CN113581206A - Preceding vehicle intention recognition system and recognition method based on V2V - Google Patents

Preceding vehicle intention recognition system and recognition method based on V2V Download PDF

Info

Publication number
CN113581206A
CN113581206A CN202110888159.1A CN202110888159A CN113581206A CN 113581206 A CN113581206 A CN 113581206A CN 202110888159 A CN202110888159 A CN 202110888159A CN 113581206 A CN113581206 A CN 113581206A
Authority
CN
China
Prior art keywords
vehicle
intention
information
lane
preceding vehicle
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202110888159.1A
Other languages
Chinese (zh)
Inventor
左益芳
王龙翔
毛祺琦
吴旭楠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xintong Institute Innovation Center For Internet Of Vehicles Chengdu Co ltd
Original Assignee
Xintong Institute Innovation Center For Internet Of Vehicles Chengdu Co ltd
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 Xintong Institute Innovation Center For Internet Of Vehicles Chengdu Co ltd filed Critical Xintong Institute Innovation Center For Internet Of Vehicles Chengdu Co ltd
Priority to CN202110888159.1A priority Critical patent/CN113581206A/en
Publication of CN113581206A publication Critical patent/CN113581206A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W60/00Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001Planning or execution of driving tasks
    • B60W60/0027Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W40/00Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W2420/00Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403Image sensing, e.g. optical camera
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W2420/00Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/408Radar; Laser, e.g. lidar
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W2520/00Input parameters relating to overall vehicle dynamics
    • B60W2520/06Direction of travel
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W2520/00Input parameters relating to overall vehicle dynamics
    • B60W2520/12Lateral speed
    • B60W2520/125Lateral acceleration
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W2540/00Input parameters relating to occupants
    • B60W2540/18Steering angle
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W2554/00Input parameters relating to objects
    • B60W2554/40Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404Characteristics
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W2556/00Input parameters relating to data
    • B60W2556/40High definition maps

Landscapes

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

Abstract

The invention discloses a front vehicle intention recognition system and method based on V2V, and belongs to the technical field of intelligent networked vehicles. The system comprises a sensing module, a decision planning module and an execution control module, wherein the sensing module, the decision planning module and the execution control module are sequentially connected. Compared with the prior art, the invention has the beneficial effects that: firstly, the driving intention of the front vehicle is sensed in a V2V mode, the shortage of information acquired by a vehicle-mounted sensor of the vehicle is overcome, and the information beyond the visual range of V2V can ensure that the driving intention of the vehicle can be acquired earlier, so that the vehicle is helped to make more accurate, effective and anthropomorphic decision and motion planning. And secondly, the information of the front vehicle is obtained in a V2V mode, so that the accuracy of the intention identification of the front vehicle is ensured, and the safety of automobile driving is improved.

Description

Preceding vehicle intention recognition system and recognition method based on V2V
The technical field is as follows:
the invention belongs to the technical field of intelligent networked automobiles, and particularly relates to a front automobile intention recognition system and method based on V2V.
Background art:
in the period of automobile intellectualization and networking rapid development, the safety and comfort problems of automobile driving still are important problems to be considered by intelligent networking automobiles, in the stage of development to a higher-level automatic driving technology, the automobile perception-control-decision technology needs to be improved more, and in the perception technology level, V2X can break through the perception boundary of single-automobile intelligence, obtain environment blind area information and beyond visual range information, and obtain richer and more accurate surrounding environment information.
The environmental information acquired through the V2X can be mined more deeply, for example, the driving intentions of other vehicles can be judged more accurately, and the driving intentions of the surrounding vehicles can be acquired earlier by the own vehicle through the identification of the driving intentions of the other vehicles, so that more accurate, effective and anthropomorphic decisions and movement planning can be made. Therefore, the identification research of the driving intentions of other vehicles is an important ring for the safety and comfort of the intelligent networked automobile.
The existing driving intention recognition is that the vehicle senses the surrounding environment based on traditional vehicle-mounted sensing sensors such as a camera and a millimeter wave radar, the driving intention of the surrounding vehicle is inferred and predicted through sensor feedback data, and the sensor feedback data has certain errors, so that the intention recognition accuracy is influenced.
Disclosure of Invention
In order to solve the above problems, the primary objective of the present invention is to provide a system and a method for recognizing the intention of a preceding vehicle based on V2V, the present invention senses the driving intention of a preceding vehicle in a manner of V2V, makes up for the shortage of information obtained by a vehicle-mounted sensor of the vehicle, and ensures that the driving intention recognition of the vehicle can be obtained earlier by the information beyond the visual range of V2V, thereby helping the vehicle to make more accurate, effective and anthropomorphic decision and motion planning.
Another object of the present invention is to provide a system and a method for recognizing a previous vehicle intention based on V2V, which can obtain previous vehicle information in a V2V manner, ensure accuracy of previous vehicle intention recognition, and improve safety of driving a vehicle.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a preceding vehicle intention recognition system based on V2V comprises a sensing module, a decision planning module and an execution control module, wherein the sensing module, the decision planning module and the execution control module are sequentially connected.
Furthermore, the perception module is provided with a vehicle-mounted OBU unit, the system is further provided with an intention identification module for identifying the driving intention of the vehicle, the intention identification module is arranged in the vehicle-mounted OBU unit or in the decision planning module, and the intention identification module CAN identify the driving intention of the vehicle through a CAN signal of the vehicle.
Further, the vehicle-mounted OBU unit receives BSM information in a V2V mode, when the intention identification module is arranged in the vehicle-mounted OBU unit, the vehicle-mounted OBU unit receives the BSM information with intention information and judges the position relation between vehicles to determine the front vehicle, and the vehicle-mounted OBU unit can directly extract the intention information of the front vehicle; when the intention identification module is arranged in the decision planning module, the vehicle-mounted OBU unit receives BSM information without intention information, firstly judges the position relation among vehicles to determine a front vehicle, and then the intention identification module in the decision planning module identifies the driving intention of the front vehicle according to the BSM information.
Furthermore, the sensing module senses the surrounding environment information of the vehicle by adopting sensing equipment such as a camera, a millimeter wave radar, an ultrasonic radar, a laser radar, a high-definition map, inertial navigation and a global satellite navigation system.
Furthermore, the decision planning module can realize the trajectory prediction, the global decision planning and the local path planning of the vehicle.
Further, the execution control module can realize longitudinal control and transverse control of the vehicle.
The invention also provides a V2V-based preceding vehicle intention identification method, which comprises the following steps:
s1: data fusion is carried out through a self-vehicle GNSS, an RTK positioning service, an IMU, a vehicle CAN signal and a camera, and a high-precision map service is combined to obtain accurate position information in a lane where a self-vehicle is located and meet the positioning requirement of the lane level;
s2: acquiring surrounding vehicle information through V2V;
s3: judging whether the vehicle is a front vehicle;
s4: and acquiring the driving intention of the front vehicle.
Further, the step S11 is further provided after the step S1: and recognizing the driving intention of the vehicle. The method specifically comprises the following steps: and acquiring the lateral acceleration, the course angle and the steering wheel angle of the vehicle according to the CAN signal of the vehicle, and identifying the driving intention of the vehicle by using a driving intention identification method by using an intention identification module of the vehicle.
Further, in S3, the determination of whether the vehicle is a preceding vehicle is performed by determining whether the vehicle is in the same lane according to the information of the own vehicle, such as the high-definition map, the GNSS, the RTK positioning service, the camera information, and the IMU, in combination with the BSM information of the other vehicle, and if the vehicle is not in the same lane, the determination is not made, and if the vehicle is in the same lane, the determination is made whether the distance in front is the closest, and if the distance is not the closest, the determination is made that the vehicle is a preceding vehicle.
Further, in S3, the intelligent networked automobile obtains accurate position information of the vehicle, including an absolute position and a relative position, through a high-precision map, a GNSS, an RTK positioning service, an IMU, and a conventional vehicle-mounted sensing sensor. The vehicle compares the data obtained by the traditional vehicle-mounted sensing sensor and the high-precision two-dimensional grid in the memory thereof, so as to determine the specific position of the vehicle on the road surface, such as the position of the vehicle on the lane and the position of the vehicle away from the center line of the lane. The GNSS, the RTK positioning service and the IMU can acquire coordinate data of vehicle position information, and the actual relative distance of the two vehicles can be calculated through longitude and latitude information between the two vehicles. V2X can acquire the environmental blind area information and the over-the-horizon information, and the accuracy of the vehicle position information is high.
Furthermore, there are two ways to obtain the driving intention of the preceding vehicle in S4, one of which is to obtain the information of the preceding vehicle through V2V, and the information of the preceding vehicle includes the driving intention of the preceding vehicle; the other mode is that BSM information of the front vehicle is obtained through V2V, and the BSM information of the front vehicle is analyzed through an intention recognition module in the decision planning of the self vehicle to determine the driving intention of the front vehicle.
Further, the BSM information of the front vehicle comprises a transverse acceleration, a course angle and a steering wheel corner, the BSM information is analyzed through an intention identification module in the decision planning of the self vehicle, and the driving intention of the front vehicle is identified by using a driving intention identification method.
Further, the method for recognizing the driving intention comprises the following steps: judging whether to change lanes or not through the transverse acceleration, the course angle and the steering wheel rotation angle, if the lane change exists, further judging whether to change the lanes leftwards or rightwards, if the lane change exists, the lane change is left lane change intention, and if the lane change is right, the lane change is right lane change intention; if the lane changing does not exist, the lane changing is a straight line intention, and the lane changing is further judged to be one of constant speed straight line running, acceleration straight line running, deceleration straight line running or emergency braking according to the vehicle speed and the longitudinal acceleration.
Further, in the driving intention identification process, the driving intention of the front vehicle is predicted through a Gaussian mixture hidden Markov algorithm based on the own vehicle Can signal or other vehicle BSM information. The method specifically comprises the following steps: the method comprises the steps of taking left lane changing, right lane changing, accelerating straight running, decelerating straight running, uniform speed straight running and emergency braking of a vehicle as hidden states, taking transverse acceleration, course angle, steering wheel rotation angle, vehicle speed, longitudinal acceleration and respective standard deviation thereof as observable sequences, obtaining probability distribution of different driving intentions through model parameters such as initial state probability, state transition probability, Gaussian weight, mean value, covariance and the like obtained through training, and determining the current driving intention when the probability of a certain intention is continuously 3 sampling interval time is more than 0.5 threshold values, wherein the lane changing intention of the vehicle is identified 1-3 seconds before a lane changing point of the vehicle.
Compared with the prior art, the invention has the beneficial effects that:
firstly, the driving intention of the front vehicle is sensed in a V2V mode, the shortage of information acquired by a vehicle-mounted sensor of the vehicle is overcome, and the information beyond the visual range of V2V can ensure that the driving intention of the vehicle can be acquired earlier, so that the vehicle is helped to make more accurate, effective and anthropomorphic decision and motion planning.
And secondly, the information of the front vehicle is obtained in a V2V mode, so that the accuracy of the intention identification of the front vehicle is ensured, and the safety of automobile driving is improved.
Drawings
Fig. 1 is a block diagram of the system configuration of embodiment 1.
FIG. 2 is a schematic flow chart of example 1.
Fig. 3 is a block diagram of the system configuration of embodiment 2.
FIG. 4 is a schematic flow chart of example 2.
FIG. 5 is a schematic diagram of a preceding vehicle determination process according to the present invention.
FIG. 6 is a schematic view of the driving intent recognition process of the present invention;
FIG. 7 is a GMM-HMM intent recognition flow of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to fig. 1 to 7 and embodiments 1 to 2. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The BSM information of the preceding vehicle transmitted via the V2V in example 1 includes the driving intention of the preceding vehicle, and the BSM information of the preceding vehicle transmitted via the V2V in example 2 does not include the driving intention of the preceding vehicle.
Example 1:
a preceding vehicle intention recognition system based on V2V comprises a sensing module, a decision planning module and an execution control module, wherein the sensing module, the decision planning module and the execution control module are sequentially connected.
The system is characterized in that a vehicle-mounted OBU unit is arranged in the perception module, an intention identification module for identifying vehicle driving intention is further arranged in the system, the intention identification module is arranged in the vehicle-mounted OBU unit, and the intention identification module CAN identify the driving intention of the vehicle through a CAN signal of the vehicle.
The vehicle-mounted OBU unit receives BSM information with intention information in a V2V mode, determines the front vehicle through the inter-vehicle position relation, and then directly extracts the intention information of the front vehicle.
The sensing module senses the surrounding environment information of the vehicle by adopting sensing equipment such as a camera, a millimeter wave radar, an ultrasonic radar, a laser radar, a high-definition map, inertial navigation and a global satellite navigation system.
The decision planning module can realize the trajectory prediction, the global decision planning and the local path planning of the vehicle. The execution control module can realize longitudinal control and transverse control of the vehicle.
The front vehicle intention identification process in this embodiment is as follows:
s01: data fusion is carried out through a self-vehicle GNSS, an RTK positioning service, an IMU, a vehicle CAN signal and a camera, and a high-precision map service is combined to obtain accurate position information in a lane where a self-vehicle is located and meet the positioning requirement of the lane level;
s02: acquiring the lateral acceleration, the course angle and the steering wheel angle of the vehicle according to the CAN signal of the vehicle, and identifying the driving intention of the vehicle by an intention identification module in an OBU of the vehicle by using a driving intention identification method;
s03: the surrounding vehicle information (including the driving intention) is acquired by means of the V2V, and whether the vehicle is a preceding vehicle is judged by the reliable positioning effect of the surrounding vehicle, so as to determine the preceding vehicle intention.
As shown in fig. 1 and 2, the driving intention recognition module in the own vehicle OBU recognizes the own vehicle intention and transmits the own vehicle intention to the other vehicle through V2V communication. The position information is determined through a high-precision map, a GNSS, an RTK positioning service, camera information and an IMU of the vehicle. And based on the CAN signal of the vehicle, the driving intention of the vehicle is identified through an OBU (on-board unit) intention identification module. The vehicle position information of the host vehicle and the driving intention are transmitted to the neighboring vehicles as BSM information by the V2V communication method. And the vehicle receiving the information judges the relative positions of the two vehicles according to the self-vehicle position information and the acquired other-vehicle position information, determines the front vehicle and further acquires the driving intention of the front vehicle.
Example 2:
a preceding vehicle intention recognition system based on V2V comprises a sensing module, a decision planning module and an execution control module, wherein the sensing module, the decision planning module and the execution control module are sequentially connected.
The system is characterized in that a vehicle-mounted OBU unit is arranged in the perception module, an intention identification module for identifying the driving intention of the vehicle is further arranged in the system, and the intention identification module is arranged in the decision planning module.
The vehicle-mounted OBU unit receives BSM information without intention information in a V2V mode, firstly judges the position relation among vehicles to determine a front vehicle, and then an intention identification module in the decision planning module identifies the driving intention of the front vehicle according to the BSM information.
The sensing module senses the surrounding environment information of the vehicle by adopting sensing equipment such as a camera, a millimeter wave radar, an ultrasonic radar, a laser radar, a high-definition map, inertial navigation and a global satellite navigation system.
The decision planning module can realize the trajectory prediction, the global decision planning and the local path planning of the vehicle. The execution control module can realize longitudinal control and transverse control of the vehicle.
The front vehicle intention identification process in this embodiment is as follows:
s11: data fusion is carried out through a self-vehicle GNSS, an RTK positioning service, an IMU, a vehicle CAN signal and a camera, and a high-precision map service is combined to obtain accurate position information in a lane where a self-vehicle is located and meet the positioning requirement of the lane level;
s12: acquiring position information and BSM information of surrounding vehicles in a V2V mode, and judging whether the surrounding vehicles are front vehicles or not through the reliable positioning effect of the surrounding vehicles;
s13: judging whether the front vehicle has a lane changing intention or not through an intention identification module in the decision planning of the self vehicle according to the transverse acceleration, the course angle and the steering wheel rotation angle in the BSM information of the front vehicle, and judging a left lane changing intention and a right lane changing intention according to the parameter characteristics if the lane changing intention exists; if no lane change intention exists, judging whether the front vehicle is in constant-speed straight running, accelerating straight running, decelerating straight running or emergency braking according to the vehicle speed and the longitudinal acceleration.
As shown in fig. 3 and 4, the BSM information transmitted through V2V communication is processed by the driving intention recognition module in the own vehicle decision planning, so as to complete the recognition of the intention of the vehicle. And determining the vehicle position information through a high-precision map, a GNSS, an RTK positioning service, camera information and an IMU of the vehicle. The vehicle position information and the BSM information are transmitted to the other vehicle through the V2V communication. The vehicle receiving the information judges the relative positions of the two vehicles through the own vehicle position information and the acquired other vehicle position information, determines the vehicle in the front vehicle, and identifies the intention of the front vehicle through a driving intention identification module in own vehicle decision planning based on the BSM information of the front vehicle.
In embodiments 1 and 2, the determination of the vehicle ahead is performed by using the high-definition map, GNSS, RTK positioning service, camera information, IMU, and other information of the vehicle itself, and combining the BSM information of the other vehicle to determine whether the vehicle is in the same lane, if not, the vehicle is not processed, if the vehicle is in the same lane, the determination is performed again to determine whether the distance in front is the closest, if the distance is not the closest, the vehicle is not processed, and if the distance is the closest, the vehicle ahead is determined. The method specifically comprises the following steps: the intelligent networked automobile obtains accurate position information of the automobile through a high-precision map, a GNSS, an RTK positioning service, an IMU and a traditional vehicle-mounted perception sensor, and the accurate position information comprises an absolute position and a relative position. The vehicle compares the data obtained by the traditional vehicle-mounted sensing sensor and the high-precision two-dimensional grid in the memory thereof, so as to determine the specific position of the vehicle on the road surface, such as the position of the vehicle on the lane and the position of the vehicle away from the center line of the lane. The GNSS, the RTK positioning service and the IMU can acquire coordinate data of vehicle position information, and the actual relative distance of the two vehicles can be calculated through longitude and latitude information between the two vehicles. V2X can acquire the environmental blind area information and the over-the-horizon information, and the accuracy of the vehicle position information is high. As shown in fig. 5, data fusion is performed through the vehicle-mounted GNSS, the RTK positioning service, the IMU, and the camera, and a high-precision map service is combined to obtain accurate position information in a lane where the vehicle is located, so as to accurately determine whether the vehicle is the vehicle closest to the front of the same lane.
In each of embodiment 1 and embodiment 2, the driving intention of the vehicle is predicted by a gaussian-mixture hidden markov algorithm (GMM-HMM) based on the own vehicle Can signal or the BSM information of the other vehicle. The method comprises the following steps of taking left lane changing of a vehicle, right lane changing of the vehicle, acceleration straight running of the vehicle, deceleration straight running of the vehicle, uniform speed straight running of the vehicle and emergency braking as hidden states, and taking transverse acceleration, a course angle, a steering wheel corner, a vehicle speed, longitudinal acceleration and respective standard deviations thereof as observable sequences. Model parameters such as initial state probability, state transition probability, Gaussian weight, mean value, covariance and the like obtained through training are used for obtaining probability distribution of different driving intentions, when the probability of a certain intention is continuously 3 sampling interval time is larger than a threshold value of 0.5, the probability distribution can be determined as the current driving intention, wherein the lane changing intention of the vehicle is identified 1-3 seconds before a lane changing point of the vehicle, as shown in fig. 6 and 7, the transverse motion of the vehicle can be effectively identified through vehicle transverse motion characteristic indexes such as transverse acceleration, course angle and steering wheel corner, and the longitudinal motion characteristic indexes of the vehicle such as vehicle speed and longitudinal acceleration can be effectively identified through the vehicle longitudinal motion characteristic indexes.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (9)

1. A preceding vehicle intention recognition system based on V2V is characterized by comprising a sensing module, a decision planning module and an execution control module which are sequentially connected.
2. A preceding vehicle intention identification method based on V2V is characterized by comprising the following steps:
s1: data fusion is carried out through a self-vehicle GNSS, an RTK positioning service, an IMU, a vehicle CAN signal and a camera, and a high-precision map service is combined to obtain accurate position information in a lane where a self-vehicle is located and meet the positioning requirement of the lane level;
s2: acquiring surrounding vehicle information through V2V;
s3: judging whether the surrounding vehicles are the front vehicles, if so, entering S4, and if not, not processing;
s4: and acquiring the driving intention of the front vehicle.
3. A preceding vehicle intention identifying method based on V2V as claimed in claim 2, wherein step S11 is further provided after S1: recognizing the driving intention of the vehicle; the method specifically comprises the following steps: and acquiring the lateral acceleration, the course angle and the steering wheel angle of the vehicle according to the CAN signal of the vehicle, and identifying the driving intention of the vehicle by an intention identification module in the OBU of the vehicle by using a driving intention identification method.
4. The V2V-based preceding vehicle intention recognition method according to claim 2, wherein the determination of the vehicle ahead in S3 is made by determining whether the vehicle is in the same lane from information such as a high-definition map of the vehicle, GNSS, RTK positioning service, camera information, IMU, etc., in combination with BSM information of other vehicles, and if not, no processing is performed, and if the vehicle is in the same lane, it is determined whether the distance in front is the closest, and if the distance is not the closest, no processing is performed, and if the distance is the closest, the vehicle ahead is determined.
5. The V2V-based preceding vehicle intention recognition method according to claim 4, wherein in S3, the intelligent networked vehicle obtains accurate position information of the vehicle, including absolute position and relative position, through high-precision maps, GNSS, RTK positioning service, IMU and conventional on-board sensing sensors; the vehicle compares the data obtained by the traditional vehicle-mounted sensing sensor and the high-precision two-dimensional grid in the memory thereof, so as to determine the specific position of the vehicle on the road surface.
6. A preceding vehicle intention recognition method based on V2V as claimed in claim 3, wherein there are two ways to obtain the driving intention of the preceding vehicle in S4, one of them is to obtain the preceding vehicle information through V2V, and the driving intention of the preceding vehicle is included in the preceding vehicle information; the other mode is that BSM information of the front vehicle is obtained through V2V, and the BSM information of the front vehicle is analyzed through an intention recognition module in the decision planning of the self vehicle to determine the driving intention of the front vehicle.
7. The V2V-based preceding vehicle intention recognition method as claimed in claim 6, wherein the BSM information of the preceding vehicle includes lateral acceleration, course angle, steering wheel angle, and the driving intention of the preceding vehicle is recognized by the driving intention recognition method through analyzing the BSM information by an intention recognition module in the decision plan of the own vehicle.
8. A preceding vehicle intention recognition method based on V2V as claimed in claim 7, wherein the driving intention recognition method is as follows: judging whether to change lanes or not through the transverse acceleration, the course angle and the steering wheel rotation angle, if the lane change exists, further judging whether to change the lanes leftwards or rightwards, if the lane change exists, the lane change is left lane change intention, and if the lane change is right, the lane change is right lane change intention; if the lane changing does not exist, the lane changing is a straight line intention, and the lane changing is further judged to be one of constant speed straight line running, acceleration straight line running, deceleration straight line running or emergency braking according to the vehicle speed and the longitudinal acceleration.
9. The V2V-based preceding vehicle intention recognition method according to claim 8, wherein in the driving intention recognition process, the driving intention of the preceding vehicle is predicted by a Gaussian mixture hidden Markov algorithm based on the own vehicle Can signal or the BSM information of other vehicles; the method specifically comprises the following steps: the method comprises the steps of taking left lane changing, right lane changing, accelerating straight going, decelerating straight going, uniform speed straight going and emergency braking of a vehicle as hidden states, taking transverse acceleration, a course angle, a steering wheel corner, a vehicle speed, longitudinal acceleration and respective standard deviations thereof as observable sequences, obtaining probability distribution of different driving intentions through model parameters including initial state probability, state transition probability, Gaussian weight, mean value and covariance obtained through training, and determining the current driving intention when the probability of a certain intention is continuously 3 sampling interval time is more than 0.5 threshold values, wherein the lane changing intention of the vehicle is identified 1-3 seconds before a lane changing point of the vehicle.
CN202110888159.1A 2021-08-03 2021-08-03 Preceding vehicle intention recognition system and recognition method based on V2V Pending CN113581206A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110888159.1A CN113581206A (en) 2021-08-03 2021-08-03 Preceding vehicle intention recognition system and recognition method based on V2V

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110888159.1A CN113581206A (en) 2021-08-03 2021-08-03 Preceding vehicle intention recognition system and recognition method based on V2V

Publications (1)

Publication Number Publication Date
CN113581206A true CN113581206A (en) 2021-11-02

Family

ID=78254622

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110888159.1A Pending CN113581206A (en) 2021-08-03 2021-08-03 Preceding vehicle intention recognition system and recognition method based on V2V

Country Status (1)

Country Link
CN (1) CN113581206A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114347984A (en) * 2021-12-23 2022-04-15 北京国家新能源汽车技术创新中心有限公司 Control decision method for switching into scene in front vehicle based on vehicle-road perception fusion technology
CN115320631A (en) * 2022-07-05 2022-11-11 西安航空学院 Method for identifying driving intention of front vehicle in adjacent lane of intelligent driving vehicle

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102431556A (en) * 2011-11-15 2012-05-02 武汉理工大学 Integrated driver early warning device based on vehicle-road cooperation
DE102016205141A1 (en) * 2015-11-04 2017-05-04 Volkswagen Aktiengesellschaft A method and vehicle communication system for determining a driving intention for a vehicle
CN107172215A (en) * 2017-07-18 2017-09-15 吉林大学 Future travel work information acquisition methods under car networking environment
US20190186940A1 (en) * 2017-12-18 2019-06-20 Hyundai Motor Company System and method for creating driving route of vehicle
CN110164183A (en) * 2019-05-17 2019-08-23 武汉理工大学 A kind of safety assistant driving method for early warning considering his vehicle driving intention under the conditions of truck traffic
CN111422197A (en) * 2020-05-18 2020-07-17 吉林大学 Intelligent driving vehicle active lane changing system considering intelligent vehicle group flow
CN112347567A (en) * 2020-11-27 2021-02-09 青岛莱吉传动系统科技有限公司 Vehicle intention and track prediction method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102431556A (en) * 2011-11-15 2012-05-02 武汉理工大学 Integrated driver early warning device based on vehicle-road cooperation
DE102016205141A1 (en) * 2015-11-04 2017-05-04 Volkswagen Aktiengesellschaft A method and vehicle communication system for determining a driving intention for a vehicle
CN107172215A (en) * 2017-07-18 2017-09-15 吉林大学 Future travel work information acquisition methods under car networking environment
US20190186940A1 (en) * 2017-12-18 2019-06-20 Hyundai Motor Company System and method for creating driving route of vehicle
CN110164183A (en) * 2019-05-17 2019-08-23 武汉理工大学 A kind of safety assistant driving method for early warning considering his vehicle driving intention under the conditions of truck traffic
CN111422197A (en) * 2020-05-18 2020-07-17 吉林大学 Intelligent driving vehicle active lane changing system considering intelligent vehicle group flow
CN112347567A (en) * 2020-11-27 2021-02-09 青岛莱吉传动系统科技有限公司 Vehicle intention and track prediction method

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114347984A (en) * 2021-12-23 2022-04-15 北京国家新能源汽车技术创新中心有限公司 Control decision method for switching into scene in front vehicle based on vehicle-road perception fusion technology
CN115320631A (en) * 2022-07-05 2022-11-11 西安航空学院 Method for identifying driving intention of front vehicle in adjacent lane of intelligent driving vehicle
CN115320631B (en) * 2022-07-05 2024-04-09 西安航空学院 Method for identifying driving intention of front vehicle of intelligent driving automobile adjacent lane

Similar Documents

Publication Publication Date Title
CN108688660B (en) Operating range determining device
CN109606361B (en) Vehicle control device
CN112208533B (en) Vehicle control system, vehicle control method, and storage medium
CN110371018B (en) Improving vehicle behavior using information from other vehicle lights
CN111508276B (en) High-precision map-based V2X reverse overtaking early warning method, system and medium
US11358599B2 (en) Traveling control apparatus, traveling control method, and non-transitory computer-readable storage medium storing program
US11285957B2 (en) Traveling control apparatus, traveling control method, and non-transitory computer-readable storage medium storing program
US11685406B2 (en) Vehicle control device, vehicle control method, and storage medium
CN111731294B (en) Travel control device, travel control method, and storage medium storing program
CN112469970A (en) Method for estimating a localization quality in terms of a self-localization of a vehicle, device for carrying out the method steps of the method, and computer program
US11042160B2 (en) Autonomous driving trajectory determination device
CN113581206A (en) Preceding vehicle intention recognition system and recognition method based on V2V
CN113848914B (en) Method for planning local path by collision coefficient artificial potential field method in dynamic environment
US10839678B2 (en) Vehicle identifying device
JP7286691B2 (en) Determination device, vehicle control device, determination method, and program
US20200219399A1 (en) Lane level positioning based on neural networks
KR20190069962A (en) Autonomous vehicle and method for changing traveling line
US20220281482A1 (en) Vehicle control device, vehicle control method, and computer-readable storage medium storing program
WO2022070250A1 (en) Information processing device, information processing method, and program
CN111127923B (en) Equipment and method for analyzing indication mark
US11990038B2 (en) Control device, moving body, control method, and storage medium
US20230339461A1 (en) System for driver assistance and method for driver assistance
JP7491267B2 (en) Information processing server, processing method for information processing server, and program
CN112172826B (en) Vehicle control device, vehicle control method, and storage medium
US20230022458A1 (en) Information processing device, information processing method, and program

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20211102

RJ01 Rejection of invention patent application after publication