算机程序或指令被处理器执行时，实现上述第二方面或第二方面的可能的实现方式中所描述的方法。
附图说明
图1是本申请实施例提供的一种信息处理系统的结构示意图；
图2是本申请实施例提供的一种直道应用场景的示意图；
图3是本申请实施例提供的一种弯道应用场景的示意图；
图4是本申请实施例提供的一种变道意图识别方法的示意图；
图5是本申请实施例提供的一种变道意图识别方法的示意图；
图6是本申请实施例提供的一种信息处理方法的流程图；
图7是本申请实施例提供的一种未经过预处理的第一车辆距车道线距离的示意图；
图8是本申请实施例提供的一种经过预处理的第一车辆距车道线距离的示意图；
图9是本申请实施例提供的一种逻辑映射函数的示意图；
图10是本申请实施例提供的一种第一车辆距路沿距离的实时值与对应的均值的曲线图；
图11是本申请实施例提供的一种成为变道投票者的示意图；
图12是本申请实施例提供的一种变道碰撞事故多发区的标注；
图13是本申请实施例提供的一种信息处理装置的结构示意图；
图14是本申请实施例提供的一种信息处理装置的结构示意图。
具体实施方式
下面结合本申请实施例中的附图对本申请实施例进行描述。
请参见图1，图1是本申请实施例提供的一种信息处理系统1000的结构示意图，该系统包括获取模块1001、基于车道线信息和车姿信息的变道识别模块1002、基于路沿信息和车姿信息的变道识别模块1003、基于目标车辆信息和车姿信息的变道识别模块1004、基于地图信息和车姿信息的变道识别模块1005、变道识别结果仲裁模块1006以及控制模块1007，模块1002-1007都可以称为处理模块，其中，获取模块1001用于获取输入信息，并对输入信息进行预处理，例如数据插值、平滑滤波、去除异常信号等等，然后将处理之后的输入信息输入到基于车道线信息和车姿信息的变道识别模块1002、基于路沿信息和车姿信息的变道识别模块1003、基于目标车辆信息和车姿信息的变道识别模块1004、基于地图信息和车姿信息的变道识别模块1005中，上述四个模块根据输入信息得到至少一个变道识别信息和至少一个变道识别信息对应的至少一个置信度概率，然后将至少一个变道识别信息和至少一个变道识别信息对应的至少一个置信度概率输入到变道识别结果仲裁模块1006得到分类信息和分类信息对应的置信度概率，控制模块1007根据分类信息和分类信息对应的置信度概率确定第一车辆的变道行为、控制第一车辆执行对应于变道行为的处理，例如，确定第一车辆的变道行为处于左变道状态，由于该第一车辆向左变道时，第一车辆的驾驶员并没有按照规定开启转向灯，则控制第一车辆执行对应于变道行为的处理可以为控制第一车辆开启转向灯，或者启动告警机制，例如第一车辆发出报警声等等，此处不做限定。其中，获取模块1001获取输入信息的方式是通过传感器获取的，必选的传感器包括惯性测量单元(inertial measurement unit，IMU)、方向盘转角传感器(steering angle sensor，SAS)、轮速计(wheel speed sensor，WSS)，可选的传感器包括摄像头、激光雷达、雷达、地图和全球卫星定位系统(global positioning system，GPS)。本申请实施例适用于搭载必选的传感器和可选的传感器中的全部或部分传感器的车辆。
本申请实施例可应用于如图2所示的，在直道行驶时进行变道的场景，也可应用于如图3所示，在弯道行驶时进行变道的场景。
如上介绍了本申请实施例涉及的一些概念，下面介绍本申请实施例的技术特征。
(1)自车：是指传感器所在的车辆，在本申请实施例中，第一车辆为自车。
(2)目标车辆：自车周围的车辆，在以下实施例中，目标车辆为第一车辆周围的车辆。
(3)车辆的变道行为有7种状态，24个状态间跳转逻辑条件，具体如图4所示。7种 状态分别为未使能(passive)、车道保持(lane keeping，LK)、向左偏离(left departure)、左变道(left lane change，LCL)、向右偏离(right departure)、右变道(right lane change，LCR)、和变道结束(after lane change，ALC)。在任一时刻，车辆只能处于某一种单一状态，只有当某一状态下的跳转逻辑条件满足时，才能跳转至下一状态，在一种示例中，假设当前车辆处于车道保持状态，当满足跳转逻辑条件11时，车辆由车道保持状态跳转至向左偏离状态。下面为了方便举例描述，取3种状态进行说明，例如，第一车辆的变道行为包括第一车辆处于左变道状态，处于不变道状态以及处于右边道状态。
(4)车道线信息可以包括：第一车辆距车道线距离、第一车辆相对车道线航向角、车道线曲率、车道线曲率导数中的一项或者多项。
第一车辆的车姿信息可以包括：偏转角速率、方向盘转角、方向盘转角速度和车速中的一项或者多项。
路沿信息可以包括：第一车辆距路沿距离、第一车辆相对路沿航向角、路沿曲率、路沿曲率导数中的一项或者多项。
目标车辆信息可以包括：目标车辆相对第一车辆的目标航向角、目标车辆相对第一车辆的横纵向距离中的一项或者多项。
目前，一种变道意图识别方法如图4所示，通过摄像头和激光雷达等传感器获取车道线信息和车姿信息，然后使用自车所在的车道对应的车道线信息，例如自车距两侧车道线位置和道路曲率等信息以及车姿信息，例如方向盘转角、横摆角速度、侧向速度、侧向位移等信息作为输入量，通过总结典型变道行为发生时，输入量的变化特征，设计固定的阈值门限和检测波峰波谷的位置，将该输入量与固定的阈值门限进行比较，确定自车的变道行为。但是通过摄像头和激光雷达等传感器获取车道线信息和车姿信息确定自车的变道行为的方式也有以下缺点：车道线信息依赖于摄像头、激光雷达等传感器获取，当遇到雨雾天气、光照条件不佳或者传感器发送故障的时候，无法清晰的获取车道线信息，容易导致漏识别或者误识别自车是否发生了变道；其次，当无法获取车道线信息，仅仅依靠车姿信息判断，会导致识别准确性降低，因此该方法不适用于无摄像头或无激光雷达传感器的车辆，例如仅仅搭载毫米波雷达的车辆无法使用该方法识别自车变道意图。
又一种变道意图识别方法如图5所示，获取车辆的行车历史轨迹数据，然后通过学习算法对该行车历史轨迹数据进行学习获得该车辆保持在当前车道内行驶的预设轨迹，然后摄像头、雷达等传感器获取该车辆当前行驶轨迹，通过当前行驶轨迹是否偏离预设轨迹超过预定的时间阈值，判断该车辆是否发生变道行为。但是该方法具有以下缺点：需要记录大量的历史轨迹数据从而确定预设轨迹，会需要大量的存储空间，而且算力消耗比较大，当实际道路情况复杂，而且驾驶员驾驶风格不同时，无法保证预设轨迹的准确性，车辆当前行驶轨迹的不确定性也比较大，容易造成误识别。
请参见图6，图6是本申请实施例提供的一种信息处理方法，该方法包括但不限于如下步骤：
步骤S601：获取第一车辆所在的车道对应的车道线信息、第一车辆的车姿信息、路沿 信息、目标车辆信息和地图信息中的至少两种。
具体地，该车道线信息、车姿信息、路沿信息、目标车辆信息和地图信息中的至少两种可以简称为输入信息。该输入信息是通过传感器获取的，传感器包括必须包含的传感器和可选的传感器，必须包含的传感器有IMU、SAS、WSS，该必须包含的传感器用于获取车姿信息；可选的传感器包含摄像头、激光雷达、雷达、地图和GPS，其中，摄像头可以用于获取车道线信息、路沿信息和目标车辆信息，激光雷达可以用于获取路沿信息和目标车辆信息，地图和GPS用于获取地图信息。
具体地，第一车辆所在的车道对应的车道线信息可以包括：第一车辆距车道线距离、第一车辆相对车道线航向角、车道线曲率、车道线曲率导数中的一项或者多项；第一车辆的车姿信息可以包括：偏转角速率、方向盘转角、方向盘转角速度和车速中的一项或者多项；路沿信息可以包括：第一车辆距路沿距离、第一车辆相对路沿航向角、路沿曲率、路沿曲率导数中的一项或者多项；目标车辆信息可以包括：目标车辆相对第一车辆的目标航向角、目标车辆相对第一车辆的横纵向距离中的一项或者多项。
具体地，该车道线信息、车姿信息、路沿信息、目标车辆信息和地图信息中的至少两种是经过预处理得到的，而不是未经过预处理的原生数据，预处理包括数据插值、平滑滤波、去除异常信号等等。在一种示例中，假设未经过预处理的车道线信息中的第一车辆距车道线距离的数据如图7所示，对该未经过预处理的车道线信息中的第一车辆距车道线距离的数据进行平滑滤波处理之后的数据如图8所示。
步骤S602：根据车道线信息、车姿信息、路沿信息、目标车辆信息和地图信息中的至少两种，确定至少一个变道识别信息和至少一个变道识别信息对应的至少一个置信度概率。
具体地，车道线信息、车姿信息、路沿信息、目标车辆信息和地图信息中的至少两种、用于指示至少一个变道识别信息和至少一个变道识别信息对应的至少一个置信度概率，也就是说，可以根据车道线信息、车姿信息、路沿信息、目标车辆信息和地图信息中的至少两种、确定第一车辆对应的至少一个变道识别信息和至少一个变道识别信息对应的至少一个置信度概率。
具体地，变道识别信息用于表示第一车辆的变道行为的类别，第一车辆的变道行为可以包括车辆变道过程的7种状态，分别如下：未使能、车道保持、向左偏离、左变道、向右偏离、右变道、和变道结束。以下实施例中，为了方便举例，取3种状态进行说明，例如，第一车辆的变道行为包括第一车辆处于左变道状态，处于不变道状态以及处于右边道状态。变道识别信息对应的置信度概率表示第一车辆的变道行为对应的可能性。在一种示例中，变道识别信息可以为1,0，-1，其中1表示第一车辆处于左变道状态，0表示第一车辆不变道，-1表示第一车辆处于右边道状态；当然，该变道识别信息还可以有其他的表示方式，本申请实施例不做限定。置信度概率表示变道识别信息为1,0，或者-1的概率。在一种示例中，假设第一变道识别信息为1，且第一变道识别信息对应的第一置信度概率为80％，那么认为第一车辆处于左变道状态的概率为80％。
具体地，至少一个变道识别信息可以包括第一变道识别信息、第二变道识别信息、第三变道识别信息和第四变道识别信息，至少一个变道识别信息对应的至少一个置信度概率可以包括第一置信度概率、第二置信度概率、第三置信度概率和第四置信度概率。其中， 车道线信息和车姿信息用于指示第一车辆的第一变道识别信息和第一变道识别信息对应的第一置信度概率；路沿信息和车姿信息用于指示第一车辆的第二变道识别信息和第二变道识别信息对应的第二置信度概率；目标车辆信息和车姿信息用于指示第一车辆的第三变道识别信息和第三变道识别信息对应的第三置信度概率；地图信息和车姿信息用于指示第一车辆的第四变道识别信息和第四变道识别信息对应的第四置信度概率；也就是说，可以根据车道线信息和车姿信息确定第一变道识别信息和第一置信度概率，根据路沿信息和车姿信息确定第二变道识别信息和第二置信度概率，根据目标车辆信息和车姿信息确定第三变道识别信息和第四置信度概率，根据地图信息和车姿信息确定第四变道识别信息和第四置信度概率。
在一种可能的实现方式中，根据车道线信息和车姿信息确定第一车辆的第一变道识别信息和该第一变道识别信息对应的第一置信度概率，包括：
根据车道线信息和车姿信息确定第一置信度概率，根据第一置信度概率确定第一变道识别信息。也就是说车道线信息和车姿信息用于指示第一置信度概率，第一变道识别信息是根据第一置信度概率确定的。
具体地，根据车道线信息和车姿信息确定第一置信度概率可以是通过逻辑映射函数将车道线信息和车姿信息进行映射确定多个第一映射值；然后将多个第一映射值加权求和确定第一置信度概率。通过逻辑映射函数将车道线信息和车姿信息进行映射确定多个第一映射值，包括通过逻辑函数将车道线信息、车姿信息、车道线信息对应的逻辑阈值和车姿信息对应的逻辑阈值进行映射确定多个第一映射值。该车道线信息对应的逻辑阈值和车姿信息对应的逻辑阈值可以是根据经验进行标定的，也可以是通过对大量的车道线信息和车姿信息数据进行学习的方式得到的，具体不做限定。可以将车身偏离、变道开始以及变道结束时，车道线信息及车姿信息的实时值记为v i，其中，i＝1,2,3,……，n，n为正整数，将车身偏离、变道开始以及变道结束时，车道线信息对应的逻辑阈值以及车姿信息对应的逻辑阈值记为v′ i，其中，i＝1,2,3,……，n，n为正整数。在一种示例中，车道线信息中的第一车辆距车道线距离v 1＝1米，第一车辆距车道线距离的逻辑阈值v′ 1＝1.1米，车姿信息中的车速v 2＝50千米/小时，车姿信息中车速对应的逻辑阈值v′ 2＝49千米/小时，具体的车道线信息和车姿信息中的其他项不进行一一举例。逻辑映射函数可以为标准logistics函数，如图9所示，其表达形式如下：
Figure PCTCN2021072211-appb-000001
然后通过逻辑函数将v i和v′ i进行映射得到多个第一映射值，具体表示形式如下：
Figure PCTCN2021072211-appb-000002
假设得到的多个第一映射值为f 1,f 2,……，f n，将该多个第一映射值加权求和得到第一置信度概率p 1，具体表示形式如下；
p 1＝w 1*f 1+w 2*f 2+…+w n*f n      (3)
其中，w 1,w 2,……,w n表示车道线和车姿信息对应的权重值，可以根据车道线和车姿信息的影响程度，取不同或相同的值，例如，车道线信息中第一车辆距车道线距离能够很直观的反映第一车辆是否变道，因此，对应的第一车辆距车道线距离的权重，例如w 1的取值可以大一些，相应的，车姿信息中的偏转角速率与车辆变道不太相关，那么对应的车姿信息中的偏转角速率的权重，例如w 2的取值可以小一些。
在一种可能的实现方式中，根据第一置信度概率确定第一变道识别信息，包括：
确定第一预设时间长度内，第一置信度概率大于第一阈值的次数，根据次数确定第一变道识别信息。也就是说第一变道识别信息是根据第一预设时间长度内，第一置信度概率大于第一阈值的次数确定的。
具体地，第一阈值可以是根据经验进行标定的，也可以是通过对大量的第一置信度概率的数据学习得到的，具体不做限定。根据次数确定第一变道识别信息是指只有当次数满足一定条件，才能够确定第一变道识别信息。
在一种示例中，假设左变道状态对应的变道识别信息为1，车道保持对应的变道识别信息为0，右变道状态对应的变道识别信息为-1；第一预设时间长度为6个周期，每个周期的时间长度为20ms，那么该6个周期对应的第一置信度概率p的取值为0.7、0.8、0.4、0.5、0.9、0.8，第一阈值α的取值为0.6，其中第一置信度概率p大于第一阈值α的次数为4次，假设第二阈值N为3，因为4次大于第二阈值N为3，第一车辆满足跳转逻辑条件，跳转至对应的状态，从而确定第一变道识别信息，假设第一车辆跳转至左变道状态，那么确定左变道状态对应的变道识别信息为1，即第一变道识别信息为1。
在一种可能的实现方式中，根据路沿信息和车姿信息确定第一车辆的第二变道识别信息和该第二变道识别信息对应的第二置信度概率，包括：
根据差值、路沿信息中除第一车辆距路沿距离之外的信息和车姿信息确定第二置信度概率；根据第二置信度概率确定第二变道识别信息。
具体地，差值可以为路沿信息中的第一车辆距路沿距离的实时值d和实时值对应的均值d avg之间的差，实时值对应的均值d avg为第二预设时间长度内的路沿信息中的第一车辆距路沿距离的平均值。
具体地，路沿信息中第一车辆距路沿距离的实时值d对应的均值d avg可以是实时值d对应的时刻之前(包括实时值d对应的时刻)的第二预设时间长度内的第一车辆距路沿距离的均值。在一种示例中，假设第二预设时间长度为3秒，第36秒时第一车辆距路沿距离的实时值d为2米，第34、35、36秒第一车辆距路沿距离分别为2.3米、2.6米、2米，该第34、35、36秒第一车辆距路沿距离的均值d avg为2.3米，那么第36秒时第一车辆距路沿 距离的实时值d为2米对应的均值d avg为2.3。例如，如图10所示，图10表示第一车辆距路沿距离的实时值与对应的均值的曲线图。其中曲线1表示第一车辆距左侧路沿距离的实时值，曲线2表示第一车辆距左侧路沿距离的实时值对应的均值；曲线3表示第一车辆距右侧路沿距离的实时值，曲线4表示第一车辆距右侧路沿距离的实时值对应的均值；
具体地，路沿信息中除第一车辆距路沿距离之外的信息可以是指第一车辆相对路沿航向角、路沿曲率、路沿曲率导数中的一项或者多项。根据差值、路沿信息中除第一车辆距路沿距离之外的信息和车姿信息确定第二置信度概率通过逻辑映射函数将差值、路沿信息中除第一车辆距路沿距离之外的信息和车姿信息进行映射确定多个第一映射值；然后将多个第一映射值加权求和确定第二置信度概率。通过逻辑映射函数将差值、路沿信息中除第一车辆距路沿距离之外的信息和车姿信息进行映射确定多个第一映射值可以是指将差值、路沿信息中除第一车辆距路沿距离之外的信息和车姿信息、以及差值对应的逻辑阈值、路沿信息中除第一车辆距路沿距离之外的信息对应的逻辑阈值、车姿信息对应的逻辑阈值进行映射确定多个第一映射值。差值对应的逻辑阈值、路沿信息中除第一车辆距路沿距离之外的信息对应的逻辑阈值、车姿信息对应的逻辑阈值可以是根据经验进行标定的，也可以是通过对数据集进行学习的方式得到的，具体不做限定。
具体地，可以将差值、路沿信息中除第一车辆距路沿距离之外的信息和车姿信息的实时值记为v i，将差值对应的逻辑阈值、路沿信息中除第一车辆距路沿距离之外的信息对应的逻辑阈值和车姿信息对应的逻辑阈值记为v′ i，其中，i＝1,2,3,……，n，n为正整数，然后将v i和v′ i进行映射得到多个第一映射值,具体如上述公式(2)所示，然后将多个第一映射值加权求和确定第二置信度概率的过程可以参考上述公式(3)，此处不再赘述。
在一种可能的实施方式中，根据第二置信度概率确定第二变道识别信息，也就是说第二变道识别信息是根据第二置信度概率确定的，具体可以参考上述根据第一置信度概率确定第一变道识别信息，此处不再赘述。
在一种可能的实现方式中，根据目标车辆信息和车姿信息确定第一车辆的第三变道识别信息和第三变道识别信息对应的第三置信度概率，包括：
根据在第三预设时间长度内变道投票者数量、车姿信息确定第三置信度概率；根据第三置信度概率确定第三变道识别信息，也就是说第三置信度概率是根据在第三预设时间长度内变道投票者数量和车姿信息确定的。
具体地，变道投票者数量是根据目标车辆信息中的目标航向角和目标车辆信息中的横纵向距离确定的，也就是说可以根据目标车辆信息中的目标航向角和目标车辆信息中的横纵向距离确定在第三预设时间长度内变道投票者数量。根据目标车辆信息中目标航向角和目标车辆信息中的横纵向距离确定在第三预设时间长度内变道投票者数量，可以理解为统计在第三预设时间长度内变道投票者数量的过程。变道投票者数量是指支持第一车辆的第一类别的变道行为的目标车辆的数量；所述第一类别为所述第一车辆的变道行为的类别中 的一种。例如变道投票者数量可以是指支持第一车辆处于向左变道状态的目标车辆的数量。
具体地，确定第三时间长度内变道投票者数量可以通过如下方式：在第三预设时间长度内，当所述目标车辆信息中的目标航向角大于第三阈值、且所述目标车辆信息中的横纵向距离大于第四阈值，所述变道投票者数量增加；当所述目标车辆信息中的目标航向角小于等于所述第三阈值、和/或所述目标车辆信息中的横纵向距离小于等于所述第四阈值，所述变道投票者数量不变。在一种示例中，假如统计第0毫秒至第100毫秒变道投票者数量如图11所示，第一车辆左变道时，前方目标车辆成为左变道投票者。假设在第0毫秒，当前变道投票者的数量为0，第三预设时间长度为100ms，第三阈值为55°，第四阈值为3米在该第三预设长度内的有2个目标车辆，分别为目标车辆1和目标车辆2，其中目标车辆1相对第一车辆的目标航向角为60°，目标车辆1相对第一车辆的横纵向距离为3.1米，目标车辆2相对第一车辆的目标航向角为61°，目标车辆2相对第一车辆的横纵向距离为3.2米由于61°>55°且3.2米>3米，那么目标车辆1为第一车辆向左侧变道的投票者，目标车辆2为第一车辆向左侧变道的投票者，相应的，变道投票者的数量增加，由0变为2，确定在第三预设时间长度内，变道投票者的数量为2。
具体地，根据第三预设时间长度内变道投票者数量、车姿信息确定第三置信度概率可以是通过逻辑映射函数将变道投票者数量、车姿信息以及变道投票者数量对应的逻辑阈值、车姿信息对应的逻辑阈值进行映射得到多个第一映射值，然后将多个第一映射值加权求和得到第三置信度概率。可以将变道投票者数量和车姿信息记为v i，其中，i＝1,2,3,……，n，n为正整数，将变道投票者数量对应的逻辑阈值以及车姿信息对应的逻辑阈值记为v′ i，其中，i＝1,2,3,……，n，n为正整数。然后将v i和v′ i进行映射得到多个第一映射值,具体如上述公式(2)所示，然后将多个第一映射值加权求和确定第二置信度概率的过程可以参考上述公式(3)，此处不再赘述。
在一种可能的实施方式中，根据第三置信度概率确定第三变道识别信息，具体可以参考上述根据第一置信度概率确定第一变道识别信息，此处不再赘述。
在一种可能的实施方式中，根据地图信息和车姿信息确定第一车辆的第四变道识别信息和第四变道识别信息对应的第四置信度概率，包括：
根据车道线信息中的第一车辆距车道线的距离、车姿信息、地图信息中的语义信息和第一车辆是否处于变道碰撞事故多发区确定第四变道识别信息和第四置信度概率。也就是说第四变道识别信息和第四置信度概率是根据车道线信息中的第一车辆距车道线的距离、车姿信息、地图信息中的语义信息和第一车辆是否处于变道碰撞事故多发区确定的，其中地图信息用于指示第一车辆是否处于变道碰撞事故多发区。
具体地，根据地图信息确定第一车辆是否处于变道碰撞事故多发区，也就是说确定第一车辆是否处于变道碰撞事故多发区可以分为两种情况：第一种情况：若地图信息中标注变道碰撞事故多发区，根据地图信息中标注的变道碰撞事故多发区确定当前第一车辆是否处于变道碰撞事故多发区；第二种情况：若地图信息中未标注变道碰撞事故多发区，根据地图信息确定当前第一车辆是否处于变道碰撞事故多发区；变道事故多发区包括十字路口、匝道上下口和车道数量变化区域，如图12所示。具体地，可以将第一车辆处于变道碰撞事 故多发区记为2，将第一车辆不处于变道碰撞事故多发区记为-2，当然也可以有其他的标记方式，本申请实施例不做限定。
具体地，地图信息中的语义信息可以包括当前车道线虚实线信息，交通规则是否允许变道信息等等，此处不做限定。可以将当前车道线是实线记为3，车道线为虚线记为-3，交通规则允许变道记为4，交通规则不允许变道记为-4，当然也可以有其他的标记方式，本申请实施例不做限定。
具体地，根据车道线信息中的第一车辆距车道线的距离、车姿信息、地图信息中的语义信息和第一车辆是否处于变道碰撞事故多发区确定第四变道识别信息和第四置信度概率可以理解为将第一车辆距车道线的距离、车姿信息、地图信息中的语义信息以及第一车辆是否处于变道碰撞事故多发区作为特征量，使用学习算法，例如支持向量机(support vector machines,SVM)、隐马尔科夫模型(hidden markov model,HMM)、反向传播(back propagation，BP)神经网络等等进行分类学习输出得到第四变道识别信息和第四置信度概率。
步骤S603：根据至少一个变道识别信息和至少一个变道识别信息对应的至少一个置信度概率、确定第一车辆的变道行为，控制第一车辆执行对应于变道行为的处理。
具体地，第一车辆执行对应于变道行为的处理可以包括开启转向灯，启动告警机制等等。例如，确定第一车辆的变道行为处于左变道状态，由于该第一车辆向左变道时，第一车辆的驾驶员并没有按照规定开启转向灯，则控制第一车辆执行对应于变道行为的处理可以为控制第一车辆开启转向灯，或者启动告警机制，例如第一车辆发出报警声等等，此处不做限定。
具体地，根据至少一个变道识别信息和至少一个变道识别信息对应的至少一个置信度概率、确定第一车辆的变道行为可以包括：
对至少一个变道识别信息和至少一个置信度概率进行分类学习，输出多个分类信息和多个分类信息对应的多个置信度概率，将每个分类信息对应的置信度概率进行比较，确定最大值的置信度概率；根据最大值的置信度概率对应的分类信息确定第一车辆的变道行为。也就是说，第一车辆的变道行为是根据最大值的置信度概率确定的，最大值的置信度概率是对多个分类信息中的每个分类信息对应的置信度概率进行比较得到的，多个分类信息和多个分类信息对应的置信度概率是对至少一个变道识别信息和至少一个置信度概率进行分类学习得到的。
具体地，每个分类信息对应一个置信度概率；分类信息用于表示第一车辆的变道行为的类别。
在一种示例中，假设变道识别信息为1、分类信息为1都表示第一车辆处于左变道状态，变道识别信息为0、分类信息为0都表示第一车辆处于不变道状态，变道识别信息为-1、分类信息为-1都表示第一车辆处于右变道状态。假设至少一个变道识别信息包括第一变道识别信息、第二变道识别信息、第三变道识别信息、第四变道识别信息，至少一个置信度概率包括第一置信度概率、第二置信度概率、第三置信度概率和第四置信度概率，其中第一变道识别信息为L 1＝1,第一置信度概率为p 1＝0.8,第二变道识别信息为L 2＝1,第二置信度概率为p 2＝0.7,第三变道识别信息为L 3＝0,第三置信度概率为p 3＝0.4,第四变道识别信息为L 41＝1、L 42＝0和L 43＝-1，第四置信度概率为p 41＝0.8、p 42＝0.1、p 43＝0.1,其 中L 41对应p 41，L 42对应p 42，L 43对应p 43，然后将该至少一个变道识别信息和至少一个置信度概率作为特征量，使用分类学习算法进行分类学习输出3个分类信息和3个分类信息对应的3个置信度概率，3个分类信息为La 1＝1、La 2＝0和La 3＝-1,3个分类信息对应的3个置信度概率分别为p′ 1＝0.7、p′ 2＝0.2、p′ 3＝0.1，将该3个置信度概率进行比较，确定p′ 1的值最大，确定置信度概率p′ 1对应的分类信息为La 1＝1，那么确定第一车辆的变道行为第一车辆处于左变道状态。
上述详细阐述了本申请实施例的方法，下面提供了本申请实施例的装置。
请参见图13，图13是本申请实施例提供的一种信息处理装置1300的结构示意图，该信息处理装置1300可以包括获取模块1301和处理模块1302，其中，各个模块的详细描述如下。
获取模块1301，用于获取第一车辆所在的车道对应的车道线信息、所述第一车辆的车姿信息、路沿信息、目标车辆信息或者地图信息中的至少两种；
处理模块1302，用于根据所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种、控制所述第一车辆执行对应于变道行为的处理，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种、用于指示所述至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率；所述变道识别信息用于表示所述第一车辆的变道行为的类别。
在一种可能的实现方式中，所述至少一个变道识别信息包括第一变道识别信息、第二变道识别信息、第三变道识别信息和第四变道识别信息，所述至少一个变道识别信息对应的至少一个置信度概率包括第一置信度概率、第二置信度概率、第三置信度概率和第四置信度概率，所述车道线信息和所述车姿信息用于指示所述第一车辆的第一变道识别信息和所述第一变道识别信息对应的第一置信度概率；所述路沿信息和所述车姿信息用于指示所述第一车辆的第二变道识别信息和所述第二变道识别信息对应的第二置信度概率；所述目标车辆信息和所述车姿信息用于指示所述第一车辆的第三变道识别信息和所述第三变道识别信息对应的第三置信度概率；所述地图信息和所述车姿信息用于指示所述第一车辆的第四变道识别信息和所述第四变道识别信息对应的第四置信度概率。
在又一种可能的实现方式中，所述车道线信息和所述车姿信息用于指示所述第一置信度概率；所述第一变道识别信息是根据所述第一置信度概率确定的。
在又一种可能的实现方式中，所述第一变道识别信息是根据在第一预设时间长度内，所述第一置信度概率大于第一阈值的次数确定的。
在又一种可能的实现方式中，所述第二置信度概率是根据差值、所述路沿信息中除所述第一车辆距路沿距离之外的信息和所述车姿信息确定的；所述差值为所述路沿信息中的第一车辆距路沿距离的实时值和所述实时值对应的均值之间的差，所述实时值对应的均值为第二预设时间长度内的所述路沿信息中的第一车辆距路沿距离的平均值；所述第二变道识别信息是根据所述第二置信度概率确定的。
在又一种可能的实现方式中，所述第三置信度概率是根据第三预设时间长度内变道投票者数量和所述车姿信息确定的，所述变道投票者数量是根据所述目标车辆信息中的目标航向角和所述目标车辆信息中的横纵向距离确定的；所述变道投票者数量是指支持所述第一车辆的第一类别的变道行为的目标车辆的数量；所述第一类别为所述第一车辆的变道行为的类别中的一种；所述第三变道识别信息是根据所述第三置信度概率确定的。
在又一种可能的实现方式中，所述第三预设时间长度内变道投票者数量是通过如下方式确定的：在所述第三预设时间长度内，当所述目标车辆信息中的目标航向角大于第三阈值、且所述目标车辆信息中的横纵向距离大于第四阈值，所述变道投票者数量增加；在所述第三预设时间长度内，当所述目标车辆信息中的目标航向角小于等于所述第三阈值、和/或所述目标车辆信息中的横纵向距离小于等于所述第四阈值，所述变道投票者数量不变。
在又一种可能的实现方式中，所述第四变道识别信息和所述第四置信度概率是根据所述车道线信息中的第一车辆距车道线的距离、所述车姿信息、所述地图信息中的语义信息和所述第一车辆是否处于所述变道碰撞事故多发区确定的，所述地图信息用于指示所述第一车辆是否处于所述变道碰撞事故多发区。
在又一种可能的实现方式中，所述第一车辆是否处于变道碰撞事故多发区是通过如下方式确定的：若所述地图信息中标注变道碰撞事故多发区，根据所述地图信息中标注的变道碰撞事故多发区确定当前所述第一车辆是否处于变道碰撞事故多发区；若所述地图信息中未标注变道碰撞事故多发区，根据所述地图信息确定当前所述第一车辆是否处于所述变道碰撞事故多发区；所述变道事故多发区包括十字路口、匝道上下口和车道数量变化区域。
在又一种可能的实现方式中，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，包括：所述变道行为是根据最大值的置信度概率对应的分类信息确定的，所述最大值的置信度概率是对多个分类信息中的每个分类信息对应的置信度概率进行比较得到的，所述多个分类信息和所述多个分类信息对应的置信度概率是对所述至少一个所述变道识别信息和所述至少一个置信度概率进行分类学习得到的，所述分类信息用于表示所述第一车辆的变道行为的类别。
在又一种可能的实现方式中，所述车姿信息包括：偏转角速率、方向盘转角、方向盘转角速度和车速中的一项或者多项；所述车道线信息包括：所述第一车辆距车道线距离、所述第一车辆相对车道线航向角、车道线曲率、车道线曲率导数中的一项或者多项；所述路沿信息包括：所述第一车辆距路沿距离、所述第一车辆相对路沿航向角、路沿曲率、路沿曲率导数中的一项或者多项；所述目标车辆信息包括：所述目标车辆相对所述第一车辆的目标航向角、所述目标车辆相对所述第一车辆的横纵向距离中的一项或者多项。
需要说明的是，各个模块的实现及有益效果还可以对应参照图6所示的方法实施例的相应描述。
请参见图14，图14是本申请实施例提供的一种装置1400，该装置1400包括处理器1401、存储器1402和接口电路1403，所述处理器1401、存储器1402和接口电路1403通过总线1404相互连接。
存储器1402包括但不限于是随机存储记忆体(random access memory，RAM)、只读存储器(read-only memory，ROM)、可擦除可编程只读存储器(erasable programmable read only memory，EPROM)、或便携式只读存储器(compact disc read-only memory，CD-ROM)，该存储器1402用于相关指令及数据。接口电路1403用于接收和发送数据。
处理器1401可以是一个或多个中央处理器(central processing unit，CPU)，在处理器1401是一个CPU的情况下，该CPU可以是单核CPU，也可以是多核CPU。
该装置1400中的处理器1401用于读取所述存储器1402中存储的计算机程序或指令，执行以下操作：
获取第一车辆对应的车道线信息、所述第一车辆的车姿信息、路沿信息、目标车辆信息或地图信息中的至少两种；
根据所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种、控制所述第一车辆执行对应于变道行为的处理，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种、用于指示所述至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率；所述变道识别信息用于表示所述第一车辆的变道行为的类别。
在一种可能的实现方式中，所述至少一个变道识别信息包括第一变道识别信息、第二变道识别信息、第三变道识别信息和第四变道识别信息，所述至少一个变道识别信息对应的至少一个置信度概率包括第一置信度概率、第二置信度概率、第三置信度概率和第四置信度概率，所述车道线信息和所述车姿信息用于指示所述第一车辆的第一变道识别信息和所述第一变道识别信息对应的第一置信度概率；所述路沿信息和所述车姿信息用于指示所述第一车辆的第二变道识别信息和所述第二变道识别信息对应的第二置信度概率；所述目标车辆信息和所述车姿信息用于指示所述第一车辆的第三变道识别信息和所述第三变道识别信息对应的第三置信度概率；所述地图信息和所述车姿信息用于指示所述第一车辆的第四变道识别信息和所述第四变道识别信息对应的第四置信度概率。
在又一种可能的实现方式中，所述车道线信息和所述车姿信息用于指示所述第一置信度概率；所述第一变道识别信息是根据所述第一置信度概率确定的。
在又一种可能的实现方式中，所述第一变道识别信息是根据在第一预设时间长度内，所述第一置信度概率大于第一阈值的次数确定的。
在又一种可能的实现方式中，所述第二置信度概率是根据差值、所述路沿信息中除所述第一车辆距路沿距离之外的信息和所述车姿信息确定的；所述差值为所述路沿信息中的第一车辆距路沿距离的实时值和所述实时值对应的均值之间的差，所述实时值对应的均值为第二预设时间长度内的所述路沿信息中的第一车辆距路沿距离的平均值；所述第二变道识别信息是根据所述第二置信度概率确定的。
在又一种可能的实现方式中，所述第三置信度概率是根据第三预设时间长度内变道投票者数量和所述车姿信息确定的，所述变道投票者数量是根据所述目标车辆信息中的目标航向角和所述目标车辆信息中的横纵向距离确定的；所述变道投票者数量是指支持所述第 一车辆的第一类别的变道行为的目标车辆的数量；所述第一类别为所述第一车辆的变道行为的类别中的一种；所述第三变道识别信息是根据所述第三置信度概率确定的。
在又一种可能的实现方式中，所述第三预设时间长度内变道投票者数量是通过如下方式确定的：在所述第三预设时间长度内，当所述目标车辆信息中的目标航向角大于第三阈值、且所述目标车辆信息中的横纵向距离大于第四阈值，所述变道投票者数量增加；在所述第三预设时间长度内，当所述目标车辆信息中的目标航向角小于等于所述第三阈值、和/或所述目标车辆信息中的横纵向距离小于等于所述第四阈值，所述变道投票者数量不变。
在又一种可能的实现方式中，所述第四变道识别信息和所述第四置信度概率是根据所述车道线信息中的第一车辆距车道线的距离、所述车姿信息、所述地图信息中的语义信息和所述第一车辆是否处于所述变道碰撞事故多发区确定的，所述地图信息用于指示所述第一车辆是否处于所述变道碰撞事故多发区。
在又一种可能的实现方式中，所述第一车辆是否处于变道碰撞事故多发区是通过如下方式确定的：若所述地图信息中标注变道碰撞事故多发区，根据所述地图信息中标注的变道碰撞事故多发区确定当前所述第一车辆是否处于变道碰撞事故多发区；若所述地图信息中未标注变道碰撞事故多发区，根据所述地图信息确定当前所述第一车辆是否处于所述变道碰撞事故多发区；所述变道事故多发区包括十字路口、匝道上下口和车道数量变化区域。
在又一种可能的实现方式中，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，包括：所述变道行为是根据最大值的置信度概率对应的分类信息确定的，所述最大值的置信度概率是对多个分类信息中的每个分类信息对应的置信度概率进行比较得到的，所述多个分类信息和所述多个分类信息对应的置信度概率是对所述至少一个所述变道识别信息和所述至少一个置信度概率进行分类学习得到的，所述分类信息用于表示所述第一车辆的变道行为的类别。
在又一种可能的实现方式中，所述车姿信息包括：偏转角速率、方向盘转角、方向盘转角速度和车速中的一项或者多项；所述车道线信息包括：所述第一车辆距车道线距离、所述第一车辆相对车道线航向角、车道线曲率、车道线曲率导数中的一项或者多项；所述路沿信息包括：所述第一车辆距路沿距离、所述第一车辆相对路沿航向角、路沿曲率、路沿曲率导数中的一项或者多项；所述目标车辆信息包括：所述目标车辆相对所述第一车辆的目标航向角、所述目标车辆相对所述第一车辆的横纵向距离中的一项或者多项。
需要说明的是，各个操作的实现及有益效果还可以对应参照图6所示的方法实施例的相应描述。
本申请实施例还提供一种芯片系统，所述芯片系统包括至少一个处理器和接口电路。进一步可选的，所述芯片系统包含至少一个存储器或者连接至少一个外部存储器。所述至少一个存储器中存储有计算机程序；所述计算机程序被所述处理器执行时，图6所示的方法流程得以实现。
本申请实施例还提供一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机程序或指令，当其在处理器上运行时，图6所示的方法流程得以实现。
本申请实施例还提供一种计算机程序产品，当所述计算机程序产品在处理器上运行时， 图6所示的方法流程得以实现。
本申请实施例还提供一种终端，包括至少一个处理器和接口电路，可选的，还包括至少一个存储器或者连接至少一个外部存储器。所述至少一个存储器中存储有计算机程序；所述计算机程序被所述处理器执行时，图6所示的方法流程得以实现。所述终端包括但不限于：车辆、车载终端、车载控制器、车载模块、车载模组、车载部件、车载芯片、车载单元、车载雷达或车载摄像头等其他传感器，车辆可通过该车载终端、车载控制器、车载模块、车载模组、车载部件、车载芯片、车载单元、车载雷达或摄像头，实施本申请提供的方法。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，该流程可以由计算机程序来指令相关的硬件完成，该程序可存储于计算机可读取存储介质中，该程序在执行时，可包括如上述各方法实施例的流程。而前述的存储介质包括：ROM或随机存储记忆体RAM、磁碟或者光盘等各种可存储程序代码的介质。

Claims (25)

  1. 一种信息处理装置，其特征在于，所述装置包括：
    获取模块，用于获取第一车辆所在的车道对应的车道线信息、所述第一车辆的车姿信息、路沿信息、目标车辆信息或者地图信息中的至少两种；
    处理模块，用于根据所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种、控制所述第一车辆执行对应于变道行为的处理，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种用于指示所述至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率；所述变道识别信息用于表示所述第一车辆的变道行为的类别。
  2. 根据权利要求1所述的装置，其特征在于，所述至少一个变道识别信息包括第一变道识别信息、第二变道识别信息、第三变道识别信息和第四变道识别信息，所述至少一个变道识别信息对应的至少一个置信度概率包括第一置信度概率、第二置信度概率、第三置信度概率和第四置信度概率，
    所述车道线信息和所述车姿信息用于指示所述第一车辆的第一变道识别信息和所述第一变道识别信息对应的第一置信度概率；
    所述路沿信息和所述车姿信息用于指示所述第一车辆的第二变道识别信息和所述第二变道识别信息对应的第二置信度概率；
    所述目标车辆信息和所述车姿信息用于指示所述第一车辆的第三变道识别信息和所述第三变道识别信息对应的第三置信度概率；
    所述地图信息和所述车姿信息用于指示所述第一车辆的第四变道识别信息和所述第四变道识别信息对应的第四置信度概率。
  3. 根据权利要求2所述的装置，其特征在于，
    所述车道线信息和所述车姿信息用于指示所述第一置信度概率；
    所述第一变道识别信息是根据所述第一置信度概率确定的。
  4. 根据权利要求2或3所述的装置，其特征在于，
    所述第一变道识别信息是根据在第一预设时间长度内，所述第一置信度概率大于第一阈值α的次数确定的。
  5. 根据权利要求2-4任一项所述的装置，其特征在于，
    所述第二置信度概率是根据差值、所述路沿信息中除所述第一车辆距路沿距离之外的信息和所述车姿信息确定的；所述差值为所述路沿信息中的第一车辆距路沿距离的实时值和所述实时值对应的均值之间的差，所述实时值对应的均值为第二预设时间长度内的所述 路沿信息中的第一车辆距路沿距离的平均值；
    所述第二变道识别信息是根据所述第二置信度概率确定的。
  6. 根据权利要求2-5任一项所述的装置，其特征在于，
    所述第三置信度概率是根据第三预设时间长度内变道投票者数量和所述车姿信息确定的，所述变道投票者数量是根据所述目标车辆信息中的目标航向角和所述目标车辆信息中的横纵向距离确定的；所述变道投票者数量是指支持所述第一车辆的第一类别的变道行为的目标车辆的数量；所述第一类别为所述第一车辆的变道行为的类别中的一种；
    所述第三变道识别信息是根据所述第三置信度概率确定的。
  7. 根据权利要求6所述的装置，其特征在于，所述第三预设时间长度内变道投票者数量是通过如下方式确定的：
    在所述第三预设时间长度内，当所述目标车辆信息中的目标航向角大于第三阈值、且所述目标车辆信息中的横纵向距离大于第四阈值，所述变道投票者数量增加；
    在所述第三预设时间长度内，当所述目标车辆信息中的目标航向角小于等于所述第三阈值、和/或所述目标车辆信息中的横纵向距离小于等于所述第四阈值，所述变道投票者数量不变。
  8. 根据权利要求2-7任一项所述的装置，其特征在于，
    所述第四变道识别信息和所述第四置信度概率是根据所述车道线信息中的第一车辆距车道线的距离、所述车姿信息、所述地图信息中的语义信息和所述第一车辆是否处于所述变道碰撞事故多发区确定的，所述地图信息用于指示所述第一车辆是否处于所述变道碰撞事故多发区。
  9. 根据权利要求8所述的装置，其特征在于，所述第一车辆是否处于变道碰撞事故多发区是通过如下方式确定的：
    若所述地图信息中标注变道碰撞事故多发区，根据所述地图信息中标注的变道碰撞事故多发区确定当前所述第一车辆是否处于变道碰撞事故多发区；
    若所述地图信息中未标注变道碰撞事故多发区，根据所述地图信息确定当前所述第一车辆是否处于所述变道碰撞事故多发区；所述变道事故多发区包括十字路口、匝道上下口和车道数量变化区域。
  10. 根据权利要求1-9任一项所述的装置，其特征在于，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，包括：
    所述变道行为是根据最大值的置信度概率对应的分类信息确定的，所述最大值的置信度概率是对多个分类信息中的每个分类信息对应的置信度概率进行比较得到的，所述多个分类信息和所述多个分类信息对应的置信度概率是对所述至少一个所述变道识别信息和所述至少一个置信度概率进行分类学习得到的，所述分类信息用于表示所述第一车辆的变道 行为的类别。
  11. 根据权利要求1-10任一项所述的装置，其特征在于，
    所述车姿信息包括：偏转角速率、方向盘转角、方向盘转角速度和车速中的一项或者多项；
    所述车道线信息包括：所述第一车辆距车道线距离、所述第一车辆相对车道线航向角、车道线曲率、车道线曲率导数中的一项或者多项；
    所述路沿信息包括：所述第一车辆距路沿距离、所述第一车辆相对路沿航向角、路沿曲率、路沿曲率导数中的一项或者多项；
    所述目标车辆信息包括：所述目标车辆相对所述第一车辆的目标航向角、所述目标车辆相对所述第一车辆的横纵向距离中的一项或者多项。
  12. 一种信息处理方法，其特征在于，包括：
    获取第一车辆对应的车道线信息、所述第一车辆的车姿信息、路沿信息、目标车辆信息或地图信息中的至少两种；
    根据所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种、控制所述第一车辆执行对应于变道行为的处理，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，所述车道线信息、所述车姿信息、所述路沿信息、所述目标车辆信息和所述地图信息中的至少两种用于指示所述至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率；所述变道识别信息用于表示所述第一车辆的变道行为的类别。
  13. 根据权利要求12所述的方法，其特征在于，所述至少一个变道识别信息包括第一变道识别信息、第二变道识别信息、第三变道识别信息和第四变道识别信息，所述至少一个变道识别信息对应的至少一个置信度概率包括第一置信度概率、第二置信度概率、第三置信度概率和第四置信度概率，
    所述车道线信息和所述车姿信息用于指示所述第一车辆的第一变道识别信息和所述第一变道识别信息对应的第一置信度概率；
    所述路沿信息和所述车姿信息用于指示所述第一车辆的第二变道识别信息和所述第二变道识别信息对应的第二置信度概率；
    所述目标车辆信息和所述车姿信息用于指示所述第一车辆的第三变道识别信息和所述第三变道识别信息对应的第三置信度概率；
    所述地图信息和所述车姿信息用于指示所述第一车辆的第四变道识别信息和所述第四变道识别信息对应的第四置信度概率。
  14. 根据权利要求12所述的方法，其特征在于，
    所述车道线信息和所述车姿信息用于指示所述第一置信度概率；
    所述第一变道识别信息是根据所述第一置信度概率确定的。
  15. 根据权利要求13或14所述的方法，其特征在于，
    所述第一变道识别信息是根据在第一预设时间长度内，所述第一置信度概率大于第一阈值的次数确定的。
  16. 根据权利要求13-15任一项所述的方法，其特征在于，
    所述第二置信度概率是根据差值、所述路沿信息中除所述第一车辆距路沿距离之外的信息和所述车姿信息确定的；所述差值为所述路沿信息中的第一车辆距路沿距离的实时值和所述实时值对应的均值之间的差，所述实时值对应的均值为第二预设时间长度内的所述路沿信息中的第一车辆距路沿距离的平均值；
    所述第二变道识别信息是根据所述第二置信度概率确定的。
  17. 根据权利要求13-16任一项所述的方法，其特征在于，
    所述第三置信度概率是根据第三预设时间长度内变道投票者数量和所述车姿信息确定的，所述变道投票者数量是根据所述目标车辆信息中的目标航向角和所述目标车辆信息中的横纵向距离确定的；所述变道投票者数量是指支持所述第一车辆的第一类别的变道行为的目标车辆的数量；所述第一类别为所述第一车辆的变道行为的类别中的一种；
    所述第三变道识别信息是根据所述第三置信度概率确定的。
  18. 根据权利要求17所述的方法，其特征在于，所述第三预设时间长度内变道投票者数量是通过如下方式确定的：
    在所述第三预设时间长度内，当所述目标车辆信息中的目标航向角大于第三阈值、且所述目标车辆信息中的横纵向距离大于第四阈值，所述变道投票者数量增加；
    在所述第三预设时间长度内，当所述目标车辆信息中的目标航向角小于等于所述第三阈值、和/或所述目标车辆信息中的横纵向距离小于等于所述第四阈值，所述变道投票者数量不变。
  19. 根据权利要求13-18任一项所述的方法，其特征在于，
    所述第四变道识别信息和所述第四置信度概率是根据所述车道线信息中的第一车辆距车道线的距离、所述车姿信息、所述地图信息中的语义信息和所述第一车辆是否处于所述变道碰撞事故多发区确定的，所述地图信息用于指示所述第一车辆是否处于所述变道碰撞事故多发区。
  20. 根据权利要求19所述的方法，其特征在于，所述第一车辆是否处于变道碰撞事故多发区是通过如下方式确定的：
    若所述地图信息中标注变道碰撞事故多发区，根据所述地图信息中标注的变道碰撞事故多发区确定当前所述第一车辆是否处于变道碰撞事故多发区；
    若所述地图信息中未标注变道碰撞事故多发区，根据所述地图信息确定当前所述第一 车辆是否处于所述变道碰撞事故多发区；所述变道事故多发区包括十字路口、匝道上下口和车道数量变化区域。
  21. 根据权利要求12-20任一项所述的方法，其特征在于，所述变道行为是根据至少一个变道识别信息和所述至少一个变道识别信息对应的至少一个置信度概率确定的，包括：
    所述变道行为是根据最大值的置信度概率对应的分类信息确定的，所述最大值的置信度概率是对多个分类信息中的每个分类信息对应的置信度概率进行比较得到的，所述多个分类信息和所述多个分类信息对应的置信度概率是对所述至少一个所述变道识别信息和所述至少一个置信度概率进行分类学习得到的，所述分类信息用于表示所述第一车辆的变道行为的类别。
  22. 根据权利要求12-21任一项所述的方法，其特征在于，
    所述车姿信息包括：偏转角速率、方向盘转角、方向盘转角速度和车速中的一项或者多项；
    所述车道线信息包括：所述第一车辆距车道线距离、所述第一车辆相对车道线航向角、车道线曲率、车道线曲率导数中的一项或者多项；
    所述路沿信息包括：所述第一车辆距路沿距离、所述第一车辆相对路沿航向角、路沿曲率、路沿曲率导数中的一项或者多项；
    所述目标车辆信息包括：所述目标车辆相对所述第一车辆的目标航向角、所述目标车辆相对所述第一车辆的横纵向距离中的一项或者多项。
  23. 一种终端，其特征在于，包括至少一个处理器和接口电路，所述接口电路和所述至少一个处理器通过线路互联，所述接口电路用于获取计算机程序，当所述计算机程序被所述处理器执行时，权利要求12-22任一项所述的方法得以实现。
  24. 一种芯片系统，其特征在于，所述芯片系统包括至少一个处理器和接口电路，所述接口电路和所述至少一个处理器通过线路互联，所述接口电路用于获取计算机程序，当所述计算机程序被所述处理器执行时，权利要求12-22任一项所述的方法得以实现。
  25. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有计算机程序或指令，当所述计算机程序或指令在处理器上运行时，实现权利要求12-22任一项所述的方法。
PCT/CN2021/072211 2021-01-15 2021-01-15 一种信息处理方法及相关装置 WO2022151369A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202180000263.0A CN112839854B (zh) 2021-01-15 2021-01-15 一种信息处理方法及相关装置
PCT/CN2021/072211 WO2022151369A1 (zh) 2021-01-15 2021-01-15 一种信息处理方法及相关装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/072211 WO2022151369A1 (zh) 2021-01-15 2021-01-15 一种信息处理方法及相关装置

Publications (1)

Publication Number Publication Date
WO2022151369A1 true WO2022151369A1 (zh) 2022-07-21

Family

ID=75929862

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/072211 WO2022151369A1 (zh) 2021-01-15 2021-01-15 一种信息处理方法及相关装置

Country Status (2)

Country Link
CN (1) CN112839854B (zh)
WO (1) WO2022151369A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220289254A1 (en) * 2021-03-11 2022-09-15 Mitsubishi Electric Corporation Other vehicle behavior prediction apparatus, other vehicle behavior prediction method, and automatic driving system
CN116682095A (zh) * 2023-08-02 2023-09-01 天津所托瑞安汽车科技有限公司 一种关注目标的确定方法、装置、设备及存储介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113581205B (zh) * 2021-08-03 2023-01-31 京东鲲鹏(江苏)科技有限公司 一种调整车辆姿态的方法和装置
CN114212110B (zh) * 2022-01-28 2024-05-03 中国第一汽车股份有限公司 障碍物轨迹预测方法、装置、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100023180A1 (en) * 2008-07-24 2010-01-28 Gm Global Technology Operations, Inc. Adaptive vehicle control system with driving style recognition based on lane-change maneuvers
CN105575150A (zh) * 2016-01-29 2016-05-11 深圳市美好幸福生活安全系统有限公司 行车安全行为分析方法、预警方法及其装置
CN105730323A (zh) * 2016-02-18 2016-07-06 吉林大学 一种汽车安全变道自动控制系统及控制方法
CN110020748A (zh) * 2019-03-18 2019-07-16 杭州飞步科技有限公司 轨迹预测方法、装置、设备和存储介质
CN110884490A (zh) * 2019-10-28 2020-03-17 广州小鹏汽车科技有限公司 一种车辆侵入判断及辅助行驶的方法、系统、车辆及存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100209884A1 (en) * 2009-02-18 2010-08-19 Gm Global Technology Operations, Inc. Driving skill recognition based on vehicle left and right turns
CN111133447B (zh) * 2018-02-18 2024-03-19 辉达公司 适于自主驾驶的对象检测和检测置信度的方法和系统
CN110481551B (zh) * 2019-08-16 2020-12-29 中国第一汽车股份有限公司 一种自动换道的控制方法、装置及车辆

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100023180A1 (en) * 2008-07-24 2010-01-28 Gm Global Technology Operations, Inc. Adaptive vehicle control system with driving style recognition based on lane-change maneuvers
CN105575150A (zh) * 2016-01-29 2016-05-11 深圳市美好幸福生活安全系统有限公司 行车安全行为分析方法、预警方法及其装置
CN105730323A (zh) * 2016-02-18 2016-07-06 吉林大学 一种汽车安全变道自动控制系统及控制方法
CN110020748A (zh) * 2019-03-18 2019-07-16 杭州飞步科技有限公司 轨迹预测方法、装置、设备和存储介质
CN110884490A (zh) * 2019-10-28 2020-03-17 广州小鹏汽车科技有限公司 一种车辆侵入判断及辅助行驶的方法、系统、车辆及存储介质

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220289254A1 (en) * 2021-03-11 2022-09-15 Mitsubishi Electric Corporation Other vehicle behavior prediction apparatus, other vehicle behavior prediction method, and automatic driving system
US12071165B2 (en) * 2021-03-11 2024-08-27 Mitsubishi Electric Corporation Automatic driving apparatus and automatic driving method
CN116682095A (zh) * 2023-08-02 2023-09-01 天津所托瑞安汽车科技有限公司 一种关注目标的确定方法、装置、设备及存储介质
CN116682095B (zh) * 2023-08-02 2023-11-07 天津所托瑞安汽车科技有限公司 一种关注目标的确定方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN112839854B (zh) 2022-07-22
CN112839854A (zh) 2021-05-25

Similar Documents

Publication Publication Date Title
WO2022151369A1 (zh) 一种信息处理方法及相关装置
EP3699048B1 (en) Travelling track prediction method and device for vehicle
US11662733B2 (en) Trajectory setting device and trajectory setting method
WO2022105579A1 (zh) 一种基于自动驾驶的控制方法、装置、车辆以及相关设备
WO2022007655A1 (zh) 一种自动换道方法、装置、设备及存储介质
JP6985203B2 (ja) 挙動予測装置
CN114074681B (zh) 基于概率的车道变更决策和运动规划系统及其方法
CN110969055B (zh) 用于车辆定位的方法、装置、设备和计算机可读存储介质
KR20190049221A (ko) 자율주행 차량의 보행자 인식 방법
JP2024023319A (ja) 緊急車両の検出
RU2711031C2 (ru) Обнаружение направления полосы движения транспортного средства
JP2016000602A (ja) 車線変更支援装置
US11042759B2 (en) Roadside object recognition apparatus
CN111399490B (zh) 一种自动驾驶方法以及装置
WO2023230740A1 (zh) 一种异常驾驶行为识别的方法、装置和交通工具
CN114312783A (zh) 用于车辆的道路进入系统和方法及计算机可读存储介质
WO2023123172A1 (zh) 一种驾驶辅助的方法以及相关设备
US12051248B2 (en) Moving body collision avoidance device, collision avoidance method and electronic device
US11628862B2 (en) Vehicle control device, vehicle control method, and storage medium
CN117227714A (zh) 一种自动驾驶车辆转弯避让控制方法及系统
US20230135702A1 (en) Apparatus for controlling autonomous driving and method thereof
CN115257813B (zh) 通过施工障碍物的智能驾驶控制方法及车辆
US20230202497A1 (en) Hypothesis inference for vehicles
JP7147448B2 (ja) 地図情報システム
CN115071701A (zh) 车辆控制装置及车辆控制方法

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: 21918573

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21918573

Country of ref document: EP

Kind code of ref document: A1