WO2021237745A1 - 一种辨识车辆列队中异常车辆参数的方法和终端设备 - Google Patents

一种辨识车辆列队中异常车辆参数的方法和终端设备 Download PDF

Info

Publication number
WO2021237745A1
WO2021237745A1 PCT/CN2020/093532 CN2020093532W WO2021237745A1 WO 2021237745 A1 WO2021237745 A1 WO 2021237745A1 CN 2020093532 W CN2020093532 W CN 2020093532W WO 2021237745 A1 WO2021237745 A1 WO 2021237745A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
time
abnormal area
target vehicle
vehicles
Prior art date
Application number
PCT/CN2020/093532
Other languages
English (en)
French (fr)
Inventor
周维
陈效华
刘亚林
余瑶
杨辉明
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 EP20937270.5A priority Critical patent/EP4145340A4/en
Priority to CN202080004923.8A priority patent/CN112673406B/zh
Priority to PCT/CN2020/093532 priority patent/WO2021237745A1/zh
Publication of WO2021237745A1 publication Critical patent/WO2021237745A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/22—Platooning, i.e. convoy of communicating vehicles
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/40—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass for recovering from a failure of a protocol instance or entity, e.g. service redundancy protocols, protocol state redundancy or protocol service redirection
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
    • H04W4/46—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for vehicle-to-vehicle communication [V2V]
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/095—Traffic lights
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • This application relates to the field of Internet of Vehicles, and more specifically, to a method and terminal device for identifying abnormal vehicle parameters in a vehicle queue.
  • Intelligent and Connected Vehicles have the function of Vehicle to Everything (V2X). Multiple adjacent ICVs form an intelligent networked vehicle fleet. Through the coordinated control of the intelligent networked vehicle fleet, not only It can reduce vehicle energy consumption and emissions, and can also alleviate traffic congestion, improve driving safety and traffic efficiency. However, we are currently in the era of incompletely intelligent networked transportation. Not all vehicles on the road are intelligent networked cars, but also include non-smart networked cars. In a non-fully intelligent networked traffic environment, non-smart connected cars may appear in the intelligent networked vehicle queue at any time, the intelligent networked vehicle queue will be disrupted at any time, and unknown vehicles appear in the intelligent networked vehicle fleet. Therefore, the intelligent networked vehicle fleet cannot perform coordinated control.
  • This application provides a method and terminal device for identifying abnormal vehicle parameters in a vehicle queue.
  • the method can identify the number of vehicles in the abnormal area of the intelligent networked fleet and the position and speed information of each vehicle, so that the intelligent networked fleet is abnormal The area is restored in an orderly manner, and coordinated control of the intelligent networked vehicle fleet is realized. Not only can energy consumption and emissions be reduced, but also traffic congestion can be relieved, and traffic safety and traffic efficiency can be improved.
  • a method for identifying abnormal vehicle parameters in a vehicle queue includes: judging the current driving scene of the target vehicle according to the driving trajectory data of the target vehicle and the current real-time map of the target vehicle, and
  • the driving scene of the target vehicle is an urban road driving scene or a highway driving scene, and the target vehicle is an intelligent networked car of an intelligent networked fleet; according to the current driving scene of the target vehicle, select the current driving scene of the target vehicle Vehicle trajectory generation algorithm; determining the at least one abnormal area included in front of the target vehicle at time Tb, the at least one abnormal area being an abnormal area in the intelligent networked fleet where the target vehicle is located, and the time Tb Is the current time; based on the selected vehicle trajectory generation algorithm and machine learning algorithm, identify the number of vehicles in each abnormal area in at least one abnormal area at time Ta, and the number of each vehicle included in each abnormal area Position information and speed information, the Ta time is the calibration time in the historical driving process of the target vehicle; based on the selected vehicle trajectory generation algorithm
  • the number of vehicles in the abnormal area at time Tb and each vehicle in the abnormal area at time Tb are identified by identifying the number of vehicles in the abnormal area at time Ta, the position information and speed information of each vehicle in the abnormal area under different driving scenarios.
  • the location information of the vehicle and the speed information of each vehicle in the abnormal area can identify the number of vehicles in the abnormal area of the intelligent networked fleet and the location and speed information of each vehicle, so that the abnormal area of the intelligent networked fleet can be restored to order .
  • the selected vehicle trajectory generation algorithm and machine learning algorithm are used to identify the number of vehicles in each abnormal area in the at least one abnormal area at time Ta .
  • the position information and speed information of each vehicle included in each abnormal area includes: calculating the average of the theoretical driving trajectory and actual driving trajectory of the target vehicle when the number of vehicles in each abnormal area is K Root Mean Square Error (RMSE), where K ⁇ 1,...,N ⁇ , N is the maximum value N of the number of vehicles included in each abnormal area, and K traverses each value from 1 to N
  • RMSE Root Mean Square Error
  • the determining the at least one abnormal area included in the front of the target vehicle at time Tb includes: acquiring multiple intelligent networked vehicles in front of the target vehicle The actual driving trajectory from time Tc to time Tb, where the time Tc is the calibration time in the historical driving process of the target vehicle; calculate the theoretical driving trajectory of multiple intelligent networked vehicles in front of the target vehicle from time Tc to time Tb Calculate the difference between the theoretical driving trajectory and the actual driving trajectory of each of the plurality of smart connected cars; according to the difference between the theoretical driving trajectory and the actual driving trajectory of each smart connected car and the first A threshold value for determining the at least one section of abnormal area included in front of the target vehicle at time Tb.
  • each segment of the at least one segment of abnormal area is abnormal
  • the distance of the area is from the first intelligent networked vehicle adjacent to the head of each abnormal area to the tail of each abnormal area.
  • the distance of each abnormal area in the at least one abnormal area is It is the area from the adjacent rear vehicle of the first intelligent networked vehicle adjacent to the head of each abnormal area to the adjacent front vehicle at the rear of each abnormal area.
  • the length of the abnormal area of the fleet can be shortened, which is beneficial to improve the accuracy of identification.
  • the root mean square error RMSE of the theoretical driving trajectory and the actual driving trajectory of the target vehicle includes: When the number of vehicles in the abnormal area at time Ta is K, randomly generate the position information and speed information of each vehicle in the abnormal area at time Ta; calculate the neighbors of the target vehicle according to the vehicle trajectory generation algorithm The theoretical trajectory of the preceding vehicle from Ta to Tb; according to the actual trajectory and theoretical trajectory of the adjacent preceding vehicle from Ta to Tb of the target vehicle, the theoretical driving trajectory of the adjacent preceding vehicle of the target vehicle is calculated And the RMSE of the actual driving trajectory.
  • the calculating the maximum number of vehicles N in the abnormal area at the time Ta includes: determining the length of the abnormal area at the time Ta; The length of the abnormal area, the average length of the vehicle and the minimum distance between two adjacent vehicles determine the maximum number of vehicles N in the abnormal area.
  • the method further includes: determining a vehicle trajectory generation algorithm in different driving scenarios, the vehicle trajectory generation algorithm including an urban road vehicle trajectory generation algorithm and a highway vehicle Trajectory generation algorithm.
  • a terminal device including: a judgment unit configured to judge the current driving scene of the target vehicle based on the driving trajectory data of the target vehicle and the current real-time map of the target vehicle, the The driving scene of the target vehicle is an urban road driving scene or a highway driving scene, the target vehicle is an intelligent networked car of an intelligent networked fleet; a processing unit, the processing unit is used to according to the current driving scene of the target vehicle, The vehicle trajectory generation algorithm in the current driving scene of the target vehicle is selected; the processing unit is further configured to determine the at least one segment of abnormal area included in front of the target vehicle at time Tb, and the at least one segment of abnormal area is the target In the abnormal area in the intelligent networked fleet where the vehicle is located, the Tb time is the current time; the processing unit is also used to identify at least one abnormal area at the time Ta based on the selected vehicle trajectory generation algorithm and machine learning algorithm The number of vehicles in each abnormal area in each section of the abnormal area, the position information and speed information of each vehicle included in each
  • the processing unit is specifically configured to calculate the theoretical driving trajectory and actual driving of the target vehicle when the number of vehicles in each abnormal area is K
  • the root mean square error RMSE of the trajectory where K ⁇ 1,...,N ⁇ , N is the maximum value N of the number of vehicles included in each abnormal area, and K traverses each value from 1 to N; when the When the RMSE meets the first condition, obtain the position information and speed information of each vehicle in the abnormal area; at time Ta, determine the number of vehicles and each vehicle corresponding to the RMSE that meet the second condition from the determined N RMSEs Location information and speed information.
  • the processing unit is specifically configured to: obtain the actual driving trajectories of multiple intelligent networked vehicles in front of the target vehicle from time Tc to time Tb, and the Tc Time is the calibration time in the historical driving process of the target vehicle; calculate the theoretical driving trajectory of multiple intelligent networked vehicles in front of the target vehicle from time Tc to time Tb; calculate each of the multiple intelligent networked vehicles The difference between the theoretical driving trajectory and the actual driving trajectory of the intelligent networked vehicle; according to the difference between the theoretical driving trajectory and the actual driving trajectory of each intelligent networked vehicle and the first threshold, it is determined that the front of the target vehicle at the time Tb includes The at least one section of abnormal area.
  • each segment of the at least one abnormal area is abnormal
  • the distance of the area is the area from the first intelligent networked vehicle adjacent to the head of each abnormal area to the front vehicle adjacent to the tail of each abnormal area.
  • the at least one section of the abnormal area is the area from the adjacent rear vehicle of the first intelligent networked car adjacent to the head of each abnormal area to the adjacent front vehicle at the rear of each abnormal area.
  • the processing unit is specifically configured to: when the number of vehicles in the abnormal area at time Ta is K, randomly generate that each vehicle in the abnormal area is Position information and speed information at time Ta; calculate the theoretical trajectory of the adjacent front vehicle of the target vehicle from time Ta to time Tb according to the vehicle trajectory generation algorithm; according to the adjacent front vehicle of the target vehicle from Ta From the actual trajectory and theoretical trajectory to Tb, the RMSE of the theoretical driving trajectory and the actual driving trajectory of the adjacent preceding vehicle of the target vehicle is calculated.
  • the processing unit is further configured to: determine the length of the abnormal area at the time Ta; The minimum distance between two vehicles determines the maximum number of vehicles N in the abnormal area.
  • the processing unit is further configured to: determine vehicle trajectory generation algorithms in different driving scenarios.
  • the vehicle trajectory generation algorithm includes an urban road vehicle trajectory generation algorithm and a high-speed vehicle trajectory generation algorithm. Algorithm for road vehicle trajectory generation.
  • a terminal device including a processor, the processor is connected to a memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the device executes the foregoing first A method in one aspect or any possible implementation of the first aspect.
  • a computer-readable storage medium stores a computer program. When the computer program is run, it implements the first aspect or any of the possible implementations of the first aspect. method.
  • a chip which is characterized by comprising a processor and an interface; the processor is configured to read instructions to execute the foregoing first aspect or any possible implementation method of the first aspect.
  • the chip may further include a memory in which instructions are stored, and the processor is configured to execute instructions stored in the memory or instructions derived from other sources.
  • Figure 1a shows a schematic diagram of an intelligent networked fleet driving on a city road
  • Figure 1b shows a schematic diagram of the intelligent networked fleet driving on the expressway
  • Figure 2 shows a schematic diagram of the communication line-of-sight of an intelligent networked car
  • Figure 3a shows a scene where the intelligent networked fleet is disrupted
  • Figure 3b shows another scenario where the intelligent networked fleet is disrupted
  • Figure 3c shows another scenario where the intelligent networked fleet is disrupted
  • Fig. 4 shows a schematic scene diagram of the identification of abnormal vehicle parameters in a vehicle lineup
  • FIG. 5 is a schematic flowchart of a method for identifying vehicle parameters in a vehicle queue based on networked information according to an embodiment of the present application
  • Figure 6 shows a schematic diagram of the intelligent networked fleet driving on urban roads
  • Figure 7 shows a schematic diagram of a vehicle trajectory generation algorithm on urban highways
  • Figure 8 shows a schematic diagram of the intelligent networked fleet driving on the expressway
  • Figure 9 shows a schematic diagram of a vehicle trajectory generation algorithm on a highway
  • FIG. 10 shows a schematic diagram of the identification of abnormal vehicle parameters in a vehicle lineup
  • Figure 11 shows a schematic diagram of the number of vehicles in the abnormal area at time Tb and their position and speed information based on the identification result at time Ta on the expressway;
  • Figure 12 shows a schematic diagram of the number of vehicles in the abnormal area at time Tb and their position and speed information based on the identification result at time Ta on urban roads;
  • Figure 13a shows a schematic diagram of the configuration of an ICV vehicle in a highway driving scenario
  • Figure 13b shows a schematic diagram of the configuration of an ICV vehicle in a highway driving scenario
  • Figure 14a shows a schematic diagram of the configuration of an ICV vehicle in an urban road driving scene
  • Figure 14b shows a schematic diagram of the configuration of an ICV vehicle in an urban road driving scene
  • FIG. 15 shows a schematic block diagram of a terminal device 200 according to an embodiment of the present application.
  • the terminal device in this application may be a vehicle-mounted terminal device. If the terminal device is located on the vehicle (for example, placed in the vehicle or installed in the vehicle), it can be considered as a vehicle-mounted terminal device.
  • the vehicle-mounted terminal device such as the center console is also called On-board unit (OBU).
  • OBU On-board unit
  • the terminal device includes a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system layer.
  • the hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory (also referred to as main memory).
  • the operating system can be any one or more computer operating systems that implement business processing through processes, such as Linux operating systems, Unix operating systems, Android operating systems, iOS operating systems or windows operating systems, and are built on the Internet Distributed system and so on.
  • This application does not specifically limit the specific structure of the execution subject of the method provided in this application, as long as it can perform data processing according to the method provided in this application by running a program that records the code of the method provided in this application, for example,
  • the execution subject of the method provided in this application may be a terminal device or a functional module in the terminal device that can call and execute the program, or an operating system.
  • Intelligent and Connected Vehicles have the function of Vehicle to Everything (V2X). Multiple adjacent ICVs form an intelligent networked vehicle fleet. Each intelligent networked vehicle in the intelligent networked vehicle fleet Vehicles have identity tags. Through the collaborative control of the intelligent networked vehicle fleet, not only can the energy consumption and emissions of the vehicles be reduced, but also traffic congestion can be relieved, and driving safety and traffic efficiency can be improved. As shown in Fig. 1a and Fig. 1b, Fig. 1a and Fig. 1b show schematic diagrams of the intelligent networked fleet driving in different driving scenarios.
  • Figure 1a is a schematic diagram of the intelligent networked fleet driving on urban roads
  • Figure 1b is a schematic diagram of the intelligent networked fleet driving on highways
  • the vehicles in Figures 1a and 1b are all intelligent networked vehicles with V2X functions.
  • the intelligent networked car has the V2X function, and each intelligent networked car has its communication line of sight.
  • the communication line of sight is the distance that the intelligent networked car can communicate.
  • Figure 2 shows a schematic diagram of the communication line of sight of an intelligent networked car.
  • the intelligent networked vehicle fleet includes seven intelligent networked cars.
  • the communication line of sight of P7 can reach P1, P1 -P6 and P7 can communicate directly.
  • the line-of-sight of P7 can reach P2, and P2-P6 and P7 can communicate directly, but P1 and P7 cannot communicate directly, which is between P7 and P1.
  • the communication data can be forwarded through P2 vehicles.
  • the communication line-of-sight of the target vehicle can cover the entire intelligent networked fleet by default. It should be understood that the communication line-of-sight of the target vehicle may not cover the entire intelligent networked fleet, and the driving trajectory of the vehicle in the intelligent networked fleet that cannot be covered by the communication line-of-sight of the target vehicle can be forwarded to the target vehicle by other vehicles.
  • the intelligent networked vehicle can be covered by the communication line-of-sight of the target vehicle in the intelligent networked fleet.
  • P1 to P9 are smart connected cars. Due to other vehicles forcibly changing lanes or P4V2X equipment failure, non-smart connected cars appear between P3 and P5.
  • P5 Since P5 does not know the position and speed information of each vehicle of V1, V2, ..., VN-1, P5 is changed from cooperative adaptive cruise control (Cooperative Adaptive Cruise Control, CACC) control to adaptive cruise control (Adaptive Cruise Control). Cruise Control, ACC) control.
  • CACC cooperative adaptive cruise control
  • Adaptive Cruise Control Adaptive Cruise Control
  • Cruise Control ACC
  • how to jump from ACC control to CACC control requires identification of the number of vehicles in the abnormal area of the fleet and the position and speed information of each vehicle. After identifying the number of vehicles in the abnormal area of the fleet and the location and speed information of each vehicle, the abnormal area of the fleet can be virtualized as an intelligent networked area, and the intelligent networked fleet returns to normal.
  • this application proposes a method for identifying abnormal vehicle parameters in a vehicle queue.
  • This method can identify the number of vehicles in the abnormal area of the intelligent networked fleet and the position and speed information of each vehicle, so that the intelligent networked The abnormal area of the convoy returned to order.
  • FIG. 5 is a schematic flowchart of a method 100 for identifying abnormal vehicle parameters in a vehicle queue according to an embodiment of the present application. 100 can be applied in the scenario shown in FIG. 3.
  • the target vehicle is taken as the execution subject of the execution method as an example to illustrate the method, and the target vehicle is an ICV.
  • the execution subject of the execution method may also be a device on the target vehicle, such as the OBU of the on-board terminal equipment.
  • the execution subject of the method can also be a server, that is, the server is used to control the intelligent networked fleet, and the information collected by each intelligent networked vehicle in the intelligent networked fleet will be sent to the server.
  • the server recognizes the abnormal vehicle parameters in the vehicle queue, and sends the recognition result to each of the intelligent networked vehicles in the intelligent networked fleet.
  • the method 100 shown in FIG. 5 may include S101 to S110. Each step in the method 100 will be described in detail below with reference to FIG. 5.
  • S102 The target vehicle collects current driving data.
  • the target vehicle collects the driving trajectory data of its own vehicle and the driving trajectory data of the preceding vehicle through on-board equipment (positioning equipment, V2X equipment).
  • S103 The target vehicle judges the current driving scene.
  • the target vehicle judges the current driving scene of the target vehicle according to the driving trajectory data of the target vehicle and the current real-time map of the target vehicle, whether it is an urban road driving scene or a highway driving scene; if it is an urban road driving scene, enter Urban road processing module, otherwise enter the highway processing module.
  • S104 In an urban road driving scene, the target vehicle judges whether there is an abnormal area in front of the target vehicle.
  • the target vehicle recognizes the number of vehicles in the abnormal area at time Ta, the position information of each vehicle in the abnormal area, and each vehicle in the abnormal area according to the vehicle trajectory generation algorithm in the urban road driving scene.
  • the Ta time is the calibration time during the driving of the target vehicle.
  • S106 According to the identified number of vehicles in the abnormal area at time Ta, the position information of each vehicle in the abnormal area, the speed information of each vehicle in the abnormal area, and the vehicle trajectory in the urban road driving scene, the target vehicle is identified An algorithm is generated to identify the number of vehicles in the abnormal area at time Tb, the position information of each vehicle in the abnormal area, and the speed information of each vehicle in the abnormal area, where the Tb time is the current time.
  • S107 In the highway driving scene, the target vehicle judges whether there is an abnormal area in front of the target vehicle.
  • the target vehicle recognizes the number of vehicles in the abnormal area at time Ta, the position information of each vehicle in the abnormal area, and each vehicle in the abnormal area according to the vehicle trajectory generation algorithm in the highway driving scene.
  • the Ta time is the calibration time during the driving of the target vehicle.
  • the target vehicle is based on the identified number of vehicles in the abnormal area at time Ta, the position information of each vehicle in the abnormal area, the speed information of each vehicle in the abnormal area, and the vehicle trajectory in the highway driving scene.
  • An algorithm is generated to identify the number of vehicles in the abnormal area at time Tb, the position information of each vehicle in the abnormal area, and the speed information of each vehicle in the abnormal area, where the Tb time is the current time.
  • the identification of the number and location of vehicles in the abnormal area and the speed information is mainly to first identify the number of vehicles in the abnormal area at time Ta, the position information of each vehicle in the abnormal area, and the information of each vehicle in the abnormal area.
  • Speed information is mainly to first identify the number of vehicles in the abnormal area at time Ta, the position information of each vehicle in the abnormal area, the speed information of each vehicle in the abnormal area, and the vehicle trajectory generation algorithm, the time Tb is identified The number of vehicles in the abnormal area, the position information of each vehicle in the abnormal area, and the speed information of each vehicle in the abnormal area.
  • This method can identify the number of vehicles in the abnormal area of the intelligent networked vehicle fleet and the location and speed information of each vehicle, so that the abnormal area of the intelligent networked vehicle fleet can be restored in order, and the collaborative control of the intelligent networked vehicle fleet can be realized. Reducing vehicle energy consumption and emissions can also alleviate traffic congestion, improve driving safety and traffic efficiency.
  • the time Ta is the calibration time during the driving of the target vehicle
  • the time Tb is the current time. Assuming the current time: 08:42:50 on April 18, 2020. Regardless of the CPU processing time, the Tb time is 08:42:50 on April 18, 2020, and the Ta time is the moment before the Tb time. Ta time is 08:42:45 on April 18, 2020, or 08:42:40 on April 18, 2020, or 08:42:35 on April 18, 2020. Time Ta is the elapsed time at time Tb.
  • Ta time is the calibration time during the driving of the target vehicle, which means that Ta is determined according to the calibration time, that is, a calibration time can be set in advance according to the driving scene or other factors, and then Ta is determined according to the calibration time.
  • the calibration time is 1s, that is, the current time is Tb, and the first second before Tb is Ta; in an urban road driving scene, the calibration time is 3s, that is, the current time is Tb, and the first three seconds of Tb is Ta.
  • the target vehicle determines the current driving scene, and the target vehicle needs to determine the current driving scene of the target vehicle based on the driving trajectory data of the target vehicle and the current real-time map of the target vehicle.
  • the driving track data of the target vehicle includes GPS information, that is, the position information, speed information, and time information of the target vehicle.
  • the position information of the vehicle in the GPS is the longitude and latitude of the vehicle position.
  • the target vehicle needs to be based on the GPS information.
  • the target vehicle is positioned on the current real-time map of the target vehicle to determine the current driving scene of the target vehicle. According to the current driving scene of the target vehicle, a vehicle trajectory generation algorithm in the driving scene of the target vehicle is selected.
  • the target vehicle may also be based on the driving trajectory data of the target vehicle, the driving trajectory data of the preceding vehicle, and the current real-time map of the target vehicle. Determine the current driving scene of the target vehicle.
  • step S104 and step 107 the method 100 both includes: determining the at least one abnormal area included in front of the target vehicle at time Tb.
  • the determining the at least one abnormal area included in front of the target vehicle at time Tb includes: acquiring actual driving trajectories of multiple intelligent networked vehicles in front of the target vehicle from time Tc to time Tb, so The Tc time is the calibration time in the historical driving process of the target vehicle; calculate the theoretical driving trajectory of the multiple intelligent networked vehicles in front of the target vehicle from the time Tc to the time Tb; calculate the The difference between the theoretical driving trajectory and the actual driving trajectory of each intelligent networked vehicle; according to the difference between the theoretical driving trajectory and the actual driving trajectory of each intelligent networked vehicle and the first threshold, determine the front of the target vehicle at Tb The at least one section of abnormal area included.
  • the time Tc in the above method will be described below first, where the Tc time is the calibration time during the driving of the target vehicle, and the Tb time is the current time. Assuming the current time: 08:41:50 on April 18, 2020. Regardless of the CPU processing time, the Tb time is 08:41:50 on April 18, 2020, and the Tc time is the moment before the Tb time. Ta time is 08:41:45 on April 18, 2020, or 08:41:40 on April 18, 2020, or 08:41:35 on April 18, 2020. Time Tc is the time elapsed at time Tb.
  • Tc time is the calibration time during the driving process of the target vehicle, which means that Tc is determined according to the calibration time, that is, a calibration time can be set in advance according to the driving scene or other factors, and then Tc is determined according to the calibration time.
  • the calibration time is 1s, that is, the current time is Tb, and the second before Tb is Tc; in an urban road driving scene, the calibration time is 3s, that is, the current time is Tb, and the first three seconds of Tb is Tc.
  • the Tc time may be the same as or different from the Ta time.
  • the calibration time of the at least one abnormal area included in the front of the target vehicle at time Tb is 3s, that is, the current time is Tb, and the three seconds before Tb is Tc; the abnormal vehicle in the vehicle queue is identified
  • the calibration time of the parameter is 2s, that is, the current moment is Tb, and the first two seconds of Tb is Ta.
  • P7 is the target vehicle.
  • P7 receives the actual trajectory of the vehicle sent by P2 to P6 and the theoretical trajectory of the vehicle from P2 to P6.
  • the theoretical trajectory of the vehicle from P2 to P6 is obtained by calculation.
  • P2 is based on the following model and the actual P1 between Tc and Tb.
  • Trajectory curve calculate the theoretical trajectory curve of P2; P3 calculates the theoretical trajectory curve of P3 based on the following model and the actual trajectory curve of P2 between Tc and Tb; P4 is calculated based on the following model and the actual trajectory curve of P3 between Tc and Tb P4 theoretical trajectory curve, P5 calculates the theoretical trajectory curve of P5 based on the following model and the actual trajectory curve of P4 between Tc and Tb, P6 calculates the theoretical trajectory of P6 based on the following model and the actual trajectory curve of P5 between Tc and Tb curve.
  • P7 determines the at least one abnormal area included in front of the P7 vehicle by comparing the actual driving trajectories of the P2 to P6 vehicles and the theoretical driving trajectories of the P2 to P6 vehicles, respectively.
  • LPX Cal represents the theoretical position of vehicle X at time Tb
  • LPX Real represents the actual position of vehicle X
  • LPX Cal represents the theoretical position of vehicle X at time Tb
  • LPX Real represents the actual position of vehicle X
  • LPX Cal represents the theoretical position of vehicle X at time Tb
  • LPX Real represents the actual position of vehicle X
  • the trajectory of a vehicle generally includes position information and speed information.
  • the above description uses the position information of the vehicle to determine whether there is an abnormal area in front of the target vehicle, and it can also determine whether there is an abnormal area in front of the target vehicle according to the speed information of the vehicle. That is, the judgment is made by comparing the theoretical and actual vehicle speeds of multiple vehicles.
  • the determining the at least one abnormal area included in front of the target vehicle at time Tb includes: acquiring actual driving trajectories of multiple intelligent networked vehicles in front of the target vehicle from time Tc to time Tb, according to The acquired actual driving trajectories of a plurality of intelligent networked vehicles in front of the target vehicle from time Tc to time Tb are determined, and the at least one abnormal area included in front of the target vehicle at time Tb is determined.
  • P7 is the target vehicle.
  • P5 changed from a smart connected car to a non-smart connected car.
  • P7 could not receive the actual trajectory of the vehicle and the theoretical trajectory of the vehicle sent by P5. Therefore, P7 judges that P5 is abnormal, that is, P4 and P6. An abnormal area appears in between.
  • the at least one section of abnormal area included in front of the target vehicle at the time Tb is determined includes:
  • P7 is the target vehicle.
  • P5 changed from a smart connected car to a non-smart connected car due to a vehicle communication failure.
  • P7 could not receive the actual trajectory of the vehicle and the theoretical driving trajectory of the vehicle sent by P5, and P7 could receive other smart connected vehicles other than P5.
  • LPX Cal represents the theoretical position of vehicle X at time Tb
  • LPX Real represents the actual position of vehicle X
  • the first threshold value is a value set in advance, and may be an empirical value or the like.
  • the intelligent networked fleet includes seven vehicles from P1 to P7, and P7 is the target vehicle.
  • P5 changed from a smart connected car to a non-smart connected car due to a vehicle communication failure.
  • P7 could not receive the actual trajectory of the vehicle and the theoretical driving trajectory of the vehicle sent by P5, and P7 could receive other smart connected vehicles other than P5. Car information. Therefore, it can be directly judged that there is an abnormality between P4 and P6 based on the loss of P5 information.
  • the target vehicle P7 can obtain the ID information, speed, and speed of each vehicle from P1 to P6. Location information, etc.
  • P5 fails and changes from a non-intelligent connected car to an ordinary vehicle.
  • the target vehicle P7 can obtain the ID information and speed of each car from P1 to P4 and P6. , Location information, etc. The ID information, speed, and location information of P5 are missing.
  • the target vehicle can directly determine that there is an abnormal area between P4 and P6.
  • the vehicle trajectory generation algorithm in the urban road driving scene is divided into two scenarios: no car in front of the target vehicle and a car in front of the target vehicle. The following are respectively introduced:
  • OVM Optimal Velocity Model
  • v represents the current vehicle speed of the target vehicle
  • V represents the traffic speed from ITS
  • ⁇ g represents the adaptive time
  • the adaptive time is a scalar quantity, which is estimated by collecting the time of a certain vehicle passing under a traffic light.
  • the driving law of the vehicle under the yellow light adopts the parking decision model.
  • the parking decision model is shown in formula (2).
  • the driver of the target vehicle needs to make a decision, whether to pass the intersection without stopping. Stop at the intersection and wait for the next green light.
  • ⁇ y represents the duration of the current yellow light
  • d veh,d represents the distance of the current vehicle from the traffic light ahead.
  • IDM Intelligent Driver Model
  • a f,max represents the maximum acceleration of the target vehicle
  • v des represents the expected speed of the target vehicle
  • v f represents the speed of the target vehicle
  • v l represents the speed of the preceding vehicle
  • s f represents the mileage displacement of the target vehicle
  • s l Represents the mileage displacement of the preceding vehicle
  • l veh represents the length of the vehicle body (the statistical length of the vehicle body length, such as the length of the trolley, the length of the large vehicle, etc.)
  • g f represents the distance between the front target vehicle
  • ⁇ represents the acceleration adjustment coefficient
  • g 0 represents the front The minimum distance between the target vehicle
  • ⁇ represents the distance between the leading vehicle when it is safe
  • dec f,max represents the maximum deceleration of the target vehicle.
  • the IDM car following model used in the embodiments of this application is only used as an example, and does not impose any limitation on this application.
  • the car following model can also be selected from other car following models, for example, General Motor (GM), Linear car following model, physiological-psychological car following model and safety distance model, etc.
  • GM General Motor
  • Linear car following model physiological-psychological car following model and safety distance model, etc.
  • the driving behavior of the target vehicle is not only affected by the vehicle in front, but also by the traffic lights.
  • traffic lights have a greater impact on vehicles that are closer to the intersection of traffic lights. Therefore, there are two situations in which there is a car in front of the target vehicle for discussion:
  • IDM Intelligent Driver Model
  • a f,max represents the maximum acceleration of the target vehicle
  • v des represents the expected speed of the target vehicle
  • v f represents the speed of the target vehicle
  • v l represents the speed of the preceding vehicle
  • s f represents the mileage displacement of the target vehicle
  • s l Represents the mileage displacement of the preceding vehicle
  • l veh represents the length of the vehicle body (the statistical length of the vehicle body length, such as the length of the trolley, the length of the large vehicle, etc.)
  • g f represents the distance between the front target vehicle
  • ⁇ represents the acceleration adjustment coefficient
  • g 0 represents the front , The minimum distance between the target vehicle
  • ⁇ represents the distance between the leading vehicle when it is safe
  • dec f,max represents the maximum deceleration of the target vehicle.
  • Figure 6 shows a schematic diagram of an intelligent networked fleet driving on a city road.
  • P1, P2, P3, P4, and P5 are intelligent networked fleets, and each vehicle has V2X function; V1, V2 are ordinary vehicles and do not have V2X function.
  • Figure 7 shows a schematic diagram of the algorithm for generating vehicle trajectories on urban highways.
  • IDM Intelligent Driver Model
  • a f,max represents the maximum acceleration of the following vehicle
  • v des represents the expected speed of the following vehicle
  • v f represents the speed of the following vehicle
  • v l represents the speed of the preceding vehicle
  • s f represents the mileage displacement of the following vehicle
  • s l Represents the mileage displacement of the preceding vehicle
  • l veh represents the length of the vehicle
  • g f represents the distance between the front and rear vehicles
  • ⁇ represents the acceleration adjustment coefficient
  • g 0 represents the minimum distance between the front and rear vehicles
  • ⁇ represents the distance between the leading vehicle when it is safe
  • dec f, max represents The maximum deceleration of the following vehicle.
  • Figure 8 shows a schematic diagram of the intelligent networked fleet driving during the time period from Ta to Tb.
  • Figure 9 shows a schematic diagram of a vehicle trajectory generation algorithm on a highway.
  • the vehicle trajectory generation algorithm the highway driving scene is the IDM following model
  • the driving trajectory of the target vehicle in the time period from Ta to Tb, the number of vehicles in the abnormal area at time Ta, the position information of each vehicle in the abnormal area, and the speed information of each vehicle in the abnormal area are based on
  • the vehicle trajectory generation algorithm can obtain the theoretical driving trajectory of each vehicle in the abnormal area from Ta to Tb.
  • the target vehicle, at time Ta the number of vehicles in the abnormal area and their position and speed information are unknown. Therefore, it is necessary to identify the number of vehicles in the abnormal area at time Ta and their position and speed information.
  • the parameter identification algorithm of abnormal area mainly includes the following three steps:
  • L veh is the average length of the vehicle
  • L Gap represents the minimum distance between the front and rear vehicles
  • T a represents the time length of the abnormal region, it can be calculated by a formula (7).
  • Machine learning algorithms can be used to calculate the root mean square error RMSE of the theoretical driving trajectory of the target vehicle and the actual driving trajectory to find the number of vehicles in the abnormal area when K (K ⁇ 1,...,N ⁇ ) RMSE:
  • T a number of time provided in the abnormal region of the vehicle K, (where, K is a random number) to generate the random region for each vehicle position abnormal T a time information, speed information; then, based on the vehicle trajectory generation algorithm and The position and speed information of the i-th vehicle (i ⁇ 1,...,K ⁇ ) at time T a , (wherein, the position and speed information of the i-th vehicle are determined according to the position and speed information of the i-1th vehicle) , Based on the One-By-One approach, the vehicle trajectory of each vehicle from T a to T b can be generated in sequence; then, based on the theoretical trajectory information of the K-th vehicle and the vehicle trajectory generation algorithm, the vehicle P5( That is, the theoretical trajectory of the target vehicle from T a to T b is After that, according to the actual trajectory of the vehicle P5 from T a to T b And theoretical trajectory Calculate its root mean square according to formula (8)
  • the abnormal region vehicle number is K
  • the number of iterations can be set to M
  • n the data length
  • the position and speed information of each vehicle at the time T a when the minimum value is obtained is only a method for determining the position information and speed information of each vehicle in the abnormal area when the number of vehicles in the abnormal area is K. It is also possible to determine the position information and speed information of each vehicle in the abnormal area when the number of vehicles in the abnormal area is K and when the RMSE meets the first condition.
  • the first condition may be the above To obtain the minimum value, the first condition may be the above Random selection meets a certain range Determine the position information and speed information of each vehicle in the abnormal area. If the range is the first five values of RMSE, the RMSE is arranged in increasing order.
  • calculating the time Ta so that the number of vehicles with the smallest RMSE in the abnormal area is only a method to determine the number of vehicles. It can also be determined that the number of vehicles in the abnormal area is K and when the RMSE meets the second condition. Quantity, the second condition can be the above To obtain the minimum value, the first condition may be the above Random selection meets a certain range If the range is the first five values of RMSE, RMSE is arranged in increasing order.
  • the number of vehicles in the abnormal area at time Ta ahead of P5 the position information of each vehicle in the abnormal area, and the speed information of each vehicle in the abnormal area can be identified.
  • the vehicle trajectory generation algorithm is used again to obtain the position and speed information of each vehicle in the abnormal area of the fleet at time Tb.
  • FIG. 11 shows a schematic diagram of the number of vehicles in the abnormal area at time Tb and their position and speed information based on the identification result at time Ta on the expressway.
  • Fig. 12 shows a schematic diagram of the number of vehicles in the abnormal area at time Tb and their position and speed information based on the identification result at time Ta on urban roads.
  • ICV vehicles need to be equipped with: GPS positioning equipment: used to obtain vehicle location information and speed information; V2X equipment: obtain location information and speed information of other connected vehicles in the intelligent networked fleet, and send them to other vehicles.
  • the connected car sends its own position information and speed information; radar and/or camera: it senses the position information and speed information of the vehicle ahead. It should be understood that the radar and/or camera can be arranged in the front and/or rear of the car.
  • Figures 13a and 13b show schematic diagrams of the configuration of ICV vehicles in highway driving scenarios.
  • ICV vehicles need to be equipped with: GPS positioning equipment: to obtain vehicle position and speed information; V2X equipment: to obtain the position and speed information of other connected vehicles in the fleet, and to send them their own position, speed and speed information. Receive front traffic light phase information; Radar or camera: Perceive the position and speed information of the vehicle in front, the radar and/or camera can be configured in the front of the body and/or the rear of the body; TelematicsBox (T-Box) T-Box : Receive current road traffic speed information sent by the traffic information center.
  • the traffic lights on the road will affect the trajectory of the vehicle. Therefore, the traffic lights in the urban road driving scene need to have the equipment networking (Infrastructure to Everything, I2X) function.
  • Figure 14a and Figure 14b show urban road driving. In the scenario, the schematic diagram of the ICV vehicle configuration.
  • each intelligent networked vehicle of the intelligent networked fleet is equipped with a radar or a camera
  • the distance of each abnormal area in the at least one abnormal area is the first phase of each abnormal area.
  • the neighboring first intelligent networked car arrives at the end of each abnormal area.
  • the distance of each abnormal area in the at least one abnormal area is the first adjacent to the head of each abnormal area.
  • FIG. 15 shows a schematic block diagram of a terminal device 200 according to an embodiment of the present application.
  • the terminal device 200 may be an access network device, or a chip or circuit, for example, a chip or circuit that can be provided in an access network device.
  • the terminal device 200 may be a vehicle-mounted terminal device, or a chip or circuit, such as a chip or circuit that can be provided in a core network device.
  • the terminal device 200 may be a server, a chip or a circuit, for example, a chip or circuit that can be installed in a server.
  • the server may be independent of the vehicle and communicate with the target vehicle through the server's transceiver to perform data Transmission, for example, the target vehicle sends the collected data to the server, the server performs calculation processing, and sends the result to the target vehicle.
  • the terminal device 200 may include a processing unit 210 (that is, an example of a processor) and a transceiver unit 230.
  • the processing unit 210 may also be referred to as a determining unit.
  • the transceiver unit 230 may include a receiving unit and a sending unit.
  • the transceiver unit 230 may be implemented by a transceiver or a transceiver-related circuit or interface circuit.
  • the device may further include a storage unit 220.
  • the storage unit 220 is used to store instructions.
  • the storage unit may also be used to store data or information.
  • the storage unit 220 may be realized by a memory.
  • the processing unit 210 is configured to execute instructions stored in the storage unit 220, so that the terminal device 200 implements the steps performed by the terminal device in the foregoing method.
  • the processing unit 210 may be used to call the data of the storage unit 220, so that the terminal device 200 implements the steps performed by the terminal device in the foregoing method.
  • the processing unit 210 is configured to execute the instructions stored in the storage unit 220, so that the terminal device 200 implements the steps performed by the access network device in the foregoing method.
  • the processing unit 210 may be used to call the data of the storage unit 220, so that the terminal device 200 implements the steps performed by the access network device in the foregoing method.
  • the processing unit 210, the storage unit 220, and the transceiver unit 230 can communicate with each other through internal connection paths, and transfer control and/or data signals.
  • the storage unit 220 is used to store a computer program, and the processing unit 210 can be used to call and run the calculation program from the storage unit 220 to control the transceiver unit 230 to receive signals and/or send signals to complete the above method. Steps for terminal equipment or access network equipment.
  • the storage unit 220 may be integrated in the processing unit 210, or may be provided separately from the processing unit 210.
  • the transceiver unit 230 includes a receiver and a transmitter.
  • the receiver and the transmitter may be the same or different physical entities. When they are the same physical entity, they can be collectively referred to as transceivers.
  • the transceiver unit 230 includes an input interface and an output interface.
  • the function of the transceiving unit 230 may be implemented by a transceiving circuit or a dedicated chip for transceiving.
  • the processing unit 210 may be realized by a dedicated processing chip, a processing circuit, a processing unit, or a general-purpose chip.
  • a general-purpose computer may be considered to implement the communication device (such as a terminal device or an access network device) provided in the embodiment of the present application. That is to say, the program code for realizing the functions of the processing unit 210 and the transceiving unit 230 is stored in the storage unit 220, and the general processing unit implements the functions of the processing unit 210 and the transceiving unit 230 by executing the code in the storage unit 220.
  • the terminal device may be applied to a target vehicle, and the target vehicle is an intelligent networked car in an intelligent networked fleet.
  • the terminal device may further include a judging unit 240.
  • the judging unit 240 is used for judging the current driving scene of the target vehicle according to the driving trajectory data of the target vehicle and the current real-time map of the target vehicle.
  • the driving scene of the target vehicle is an urban road driving scene or a highway driving scene.
  • the vehicle is an intelligent networked car of an intelligent networked fleet; the processing unit 210 is configured to select the vehicle trajectory generation algorithm in the current driving scene of the target vehicle according to the current driving scene of the target vehicle; the processing unit 210 also Used to determine the at least one section of abnormal area included in front of the target vehicle at time Tb, where the at least one section of abnormal area is an abnormal area in the intelligent networked fleet where the target vehicle is located, and the time Tb is the current time; The processing unit 210 is further configured to identify the number of vehicles in each abnormal area in at least one abnormal area and the number of vehicles included in each abnormal area at the time Ta based on the selected vehicle trajectory generation algorithm and machine learning algorithm The position information and speed information of each vehicle, the Ta time is the calibration time in the historical driving process of the target vehicle; the processing unit 210 is also used to generate the algorithm based on the selected vehicle trajectory, and according to the time in the Ta At time, the number of vehicles in each section of abnormal area, the position information and speed information of each vehicle included in each section of abnormal area,
  • the processing unit 210 is specifically configured to calculate the root mean square error (Root Mean Square Error) between the theoretical driving trajectory and the actual driving trajectory of the target vehicle when the number of vehicles in each abnormal area is K.
  • RMSE Root Mean Square Error
  • K ⁇ 1,...,N ⁇ , N is the maximum value N of the number of vehicles included in each abnormal area, and K traverses each value from 1 to N; when the RMSE meets the first condition
  • the location information and speed information of each vehicle in the abnormal area are acquired; at time Ta, the number of vehicles corresponding to the RMSE that meets the second condition, the location information of each vehicle, and the number of vehicles corresponding to the RMSE that meet the second condition are determined from the determined N RMSEs.
  • Speed information the root mean square error
  • the processing unit 210 is specifically configured to obtain actual driving trajectories of multiple intelligent networked vehicles in front of the target vehicle from time Tc to time Tb, where the time Tc is a calibration during the historical driving process of the target vehicle Time; Calculate the theoretical driving trajectory of multiple intelligent connected cars in front of the target vehicle from time Tc to Tb; calculate the theoretical driving trajectory and actual driving trajectory of each of the multiple intelligent connected cars According to the difference between the theoretical driving trajectory and the actual driving trajectory of each intelligent networked vehicle and the first threshold, determine the at least one abnormal area included in front of the target vehicle at Tb.
  • each intelligent networked vehicle of the intelligent networked fleet is equipped with a radar or a camera
  • the distance of each abnormal area in the at least one abnormal area is the first phase of each abnormal area.
  • the neighboring first intelligent networked car arrives at the end of each abnormal area.
  • the distance of each abnormal area in the at least one abnormal area is the first adjacent to the head of each abnormal area.
  • the length of the abnormal area of the fleet can be shortened, which is beneficial to improve the accuracy of identification.
  • the processing unit 210 is specifically configured to randomly generate position information and speed information of each vehicle in the abnormal area at time Ta when the number of vehicles in the abnormal area at time Ta is K; according to the vehicle trajectory Generate algorithm to calculate the theoretical trajectory of the adjacent front vehicle of the target vehicle from time Ta to time Tb; calculate the actual trajectory and theoretical trajectory of the adjacent front vehicle from Ta to Tb of the target vehicle The RMSE of the theoretical driving trajectory and the actual driving trajectory of the neighboring vehicle in front of the target vehicle.
  • the processing unit 210 is specifically configured to determine the length of the abnormal area at the time Ta; determine the abnormality according to the length of the abnormal area, the average length of the vehicle, and the minimum distance between two adjacent vehicles The largest number of vehicles in the area N.
  • the processing unit 210 is further configured to determine vehicle trajectory generation algorithms in different driving scenarios, where the vehicle trajectory generation algorithm includes an urban road vehicle trajectory generation algorithm and an expressway vehicle trajectory generation algorithm.
  • the processor may be a central processing unit (central processing unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (digital signal processors, DSP), and dedicated integration Circuit (application specific integrated circuit, ASIC), ready-made programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the memory in the embodiments of the present application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory can be read-only memory (ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), and electrically available Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • the volatile memory may be random access memory (RAM), which is used as an external cache.
  • RAM random access memory
  • static random access memory static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • Access memory synchronous DRAM, SDRAM
  • double data rate synchronous dynamic random access memory double data rate SDRAM, DDR SDRAM
  • enhanced synchronous dynamic random access memory enhanced SDRAM, ESDRAM
  • synchronous connection dynamic random access memory Take memory (synchlink DRAM, SLDRAM) and direct memory bus random access memory (direct rambus RAM, DR RAM).
  • the foregoing embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination.
  • the above-mentioned embodiments may be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions or computer programs.
  • the computer instructions or computer programs are loaded or executed on the computer, the processes or functions described in the embodiments of the present application are generated in whole or in part.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • the computer instructions may be transmitted from a website, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more sets of available media.
  • the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium.
  • the semiconductor medium may be a solid state drive.
  • the embodiments of the present application also provide a computer-readable medium on which a computer program is stored, and when the computer program is executed by a computer, the steps performed by the terminal device in any of the foregoing embodiments are implemented.
  • the embodiments of the present application also provide a computer program product, which, when executed by a computer, implements the steps executed by the terminal device in any of the foregoing embodiments.
  • An embodiment of the present application also provides a system chip, which includes a communication unit and a processing unit.
  • the processing unit may be a processor, and the processor may implement the functions of the processing unit and the judgment unit in the foregoing embodiments.
  • the communication unit may be, for example, a communication interface, an input/output interface, a pin or a circuit, or the like.
  • the processing unit can execute computer instructions, so that the chip in the communication device executes the steps performed by the terminal device provided in the embodiment of the present application.
  • the computer instructions are stored in a storage unit.
  • various aspects or features of the present application can be implemented as methods, devices, or products using standard programming and/or engineering techniques.
  • article of manufacture used in this application encompasses a computer program accessible from any computer-readable device, carrier, or medium.
  • computer-readable media may include, but are not limited to: magnetic storage devices (for example, hard disks, floppy disks or tapes, etc.), optical disks (for example, compact discs (CD), digital versatile discs (DVD) Etc.), smart cards and flash memory devices (for example, erasable programmable read-only memory (EPROM), cards, sticks or key drives, etc.).
  • various storage media described herein may represent one or more devices and/or other machine-readable media for storing information.
  • machine-readable medium may include, but is not limited to, wireless channels and various other media capable of storing, containing, and/or carrying instructions and/or data.
  • the disclosed system, device, and method can be implemented in other ways.
  • the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or It can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of this application essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

一种辨识车辆列队中异常车辆参数的方法和终端设备。该方法包括：根据目标车辆的行驶轨迹数据和目标车辆的当前实时地图判断当前目标车辆的驾驶场景；根据当前目标车辆的驾驶场景，选择目标车辆当前驾驶场景下的车辆轨迹生成算法；确定Tb时刻目标车辆的前方包括的至少一段异常区域，Tb时刻为当前时刻；基于车辆轨迹生成算法和机器学习算法，辨识在Ta时刻，至少一段异常区域中的车辆数量、每辆车的位置信息和速度信息，Ta时刻为目标车辆历史行驶过程中的标定时刻；基于选择的车辆轨迹生成算法，根据在Ta时刻，每段异常区域中的车辆数量、每辆车的位置信息和速度信息，辨识Tb时刻每段异常区域的车辆数量、每辆车的位置信息和速度信息。

Description

一种辨识车辆列队中异常车辆参数的方法和终端设备 技术领域
本申请涉及车联网领域，并且更具体的，涉及一种辨识车辆列队中异常车辆参数的方法和终端设备。
背景技术
智能网联汽车(Intelligent and Connected Vehicles，ICV)具备车联网(Vehicle to Everything，V2X)功能，多个依次相邻的ICV组成智能网联汽车车队，通过对该智能网联汽车车队协同控制，不仅可以降低辆能耗、减少排放，还可以缓解交通拥堵、提高行车安全与交通通行效率。但是当前正处在非完全智能网联交通的时代，道路上行驶的车辆不全是智能网联汽车，还包含非智能网联汽车。在非完全智能网联交通环境下，智能网联汽车车辆队列中可能随时会出现非智能网联汽车，智能网联汽车车辆队列随时会被打乱，智能网联汽车车队中出现了未知车辆，因此该智能网联汽车车队不能进行协同控制。
因此，当智能网联车队被打乱，如何辨识出车队异常区域中的车辆数量以及每辆车的位置、速度信息，进而进行智能网联汽车车队协同控制是一项亟待解决的问题。
发明内容
本申请提供一种辨识车辆列队中异常车辆参数的方法和终端设备，该方法可以识别智能网联车队异常区域中的车辆数量及其每一辆车的位置、速度信息，使得智能网联车队异常区域恢复有序，实现对该智能网联汽车车队协同控制，不仅可以降低辆能耗、减少排放，还可以缓解交通拥堵、提高行车安全与交通通行效率。
第一方面，提供了一种辨识车辆列队中异常车辆参数的方法，该方法包括：根据目标车辆的行驶轨迹数据和所述目标车辆的当前实时地图判断当前所述目标车辆的驾驶场景，所述目标车辆的驾驶场景为城市道路驾驶场景或高速公路驾驶场景，所述目标车辆为智能网联车队的智能网联汽车；根据当前所述目标车辆的驾驶场景，选择所述目标车辆当前驾驶场景下的车辆轨迹生成算法；确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域，所述至少一段异常区域为所述目标车辆所在的智能网联车队中的异常区域，所述Tb时刻为当前时刻；基于选择的所述车辆轨迹生成算法和机器学习算法，辨识在Ta时刻，至少一段异常区域中的每段异常区域中的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，所述Ta时刻为所述目标车辆历史行驶过程中的标定时刻；基于选择的所述车辆轨迹生成算法，根据在所述Ta时刻，所述每段异常区域中的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，辨识Tb时刻所述每段异常区域的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息。
因此，通过在判断的不同驾驶场景下辨识Ta时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和速度信息来辨识Tb时刻异常区域中的车辆数量、异常区域中的 每辆车的位置信息和异常区域中的每辆车的速度信息，可以识别智能网联车队异常区域中的车辆数量及其每一辆车的位置、速度信息，使得智能网联车队异常区域恢复有序。
结合第一方面，在第一方面的某些实现方式中，所述基于选择的所述车辆轨迹生成算法和机器学习算法，辨识Ta时刻所述至少一段异常区域中的每段异常区域的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，包括：计算所述每段异常区域中的车辆数量为K时，所述目标车辆的理论行驶轨迹和实际行驶轨迹的均方根误差(Root Mean Square Error，RMSE)，其中，K∈{1,…,N}，N为所述每段异常区域包括的车辆数量的最大值N，K遍历1到N的每个值；当所述RMSE符合第一条件时，获取所述异常区域中每辆车的位置信息信息和速度信息；在Ta时刻，从确定的N个RMSE中确定符合第二条件的RMSE对应的车辆数量、每辆车的位置信息信息和速度信息。
结合第一方面，在第一方面的某些实现方式中，所述确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域，包括：获取所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的实际行驶轨迹，所述Tc时刻为所述目标车辆历史行驶过程中的标定时刻；计算所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的理论行驶轨迹；计算所述多个智能网联汽车中的每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差；根据所述每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差与第一阈值，确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域。
结合第一方面，在第一方面的某些实现方式中，当所述智能网联车队的每个智能网联汽车的车头配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车到所述每段异常区域的尾部。
结合第一方面，在第一方面的某些实现方式中，当所述智能网联汽车的车头和车尾均配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车的相邻后车到所述每段异常区域的尾部相邻的前方车辆之间的区域。
此时，当所述智能网联汽车的车辆队列中的车辆的车头和车尾均配置有雷达或者摄像头时，可以缩短车队异常区域长度，有利于提高辨识的精度。
结合第一方面，在第一方面的某些实现方式中，计算所述每段异常区域中的车辆数量为K时，目标车辆的理论行驶轨迹和实际行驶轨迹的均方根误差RMSE，包括：在Ta时刻所述异常区域车辆数量为K时，随机生成所述异常区域中的每一辆车在Ta时刻的位置信息、速度信息；根据车辆轨迹生成算法，计算出所述目标车辆的相邻的前方车辆从Ta时刻到Tb时刻的理论轨迹；根据所述目标车辆的相邻的前方车辆从Ta到Tb的实际轨迹和理论轨迹，计算所述目标车辆的相邻的前方车辆的理论行驶轨迹和实际行驶轨迹的RMSE。
结合第一方面，在第一方面的某些实现方式中，所述计算Ta时刻，所述异常区域中最大的车辆数量N，包括：确定所述Ta时刻所述异常区域的长度；根据所述异常区域的长度、车辆平均长度和相邻两辆车的最小车间距，确定所述异常区域中最大的车辆数量N。
结合第一方面，在第一方面的某些实现方式中，所述方法还包括：确定不同驾驶场景下的车辆轨迹生成算法，所述车辆轨迹生成算法包括城市道路车辆轨迹生成算法和高速公路车辆轨迹生成算法。
第二方面，提供了一种终端设备，包括：判断单元，所述判断单元用于根据目标车辆 的行驶轨迹数据和所述目标车辆的当前实时地图判断当前所述目标车辆的驾驶场景，所述目标车辆的驾驶场景为城市道路驾驶场景或高速公路驾驶场景，所述目标车辆为智能网联车队的智能网联汽车；处理单元，所述处理单元用于根据当前所述目标车辆的驾驶场景，选择所述目标车辆当前驾驶场景下的车辆轨迹生成算法；所述处理单元还用于确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域，所述至少一段异常区域为所述目标车辆所在的智能网联车队中的异常区域，所述Tb时刻为当前时刻；所述处理单元还用于基于选择的所述车辆轨迹生成算法和机器学习算法，辨识在Ta时刻，至少一段异常区域中的每段异常区域中的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，所述Ta时刻为所述目标车辆历史行驶过程中的标定时刻；所述处理单元还用于基于选择的所述车辆轨迹生成算法，根据在所述Ta时刻，所述每段异常区域中的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，辨识Tb时刻所述每段异常区域的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息。
结合第二方面，在第二方面的某些实现方式中，所述处理单元具体用于：计算所述每段异常区域中的车辆数量为K时，所述目标车辆的理论行驶轨迹和实际行驶轨迹的均方根误差RMSE，其中，K∈{1,…,N}，N为所述每段异常区域包括的车辆数量的最大值N，K遍历1到N的每个值；当所述RMSE符合第一条件时，获取所述异常区域中每辆车的位置信息信息和速度信息；在Ta时刻，从确定的N个RMSE中确定符合第二条件的RMSE对应的车辆数量、每辆车的位置信息信息和速度信息。
结合第二方面，在第二方面的某些实现方式中，所述处理单元具体用于：获取所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的实际行驶轨迹，所述Tc时刻为所述目标车辆历史行驶过程中的标定时刻；计算所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的理论行驶轨迹；计算所述多个智能网联汽车中的每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差；根据所述每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差与第一阈值，确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域。
结合第二方面，在第二方面的某些实现方式中，当所述智能网联车队的每个智能网联汽车的车头配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车到所述每段异常区域的尾部相邻的前方车辆之间的区域。
结合第二方面，在第二方面的某些实现方式中，当所述智能网联车队的每个智能网联汽车的车头和车尾均配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车的相邻后车到所述每段异常区域的尾部相邻的前方车辆之间的区域。
结合第二方面，在第二方面的某些实现方式中，所述处理单元具体用于：在Ta时刻所述异常区域车辆数量为K时，随机生成所述异常区域中的每一辆车在Ta时刻的位置信息、速度信息；根据车辆轨迹生成算法，计算出所述目标车辆的相邻的前方车辆从Ta时刻到Tb时刻的理论轨迹；根据所述目标车辆的相邻的前方车辆从Ta到Tb的实际轨迹和理论轨迹，计算所述目标车辆的相邻的前方车辆的理论行驶轨迹和实际行驶轨迹的RMSE。
结合第二方面，在第二方面的某些实现方式中，所述处理单元还用于：确定所述Ta时刻所述异常区域的长度；根据所述异常区域的长度、车辆平均长度和相邻两辆车的最小 车间距，确定所述异常区域中最大的车辆数量N。
结合第二方面，在第二方面的某些实现方式中，所述处理单元还用于：确定不同驾驶场景下的车辆轨迹生成算法，所述车辆轨迹生成算法包括城市道路车辆轨迹生成算法和高速公路车辆轨迹生成算法。
第三方面，提供了一种终端设备，包括处理器，该处理器与存储器相连，该存储器用于存储计算机程序，该处理器用于执行该存储器中存储的计算机程序，以使得该装置执行上述第一方面或第一方面的任意可能的实现方式中的方法。
第四方面，提供了一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序，当该计算机程序被运行时，实现上述第一方面或第一方面的任意可能的实现方式中的方法。
第五方面，提供了一种芯片，其特征在于，包括处理器和接口；该处理器用于读取指令以执行上述第一方面或第一方面的任意可能的实现方式中的方法。
可选地，该芯片还可以包括存储器，该存储器中存储有指令，处理器用于执行存储器中存储的指令或源于其他的指令。
附图说明
图1a示出了城市道路上，智能网联车队行驶示意图；
图1b示出了高速公路上，智能网联车队行驶示意图；
图2示出了一种智能网联汽车的通信视距示意图；
图3a示出了智能网联车队被打乱的一种场景；
图3b示出了智能网联车队被打乱的另一种场景；
图3c示出了智能网联车队被打乱的另一种场景；
图4示出了车辆列队行驶中异常车辆参数辨识的示意性场景图；
图5是本申请一个实施例的基于网联信息的车辆队列行驶中车辆参数辨识的方法的示意性流程图；
图6示出了在城市道路上智能网联车队行驶示意图；
图7示出了在城市公路上车辆轨迹生成算法示意图；
图8示出高速公路上智能网联车队行驶示意图；
图9示出了高速公路上，车辆轨迹生成算法示意图；
图10示出了车辆列队行驶中异常车辆参数辨识的示意图；
图11示出了在高速公路上，基于Ta时刻辨识的结果，得到Tb时刻异常区域车辆数量及其位置、速度信息的示意图；
图12示出了在城市道路上，基于Ta时刻辨识的结果，得到Tb时刻异常区域车辆数量及其位置、速度信息的示意图；
图13a示出了高速公路驾驶场景下，ICV车辆的配置示意图；
图13b示出了高速公路驾驶场景下，ICV车辆的配置示意图；
图14a示出了城市道路驾驶场景下，ICV车辆的配置示意图；
图14b示出了城市道路驾驶场景下，ICV车辆的配置示意图；
图15示出了本申请实施例的终端设备200的示意性框图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合本申请中的附图，对本申请中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请中的终端设备可以是车载终端设备，该终端设备如果位于车辆上(例如放置在车辆内或安装在车辆内)，都可以认为是车载终端设备，车载终端设备例如中控台也称为车载单元(on-board unit，OBU)。
在本申请中，终端设备包括硬件层、运行在硬件层之上的操作系统层，以及运行在操作系统层上的应用层。该硬件层包括中央处理器(central processing unit，CPU)、内存管理单元(memory management unit，MMU)和内存(也称为主存)等硬件。该操作系统可以是任意一种或多种通过进程(process)实现业务处理的计算机操作系统，例如，Linux操作系统、Unix操作系统、Android操作系统、iOS操作系统或windows操作系统，以及建立在互联网之上的分布式系统(distributed system)等。本申请并未对本申请提供的方法的执行主体的具体结构特别限定，只要能够通过运行记录有本申请的提供的方法的代码的程序，以根据本申请提供的方法进行数据处理即可，例如，本申请提供的方法的执行主体可以是终端设备或者，是终端设备中能够调用程序并执行程序的功能模块，或者是操作系统等。
智能网联汽车(Intelligent and Connected Vehicles，ICV)具备车联网(Vehicle to Everything，V2X)功能，多个依次相邻的ICV组成智能网联汽车车队，智能网联汽车车队中的每辆智能网联汽车都有身份标识，通过对该智能网联汽车车队协同控制，不仅可以降低辆能耗、减少排放，还可以缓解交通拥堵、提高行车安全与交通通行效率。如图1a和图1b所示，图1a和图1b示出了不同行驶场景下，智能网联车队行驶示意图。图1a为城市道路上，智能网联车队行驶示意图，图1b为高速公路上，智能网联车队行驶示意图，图1a和图1b中的车辆均为智能网联汽车，具备V2X功能。
智能网联汽车具备V2X功能，每个智能网联汽车都具有其通信视距，通信视距即为智能网联汽车可以通信的距离。图2示出了一种智能网联汽车的通信视距示意图，在图2中，智能网联汽车车队包括七辆智能网联汽车，一种情况下，P7的通信视距可以达到P1，P1-P6和P7之间可以直接通信，另一种情况下，P7的通信视距可以达到P2，P2-P6和P7之间可以直接通信，但是P1与P7之间不能直接通信，P7与P1之间的通信数据可以通过P2车辆转发。
在本申请实施例中，为了便于描述，默认目标车辆的通信视距可以覆盖整个智能网联车队。应理解，目标车辆的通信视距也可以不覆盖整个智能网联车队，目标车辆的通信视距不能覆盖的智能网联车队中的车辆的行驶轨迹可以通过其他车辆转发给目标车辆，其他车辆为所述智能网联车队中的目标车辆的通信视距可以覆盖的智能网联汽车。
但是当前正处在非完全智能网联交通的时代，道路上行驶的车辆不全是智能网联汽车，还包含非智能网联汽车。在非完全智能网联交通环境下，智能网联汽车车辆队列中可能随时会出现非智能网联汽车，智能网联汽车车辆队列随时会被打乱。如图3a所示，在交叉 路口，其他车辆汇入，智能网联车队被打乱，图3b所示，正常行驶中，其他车辆强行汇入(如变道)，智能网联车队被打乱，图3c所示，队列中某车V2X设备故障，智能网联汽车可能会变为普通车辆，智能网联车队被打乱。
当智能网联车队被打乱，智能网联汽车车队中出现了未知车辆，因此该智能网联汽车车队不能进行协同控制。如何使被打乱的智能网联车队从“无序”恢复到“有序”(智能网联)，即如何辨识出车队异常区域中的车辆数量以及每辆车的位置、速度信息是一项亟待解决的问题。在图4中，P1至P9为智能网联汽车，由于其他车辆强行变道或P4V2X设备故障的影响，导致P3与P5之间出现非智能网联汽车。由于P5不知道V1、V2、···、VN-1每一辆车的位置、速度信息，P5由协同式自适应巡航控制(Cooperative Adaptive Cruise Control，CACC)控制变为自适应巡航控制(Adaptive Cruise Control，ACC)控制。在这种驾驶场景下，如何由ACC控制跳转到CACC控制，需要对车队异常区域中的车辆数量及其每一辆车的位置、速度信息进行辨识。在辨识出车队异常区域中的车辆数量及其每一辆车的位置、速度信息后，车队异常区域可以虚拟为智能网联区域，智能网联车队恢复正常。
有鉴于此，本申请提出了一种辨识车辆列队中异常车辆参数的方法，该方法可以识别智能网联车队异常区域中的车辆数量及其每一辆车的位置、速度信息，使得智能网联车队异常区域恢复有序。
下面结合图5详细说明本申请提供的一种辨识车辆列队中异常车辆参数的方法100，图5是本申请一个实施例的辨识车辆列队中异常车辆参数的方法100的示意性流程图，该方法100可以应用在图3所示的场景中。
应理解，在本申请中，以目标车辆作为执行方法的执行主体为例，对方法进行说明，该目标车辆是一辆ICV。作为示例而非限定，执行方法的执行主体也可以是目标车辆上的一个装置，如车载终端设备中控台OBU。
还应理解，该方法的执行主体还可以是服务器，即该服务器用于控制该智能网联车队，该智能网联车队中的每个智能网联汽车采集到的信息都会发送给该服务器，该服务器辨识车辆列队中异常车辆参数，并将识别结果发送给智能网联车队该每个智能网联汽车。
如图5所示，图5中示出的方法100可以包括S101至S110。下面结合图5详细说明方法100中的各个步骤。
S101，辨识流程开始。
S102，目标车辆采集当前行车数据。
首先目标车辆通过车载设备(定位设备、V2X设备)采集自车的行驶轨迹数据、前方车辆的行驶轨迹数据等。
S103，目标车辆判断当前驾驶场景。
目标车辆根据所述目标车辆的行驶轨迹数据和所述目标车辆的当前实时地图判断当前所述目标车辆的驾驶场景，是城市道路驾驶场景还是高速公路驾驶场景；如果是城市道路驾驶场景，则进入城市道路处理模块，否则进入高速公路处理模块。
S104，在城市道路驾驶场景下，目标车辆判断目标车辆前方是否存在异常区域。
S105，在城市道路驾驶场景下，目标车辆根据城市道路驾驶场景下的车辆轨迹生成算法，辨识Ta时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息，所述Ta时刻为所述目标车辆行驶过程中的标定时刻。
S106，目标车辆根据辨识的所述Ta时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息以及所述城市道路驾驶场景下的车辆轨迹生成算法，辨识Tb时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息，所述Tb时刻为当前时刻。
S107，在高速公路驾驶场景下，目标车辆判断目标车辆前方是否存在异常区域。
S108，在高速公路驾驶场景下，目标车辆根据高速公路驾驶场景下的车辆轨迹生成算法，辨识Ta时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息，所述Ta时刻为所述目标车辆行驶过程中的标定时刻。
S109，目标车辆根据辨识的所述Ta时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息以及所述高速公路驾驶场景下的车辆轨迹生成算法，辨识Tb时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息，所述Tb时刻为当前时刻。
S110，辨识流程结束。
根据该方法100可以看出异常区域车辆数量和位置、速度信息的辨识主要是首先辨识Ta时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息；然后根据辨识的所述Ta时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息以及所述车辆轨迹生成算法，辨识Tb时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息。该方法可以识别智能网联车队异常区域中的车辆数量及其每一辆车的位置、速度信息，使得智能网联车队异常区域恢复有序，实现对该智能网联汽车车队协同控制，不仅可以降低辆能耗、减少排放，还可以缓解交通拥堵、提高行车安全与交通通行效率。
为了更清楚的理解本申请，下面对上述方法中Ta时刻和Tb时刻进行描述，所述Ta时刻为所述目标车辆行驶过程中的标定时刻，所述Tb时刻为当前时刻。假设现在时间时：2020年4月18日08:42:50在不考虑CPU处理时间，则Tb时刻为2020年4月18日08:42:50，Ta时刻为Tb时刻的前一时刻，如Ta时刻为2020年4月18日08:42:45，或2020年4月18日08:42:40，或2020年4月18日08:42:35。Ta时刻是Tb时刻过去的时间。
同时，Ta时刻为所述目标车辆行驶过程中的标定时刻，是指Ta是根据标定时间确定的时刻，即可以事先根据驾驶场景或者其他因素设定一个标定时间，再根据该标定时间确定Ta，例如，在高速公路驾驶场景下，标定时间为1s，即当前时刻为Tb，Tb前一秒为Ta；在城市道路驾驶场景下，标定时间为3s，即当前时刻为Tb，Tb前三秒为Ta。
在步骤S103中，目标车辆判断当前驾驶场景，该目标车辆需要根据所述目标车辆的行驶轨迹数据和所述目标车辆的当前实时地图判断当前所述目标车辆的驾驶场景。所述目标车辆的行驶轨迹数据包括GPS信息，即所述目标车辆的位置信息、速度信息和时间信息，其中，GPS中的车辆的位置信息是车辆位置的经度和纬度，目标车辆需要根据GPS信息将该目标车辆定位于所述目标车辆的当前实时地图中，来判断当前所述目标车辆的驾驶场景。根据当前所述目标车辆的驾驶场景，选择所述目标车辆的驾驶场景下的车辆轨迹生成算法。
应理解，为了准确度更高，目标车辆在判断当前驾驶场景时，该目标车辆还可以根据所述目标车辆的行驶轨迹数据、所述前方车辆的行驶轨迹数据和所述目标车辆的当前实时 地图判断当前所述目标车辆的驾驶场景。
在步骤S104和步骤107中，该方法100均包括：确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域。
可选的，所述确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域，包括：获取所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的实际行驶轨迹，所述Tc时刻为所述目标车辆历史行驶过程中的标定时刻；计算所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的理论行驶轨迹；计算所述多个智能网联汽车中的每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差；根据所述每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差与第一阈值，确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域。
为了更清楚的理解本申请，下面先对上述方法中Tc时刻进行描述，所述Tc时刻为所述目标车辆行驶过程中的标定时刻，所述Tb时刻为当前时刻。假设现在时间时：2020年4月18日08:41:50在不考虑CPU处理时间，则Tb时刻为2020年4月18日08:41:50，Tc时刻为Tb时刻的前一时刻，如Ta时刻为2020年4月18日08:41:45，或2020年4月18日08:41:40，或2020年4月18日08:41:35。Tc时刻是Tb时刻过去的时间。
同时，Tc时刻为所述目标车辆行驶过程中的标定时刻，是指Tc是根据标定时间确定的时刻，即可以事先根据驾驶场景或者其他因素设定一个标定时间，再根据该标定时间确定Tc，例如，在高速公路驾驶场景下，标定时间为1s，即当前时刻为Tb，Tb前一秒为Tc；在城市道路驾驶场景下，标定时间为3s，即当前时刻为Tb，Tb前三秒为Tc。
应理解，所述Tc时刻可以和所述Ta时刻相同，也可以不同。例如，在高速公路场景下，确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域的标定时间为3s，即当前时刻为Tb，Tb前三秒为Tc；辨识车辆列队中异常车辆参数的标定时间为2s，即当前时刻为Tb，Tb前两秒为Ta。
具体而言，假如所述智能网联车队包括P1至P7七辆车，P7为目标车辆。P7接收P2至P6分别发送的车辆实际行驶轨迹以及P2至P6的车辆理论行驶轨迹，P2至P6的车辆理论行驶轨迹是通过计算依次得到的，P2基于跟车模型和Tc到Tb间的P1实际轨迹曲线，计算P2的理论轨迹曲线；P3基于跟车模型和Tc到Tb间的P2实际轨迹曲线，计算P3的理论轨迹曲线；P4基于跟车模型和Tc到Tb间的P3实际轨迹曲线，计算P4的理论轨迹曲线，P5基于跟车模型和Tc到Tb间的P4实际轨迹曲线，计算P5的理论轨迹曲线，P6基于跟车模型和Tc到Tb间的P5实际轨迹曲线，计算P6的理论轨迹曲线。
应理解，还可以基于车辆轨迹生成算法依次计算P2至P6的车辆理论行驶轨迹。
P7通过分别比较P2至P6车辆的实际行驶轨迹以及P2至P6车辆的理论行驶轨迹来确定所述P7车辆的前方包括的所述至少一段异常区域。
如果
|LP2,Cal-LP2,Real|≤第一阈值
|LP3,Cal-LP3,Real|≤第一阈值
|LP4,Cal-LP4,Real|≤第一阈值
|LP5,Cal-LP5,Real|≤第一阈值
|LP6,Cal-LP6,Real|≤第一阈值
其中，LPX,Cal表示在Tb时刻车辆X理论位置点；LPX,Real表示车辆X实际位置点；
则说明P1与P2之间、P2与P3之间、P3与P4之间、P4与P5之间、P5与P6之间，均不存在未知区域，即所述P7车辆的前方不包括异常区域。
若
|LP2,Cal-LP2,Real|≤第一阈值
|LP3,Cal-LP3,Real|≤第一阈值
|LP4,Cal-LP4,Real|>第一阈值
|LP5,Cal-LP5,Real|≤第一阈值
|LP6,Cal-LP6,Real|>第一阈值
其中，LPX,Cal表示在Tb时刻车辆X理论位置点；LPX,Real表示车辆X实际位置点；
则说明P1与P2之间、P2与P3之间、P4与P5之间均不存在未知区域；P3与P4之间、P5与P6之间则出现异常区域，可能是P3与P4之间、P5与P6之间驶入了非智能网联汽车，即所述P7车辆的前方包括两段异常区域。
若
|LP2,Cal-LP2,Real|≤第一阈值
|LP3,Cal-LP3,Real|≤第一阈值
|LP4,Cal-LP4,Real|≤第一阈值
|LP5,Cal-LP5,Real|≤第一阈值
|LP6,Cal-LP6,Real|>第一阈值
其中，LPX,Cal表示在Tb时刻车辆X理论位置点；LPX,Real表示车辆X实际位置点；
则说明P1与P2之间、P2与P3之间、P3与P4之间、P4与P5之间均不存在未知区域；P5与P6之间则出现异常区域，可能是P5与P6之间驶入了非智能网联汽车，即所述P7车辆的前方包括一段异常区域。
应理解，车辆的行驶轨迹一般包括位置信息和速度信息，上述描述了根据车辆的位置信息来判断目标车辆前方是否出现异常区域，还可以根据车辆的速度信息来判断目标车辆前方是否出现异常区域，即通过比较多个车辆的理论车速和实际车速进行判断。
可选的，所述确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域，包括：获取所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的实际行驶轨迹，根据获取到的所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的实际行驶轨迹，确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域。
具体而言，假如所述智能网联车队包括P1至P7七辆车，P7为目标车辆。行驶途中，P5由于车辆通信故障，由智能网联汽车变为非智能网联汽车，P7接收不到P5发送的车辆实际行驶轨迹以及车辆理论行驶轨迹，因此P7判断P5出现异常，即P4与P6之间则出现异常区域。
可选的，所述确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域，包括：
获取所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的实际行驶轨迹；计算所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的理论行驶轨迹；计算所述多个智能网联汽车中的每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差；根据所述每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差与第一阈值，以及获取到的所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的实际行驶轨迹，确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域。
具体而言，假如所述智能网联车队包括P1至P7七辆车，P7为目标车辆。行驶途中，P5由于车辆通信故障，由智能网联汽车变为非智能网联汽车，P7接收不到P5发送的车辆实际行驶轨迹以及车辆理论行驶轨迹，P7可以接收到P5以外的其他智能网联汽车的信息。
若：
|LP2,Cal-LP2,Real|≤第一阈值
|LP3,Cal-LP3,Real|>第一阈值
|LP4,Cal-LP4,Real|≤第一阈值
|LP6,Cal-LP6,Real|>第一阈值
其中，LPX,Cal表示在Tb时刻车辆X理论位置点；LPX,Real表示车辆X实际位置点；
则说明P1与P2之间、P3与P4之间均不存在未知区域；P2与P3之间、P4与P6之间则出现异常区域，可能是P2与P3之间驶入了非智能网联汽车，P4与P6之间P5发生了故障，同时也可能驶入了非智能网联汽车。
应理解，该第一阈值为事先设定的值，可以是经验值等。
在上述情况下，所述智能网联车队包括P1至P7七辆车，P7为目标车辆。行驶途中，P5由于车辆通信故障，由智能网联汽车变为非智能网联汽车，P7接收不到P5发送的车辆实际行驶轨迹以及车辆理论行驶轨迹，P7可以接收到P5以外的其他智能网联汽车的信息。因此可以根据P5的信息丢失直接判断P4和P6之间出现异常。
例如，设过去时间为：2020年5月17日10：08：23，在这一刻，所有车辆都是智能网联汽车，目标车辆P7可获取P1～P6每一辆车的ID信息、速度、位置信息等。
在2020年5月17日10：09：23，P5出现故障，由非智能网联汽车变为普通车辆，则此时目标车辆P7可获取P1～P4、P6每一辆车的ID信息、速度、位置信息等。P5的ID信息、速度、位置信息缺失。目标车辆可直接判断出：P4与P6之间出现异常区域。
由于在不同的驾驶场景下，车辆轨迹生成算法不同，下面分别介绍城市道路驾驶场景和高速公路驾驶场景的车辆轨迹生成算法。
1、城市道路驾驶场景的车辆轨迹生成算法：
城市道路驾驶场景下的车辆轨迹生成算法分目标车辆前方无车和目标车辆前方有车两种场景进行研究，下面分别进行介绍：
(1)目标车辆前方无车：
当目标车辆前方无车时，根据红绿灯的类型，又分为以下三种情况：
a、绿灯下的车辆行驶规律研究：
采用最优速度模型(Optimal Velocity Model，OVM)，当目标车辆速度小于或等于当前的交通车速时，车辆C通常加速行驶，且该加速度可通过式(1)最优速度模型(Optimal  Velocity Model，OVM)进行估算。
Figure PCTCN2020093532-appb-000001
其中，v表示目标车辆当前车速，V表示来自ITS的交通车速，τ g表示自适应的时间，自适应的时间为标定量，通过采集红绿灯下某一辆车通过的时间，进行估算得到。
b、黄灯下的车辆行驶规律研究：
黄灯下的车辆行驶规律采用停车决策模型，该停车决策模型如式(2)所示，当红绿灯从绿色变为黄色时，目标车辆的驾驶员需要做出决策，是不停车通过红绿灯路口，还是停在路口等待下一个绿灯。
Figure PCTCN2020093532-appb-000002
其中，τ y表示当前黄灯持续的时间，d veh,d表示当前车辆距离前方红绿灯的距离。
c、黄灯下的车辆行驶规律研究：
红灯下的跟车模型(红绿灯假设为L＝0的静止车)，当红绿灯状态为红色时，红绿灯可假定为一辆忽略车辆长度的静止车辆。当红绿灯状态从红色变为绿色时，该静止车辆将立即消失。本申请采用Martin Triber提出的智能驾驶模型(Intelligent Driver Model，IDM)。IDM是利用车头时间距、前后车速差以及后车的车速作为模型的输入，具体定义如式(3)所述。
Figure PCTCN2020093532-appb-000003
其中，a f,max表示目标车的最大加速度；v des表示目标车的期望车速；v f表示目标车的速度；v l表示前车的速度；s f表示目标车行驶的里程位移；s l表示前车行驶的里程位移；l veh表示车身长度(车身长度统计学的长度，如小车长度，大车长度等)；g f表示前目标车车间距；δ表示加速度调整系数；g 0表示前目标车最小车间距；Γ表示安全时头车间距；dec f,max表示目标车最大减速度。
应理解，本申请实施例采用的IDM跟车模型仅用来示例，并不对本申请造成任何限定，跟车模型还可以选用其他跟车模型，例如，通用跟车模型(General Motor，GM)、线性跟车模型、生理-心理跟车模型和安全距离模型等。
(2)目标车辆前方有车：
在此种驾驶场景下，目标车辆的驾驶行为不仅受到前方车辆的影响，还受到红绿灯的影响。通常，红绿灯对那些离红绿灯路口比较近的车辆，影响比较大。因此，目标车辆前方有车可分两种情况进行讨论：
a、正常行驶时，跟车行为分析：
本申请实施例采用Martin Triber提出的智能驾驶模型(Intelligent Driver Model，IDM)来描述正常行驶时的跟车行为。IDM是利用车头时间距、前后车速差以及目标车辆的车速 作为模型的输入，具体定义如式(4)所述。
Figure PCTCN2020093532-appb-000004
其中，a f,max表示目标车的最大加速度；v des表示目标车的期望车速；v f表示目标车的速度；v l表示前车的速度；s f表示目标车行驶的里程位移；s l表示前车行驶的里程位移；l veh表示车身长度(车身长度统计学的长度，如小车长度，大车长度等)；g f表示前目标车车间距；δ表示加速度调整系数；g 0表示前、目标车最小车间距；Γ表示安全时头车间距；dec f,max表示目标车最大减速度。
b、车辆在红绿灯路口前的停车队列行为与启动时的冲击波行为分析：
由于红绿灯间隔性的影响，在红绿灯路口，会经常出现车辆停车时的队列现象和启动时的冲击波现象，停车队列行为与启动时的冲击波行主要是指驾驶员在此刻会有反应时间，该驾驶员的反应时间会影响车辆轨迹生成算法。
为便于阐述城市道路车辆轨迹生成算法原理，以图6和图7进行说明。
图6示出了在城市道路上，智能网联车队行驶示意图。其中，P1、P2、P3、P4、P5是智能网联车队，每辆车都具备V2X功能；V1、V2是普通车辆，均不具备V2X功能。图7则示出了在城市公路上，车辆轨迹生成算法示意图。只要知道Ta到Tb时间段P1车的实际行驶轨迹、P2、P3、P4、P5在Ta时刻的位置、速度信息以及前方红绿灯相位信息，基于上述的城市道路车辆行驶规律，通过One-By-One的方式，即根据P1的是实际行驶轨迹和车辆轨迹生成算法生成P2的理论轨迹生成算法，根据P2的是理论行驶轨迹和车辆轨迹生成算法生成P3的理论轨迹生成算法，根据P3的是理论行驶轨迹和车辆轨迹生成算法生成P4的理论轨迹生成算法，根据P4的是理论行驶轨迹和车辆轨迹生成算法生成P5的理论轨迹生成算法，从而依次生出P2、P3、P4、P5的理论行驶轨迹，见图6中虚线所述。
2、高速公路驾驶场景的车辆轨迹生成算法：
相比于城市道路，由于没有红绿灯间隔性的影响，高速公路车速轨迹生成算法则比较简单。可采用Martin Triber提出的智能驾驶模型(Intelligent Driver Model，IDM)来描述正常行驶时的跟车行为。IDM是利用车头时间距、前后车速差以及后车的车速作为模型的输入，具体定义如式(5)所述。
Figure PCTCN2020093532-appb-000005
其中，a f,max表示后车的最大加速度；v des表示后车的期望车速；v f表示后车的速度；v l表示前车的速度；s f表示后车行驶的里程位移；s l表示前车行驶的里程位移；l veh表 示车身长度；g f表示前后车车间距；δ表示加速度调整系数；g 0表示前后车最小车间距；Γ表示安全时头车间距；dec f,max表示后车最大减速度。
为便于阐述高速公路车辆轨迹生成算法原理，以图8和图9进行说明。
图8示出了Ta到Tb时间段，智能网联车队行驶示意图。图9则示出了高速公路上，车辆轨迹生成算法示意图。只要知道Ta到Tb时间段P1车的行驶轨迹及P2、P3、P4、P5在Ta时刻的位置、速度信息，基于车辆轨迹生成算法(高速公路驾驶场景即IDM跟车模型)，通过One-By-One的方式，就可依次生出Ta到Tb时间段P2、P3、P4、P5的理论行驶轨迹。
通过上述内容可知，在获知Ta到Tb时间段目标车辆的行驶轨迹以及Ta时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息，基于车辆轨迹生成算法，就可获知Ta到Tb时间段异常区域中的每辆车的理论行驶轨迹。然而，对于目标车辆来说，在Ta时刻，其异常区域的车辆数量及其位置、速度信息是未知的。因此，需要对Ta时刻异常区域中的车辆数量及其位置、速度信息进行辨识。
下面具体描述异常区域参数辨识算法，即在步骤S105和步骤S108中如何辨识Ta时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息。
异常区域参数辨识算法主要包括以下三个步骤：
1、根据式(6)计算Ta时刻，所述异常区域中最大的车辆数量N，如图10所示，以P5为例进行说明，P5前方的车队出现异常，P3与P5之间的区域是车队异常区域。
Figure PCTCN2020093532-appb-000006
其中，L veh是车辆平均长度，L Gap表示前后两辆车的最小车间距，
Figure PCTCN2020093532-appb-000007
表示T a时刻异常区域的长度，可通过式(7)进行计算。
Figure PCTCN2020093532-appb-000008
其中，
Figure PCTCN2020093532-appb-000009
表示智能网联车P3的位置，
Figure PCTCN2020093532-appb-000010
表示智能网联车P5的位置。
2、计算所述异常区域车辆数量为K时，目标车辆的理论行驶轨迹和实际行驶轨迹的均方根误差(Root Mean Square Error，RMSE)，其中，K∈{1,…,N}；
在计算目标车辆的理论行驶轨迹和实际行驶轨迹的均方根误差RMSE时可以采用机器学习算法(如遗传算法)，寻找异常区域车辆数量为K时(K∈{1,…,N})的RMSE：
设在T a时刻异常区域车辆数量为K，(其中，K为随机数)先随机生成所述异常区域每一辆车在T a时刻的位置信息、速度信息；然后，基于车辆轨迹生成算法和T a时刻第i(i∈{1,…,K})辆车的位置、速度信息，(其中，第i辆车的位置、速度信息根据第i-1辆车的位置、速度信息确定)，基于One-By-One的方式，可依次生出每辆车从T a到T b时刻的车辆行驶轨迹；之后，基于第K辆车的理论轨迹信息和车辆轨迹生成算法，计算出车辆P5(即目标车辆)从T a到T b的理论轨迹为
Figure PCTCN2020093532-appb-000011
之后，再根据车辆P5从T a到T b的实际轨迹
Figure PCTCN2020093532-appb-000012
和理论轨迹
Figure PCTCN2020093532-appb-000013
根据式(8)计算其均方根
Figure PCTCN2020093532-appb-000014
在所述异常区域车辆数量为K时，可以设定迭代次数M，M为随机生成所述异常区域每一辆车在T a时刻的位置信息、速度信息的次数，如M为50，则随机生成50组所述异常区域每一辆车在T a时刻的位置信息、速度信息。
通过机器学习算法，可以从多个RMSE中确定出使
Figure PCTCN2020093532-appb-000015
取得最小值的每一辆车在T a时刻的位置、速度信息。
Figure PCTCN2020093532-appb-000016
其中，n表示数据长度。
应理解，上述通过确定使
Figure PCTCN2020093532-appb-000017
取得最小值时的每一辆车在T a时刻的位置、速度信息只是一种在所述异常区域车辆数量为K时，确定所述异常区域每辆车的位置信息信息和速度信息的方法，还可以通过在所述异常区域车辆数量为K时，当所述RMSE符合第一条件时，确定所述异常区域每辆车的位置信息信息和速度信息，所述第一条件可以是上述
Figure PCTCN2020093532-appb-000018
取得最小值，所述第一条件可以是上述
Figure PCTCN2020093532-appb-000019
满足一定的范围随机选取
Figure PCTCN2020093532-appb-000020
确定所述异常区域每辆车的位置信息信息和速度信息，如该范围是RMSE的前五个值，RMSE按递增顺序排列。
3、确定所述异常区域车辆数量为K时，当所述RMSE最小时，所述异常区域每辆车的位置信息信息和速度信息，其中，K遍历1到N的每个值；根据式(9)计算Ta时刻，使得异常区域RMSE最小的车辆数量，并得到该车辆数量下的每辆车的位置、速度信息。
Figure PCTCN2020093532-appb-000021
应理解，计算Ta时刻，使得异常区域RMSE最小的车辆数量只是一种确定车辆数量的方法，还可以通过在所述异常区域车辆数量为K时，当所述RMSE符合第二条件时，确定车辆数量，所述第二条件可以是上述
Figure PCTCN2020093532-appb-000022
取得最小值，所述第一条件可以是上述
Figure PCTCN2020093532-appb-000023
满足一定的范围随机选取
Figure PCTCN2020093532-appb-000024
如该范围是RMSE的前五个值，RMSE按递增顺序排列。
通过上述三个步骤可以辨识出P5前方Ta时刻异常区域中的车辆数量、异常区域中的每辆车的位置信息和异常区域中的每辆车的速度信息。
在辨识出Ta时刻车队异常区域的车辆数量及其位置、速度信息后，再次利用车辆轨迹生成算法，就可得到车队异常区域的每一辆车在Tb时刻的位置、速度信息。
图11示出了在高速公路上，基于Ta时刻辨识的结果，得到Tb时刻异常区域车辆数量及其位置、速度信息的示意图。
图12示出了在城市道路上，基于Ta时刻辨识的结果，得到Tb时刻异常区域车辆数量及其位置、速度信息的示意图。
由于在高速公路驾驶场景和在城市道路驾驶场景的环境不同，因此，不同驾驶场景下应用该方法100的车辆配置要求不同，为了更清楚的理解本申请，下面对不同驾驶场景中，目标车辆的配置要求进行介绍。
在高速公路驾驶场景下，ICV车辆需要配备有：GPS定位设备：用于获取车辆位置信息和速度信息；V2X设备：获取智能网联车队的其他网联车的位置信息和速度信息，并向其他网联车发送自身的位置信息和速度信息；雷达和/或摄像头：感知前方车辆的位置信息和速度信息，应理解，雷达和/或摄像头可以配置在车身前部和/或车身尾部。图13a和图13b所示为高速公路驾驶场景下，ICV车辆的配置示意图。
在城市道路驾驶场景下，ICV车辆需配备有：GPS定位设备：获取车辆位置及速度信息；V2X设备：获取车队其他网联车的位置、速度信息，并向他们发送自身的位置、速度信息和接收前方红绿灯相位信息；雷达或摄像头：感知前方车辆的位置、速度信息，雷达 和/或摄像头可以配置在车身前部和/或车身尾部；远程信息处理器(TelematicsBox，T-Box)T-Box：接收交通信息中心发送的当前道路交通车速信息。此外，在城市道路驾驶场景下，道路中的红绿灯会影响车辆行驶轨迹，因此城市道路驾驶场景下红绿灯需要具备设备联网(Infrastructure to Everything，I2X)功能，图14a和图14b所示为城市道路驾驶场景下，ICV车辆的配置示意图。
可选的，当所述智能网联车队的每个智能网联汽车的车头配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车到所述每段异常区域的尾部。
可选的，当所述智能网联汽车的车头和车尾均配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车的相邻后车到所述每段异常区域的尾部相邻的前方车辆之间的区域。
当所述智能网联汽车的车辆队列中的车辆的车头和车尾均配置有雷达或者摄像头时，车队异常区域长度将变短，有利于提高辨识的精度。
以上结合图1至图14对本申请实施例的基于网联信息的车辆列队行驶中异常车辆参数辨识的方法做了详细说明。以下，结合图15对本申请实施例通信装置进行详细说明。
图15示出了本申请实施例的终端设备200的示意性框图。
一些实施例中，该终端设备200可以为接入网设备，也可以为芯片或电路，比如可设置于接入网设备的芯片或电路。
一些实施例中，该终端设备200可以为车载终端设备，也可以为芯片或电路，比如可设置于核心网设备的芯片或电路。
一些实施例中，该终端设备200可以为服务器，也可以为芯片或电路，比如可设置于服务器的芯片或电路，该服务器可以独立于车辆，通过该服务器的收发器与目标车辆通信，进行数据传送，例如，目标车辆将采集到的数据发送给该服务器，由该服务器进行计算处理，将结果发送给该目标车辆。
一种可能的方式中，该终端设备200可以包括处理单元210(即，处理器的一例)和收发单元230。一些可能的实现方式中，处理单元210还可以称为确定单元。一些可能的实现方式中，收发单元230可以包括接收单元和发送单元。
在一种实现方式中，收发单元230可以通过收发器或者收发器相关电路或者接口电路实现。
在一种实现方式中，该装置还可以包括存储单元220。一种可能的方式中，该存储单元220用于存储指令。在一种实现方式中，该存储单元也可以用于存储数据或者信息。存储单元220可以通过存储器实现。
一些可能的设计中，该处理单元210用于执行该存储单元220存储的指令，以使终端设备200实现如上述方法中终端设备执行的步骤。或者，该处理单元210可以用于调用存储单元220的数据，以使终端设备200实现如上述方法中终端设备执行的步骤。
一些可能的设计中，该处理单元210用于执行该存储单元220存储的指令，以使终端设备200实现如上述方法中接入网设备执行的步骤。或者，该处理单元210可以用于调用存储单元220的数据，以使终端设备200实现如上述方法中接入网设备执行的步骤。
例如，该处理单元210、存储单元220、收发单元230可以通过内部连接通路互相通 信，传递控制和/或数据信号。例如，该存储单元220用于存储计算机程序，该处理单元210可以用于从该存储单元220中调用并运行该计算计程序，以控制收发单元230接收信号和/或发送信号，完成上述方法中终端设备或接入网设备的步骤。该存储单元220可以集成在处理单元210中，也可以与处理单元210分开设置。
可选地，若该终端设备200为通信设备(例如，终端设备)，该收发单元230包括接收器和发送器。其中，接收器和发送器可以为相同或者不同的物理实体。为相同的物理实体时，可以统称为收发器。
可选地，若该终端设备200为芯片或电路，该收发单元230包括输入接口和输出接口。
作为一种实现方式，收发单元230的功能可以考虑通过收发电路或者收发的专用芯片实现。处理单元210可以考虑通过专用处理芯片、处理电路、处理单元或者通用芯片实现。
作为另一种实现方式，可以考虑使用通用计算机的方式来实现本申请实施例提供的通信设备(例如终端设备，或接入网设备)。即将实现处理单元210、收发单元230功能的程序代码存储在存储单元220中，通用处理单元通过执行存储单元220中的代码来实现处理单元210、收发单元230的功能。
在一种实现方式中，所述终端设备可以应用于目标车辆，所述目标车辆为智能网联车队中的一辆智能网联汽车，所述终端设备还可以包括判断单元240，所述判断单元240用于根据目标车辆的行驶轨迹数据和所述目标车辆的当前实时地图判断当前所述目标车辆的驾驶场景，所述目标车辆的驾驶场景为城市道路驾驶场景或高速公路驾驶场景，所述目标车辆为智能网联车队的智能网联汽车；所述处理单元210用于根据当前所述目标车辆的驾驶场景，选择所述目标车辆当前驾驶场景下的车辆轨迹生成算法；所述处理单元210还用于确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域，所述至少一段异常区域为所述目标车辆所在的智能网联车队中的异常区域，所述Tb时刻为当前时刻；所述处理单元210还用于基于选择的所述车辆轨迹生成算法和机器学习算法，辨识在Ta时刻，至少一段异常区域中的每段异常区域中的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，所述Ta时刻为所述目标车辆历史行驶过程中的标定时刻；所述处理单元210还用于基于选择的所述车辆轨迹生成算法，根据在所述Ta时刻，所述每段异常区域中的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，辨识Tb时刻所述每段异常区域的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息。
可选的，所述处理单元210具体用于计算所述每段异常区域中的车辆数量为K时，所述目标车辆的理论行驶轨迹和实际行驶轨迹的均方根误差(Root Mean Square Error，RMSE)，其中，K∈{1,…,N}，N为所述每段异常区域包括的车辆数量的最大值N，K遍历1到N的每个值；当所述RMSE符合第一条件时，获取所述异常区域中每辆车的位置信息信息和速度信息；在Ta时刻，从确定的N个RMSE中确定符合第二条件的RMSE对应的车辆数量、每辆车的位置信息信息和速度信息。
可选的，所述处理单元210具体用于获取所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的实际行驶轨迹，所述Tc时刻为所述目标车辆历史行驶过程中的标定时刻；计算所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的理论行驶轨迹；计算所述多个智能网联汽车中的每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差；根据所述每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差与第一阈值，确定Tb时刻所述目 标车辆的前方包括的所述至少一段异常区域。
可选的，当所述智能网联车队的每个智能网联汽车的车头配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车到所述每段异常区域的尾部。
可选的，当所述智能网联汽车的车头和车尾均配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车的相邻后车到所述每段异常区域的尾部相邻的前方车辆之间的区域。
此时，当所述智能网联汽车的车辆队列中的车辆的车头和车尾均配置有雷达或者摄像头时，可以缩短车队异常区域长度，有利于提高辨识的精度。
可选的，所述处理单元210具体用于在Ta时刻所述异常区域车辆数量为K时，随机生成所述异常区域中的每一辆车在Ta时刻的位置信息、速度信息；根据车辆轨迹生成算法，计算出所述目标车辆的相邻的前方车辆从Ta时刻到Tb时刻的理论轨迹；根据所述目标车辆的相邻的前方车辆从Ta到Tb的实际轨迹和理论轨迹，计算所述目标车辆的相邻的前方车辆的理论行驶轨迹和实际行驶轨迹的RMSE。
可选的，所述处理单元210具体用于确定所述Ta时刻所述异常区域的长度；根据所述异常区域的长度、车辆平均长度和相邻两辆车的最小车间距，确定所述异常区域中最大的车辆数量N。
可选的，所述处理单元210还用于：确定不同驾驶场景下的车辆轨迹生成算法，所述车辆轨迹生成算法包括城市道路车辆轨迹生成算法和高速公路车辆轨迹生成算法。
本申请的说明书实施例和权利要求书及附图中的术语“第一”、“第二”等仅用于区分描述的目的，而不能理解为指示或暗示相对重要性，也不能理解为指示或暗示顺序。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元。方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
应理解，本申请实施例中，该处理器可以为中央处理单元(central processing unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现成可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
还应理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的随机存取存储器(random access memory，RAM)可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存 储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。
上述实施例，可以全部或部分地通过软件、硬件、固件或其他任意组合来实现。当使用软件实现时，上述实施例可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令或计算机程序。在计算机上加载或执行所述计算机指令或计算机程序时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以为通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集合的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质。半导体介质可以是固态硬盘。
本申请实施例还提供了一种计算机可读介质，其上存储有计算机程序，该计算机程序被计算机执行时实现上述任一实施例中的终端设备执行的步骤。
本申请实施例还提供了一种计算机程序产品，该计算机程序产品被计算机执行时实现上述任一实施例中的终端设备执行的步骤。
本申请实施例还提供了一种系统芯片，该系统芯片包括：通信单元和处理单元。该处理单元，例如可以是处理器，该处理器可以实现上述实施例中处理单元和判断单元的功能。该通信单元例如可以是通信接口、输入/输出接口、管脚或电路等。该处理单元可执行计算机指令，以使该通信装置内的芯片执行上述本申请实施例提供的终端设备执行的步骤。
可选地，该计算机指令被存储在存储单元中。
本申请中的各个实施例可以独立的使用，也可以进行联合的使用，这里不做限定。
另外，本申请的各个方面或特征可以实现成方法、装置或使用标准编程和/或工程技术的制品。本申请中使用的术语“制品”涵盖可从任何计算机可读器件、载体或介质访问的计算机程序。例如，计算机可读介质可以包括，但不限于:磁存储器件(例如，硬盘、软盘或磁带等)，光盘(例如，压缩盘(compact disc，CD)、数字通用盘(digital versatile disc，DVD)等)，智能卡和闪存器件(例如，可擦写可编程只读存储器(erasable programmable read-only memory，EPROM)、卡、棒或钥匙驱动器等)。另外，本文描述的各种存储介质可代表用于存储信息的一个或多个设备和/或其它机器可读介质。术语“机器可读介质”可包括但不限于，无线信道和能够存储、包含和/或承载指令和/或数据的各种其它介质。
应理解，在本申请中的所有表格参数仅用于示例，并不表示具体的计算数值或者参数等。
应理解，“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。“至少一个”是指一个或一个以上；“A和B中的至少一个”，类似于“A和/或B”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和B中的至少一个，可以表示：单独存在A，同时存在A和B，单独存在B这三种情 况。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (19)

  1. 一种辨识车辆列队中异常车辆参数的方法，其特征在于，包括：
    根据目标车辆的行驶轨迹数据和所述目标车辆的当前实时地图判断当前所述目标车辆的驾驶场景，所述目标车辆的驾驶场景为城市道路驾驶场景或高速公路驾驶场景，所述目标车辆为智能网联车队的智能网联汽车；
    根据当前所述目标车辆的驾驶场景，选择所述目标车辆当前驾驶场景下的车辆轨迹生成算法；
    确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域，所述至少一段异常区域为所述目标车辆所在的智能网联车队中的异常区域，所述Tb时刻为当前时刻；
    基于选择的所述车辆轨迹生成算法和机器学习算法，辨识在Ta时刻，至少一段异常区域中的每段异常区域中的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，所述Ta时刻为所述目标车辆历史行驶过程中的标定时刻；
    基于选择的所述车辆轨迹生成算法，根据在所述Ta时刻，所述每段异常区域中的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，辨识Tb时刻所述每段异常区域的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息。
  2. 根据权利要求1所述的方法，其特征在于，所述基于选择的所述车辆轨迹生成算法和机器学习算法，辨识Ta时刻所述至少一段异常区域中的每段异常区域的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，包括：
    计算所述每段异常区域中的车辆数量为K时，所述目标车辆的理论行驶轨迹和实际行驶轨迹的均方根误差RMSE，其中，K∈{1,…,N}，N为所述每段异常区域包括的车辆数量的最大值N，K遍历1到N的每个值；
    当所述RMSE符合第一条件时，获取所述异常区域中每辆车的位置信息信息和速度信息；
    在Ta时刻，从确定的N个RMSE中确定符合第二条件的RMSE对应的车辆数量、每辆车的位置信息信息和速度信息。
  3. 根据权利要求1或2所述的方法，其特征在于，所述确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域，包括：
    获取所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的实际行驶轨迹，所述Tc时刻为所述目标车辆历史行驶过程中的标定时刻；
    计算所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的理论行驶轨迹；
    计算所述多个智能网联汽车中的每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差；
    根据所述每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差与第一阈值，确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，当所述智能网联车队的每个智能网联汽车的车头配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车到所述每段异常区域的尾部相邻的前方车辆之间的区域。
  5. 根据权利要求1至3中任一项所述的方法，其特征在于，当所述智能网联汽车的 车头和车尾均配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车的相邻后车到所述每段异常区域的尾部相邻的前方车辆之间的区域。
  6. 根据权利要求2至5中任一项所述的方法，其特征在于，计算所述每段异常区域中的车辆数量为K时，目标车辆的理论行驶轨迹和实际行驶轨迹的均方根误差RMSE，包括：
    在Ta时刻所述异常区域车辆数量为K时，随机生成所述异常区域中的每一辆车在Ta时刻的位置信息、速度信息；
    根据车辆轨迹生成算法，计算出所述目标车辆的相邻的前方车辆从Ta时刻到Tb时刻的理论轨迹；
    根据所述目标车辆的相邻的前方车辆从Ta到Tb的实际轨迹和理论轨迹，计算所述目标车辆的相邻的前方车辆的理论行驶轨迹和实际行驶轨迹的RMSE。
  7. 根据权利要求2至6中任一项所述的方法，其特征在于，所述方法还包括：
    确定所述Ta时刻所述异常区域的长度；
    根据所述异常区域的长度、车辆平均长度和相邻两辆车的最小车间距，确定所述异常区域中最大的车辆数量N。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述方法还包括：
    确定不同驾驶场景下的车辆轨迹生成算法，所述车辆轨迹生成算法包括城市道路车辆轨迹生成算法和高速公路车辆轨迹生成算法。
  9. 一种终端设备，其特征在于，包括：
    判断单元，所述判断单元用于根据目标车辆的行驶轨迹数据和所述目标车辆的当前实时地图判断当前所述目标车辆的驾驶场景，所述目标车辆的驾驶场景为城市道路驾驶场景或高速公路驾驶场景，所述目标车辆为智能网联车队的智能网联汽车；
    处理单元，所述处理单元用于根据当前所述目标车辆的驾驶场景，选择所述目标车辆当前驾驶场景下的车辆轨迹生成算法；
    所述处理单元还用于确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域，所述至少一段异常区域为所述目标车辆所在的智能网联车队中的异常区域，所述Tb时刻为当前时刻；
    所述处理单元还用于基于选择的所述车辆轨迹生成算法和机器学习算法，辨识在Ta时刻，至少一段异常区域中的每段异常区域中的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，所述Ta时刻为所述目标车辆历史行驶过程中的标定时刻；
    所述处理单元还用于基于选择的所述车辆轨迹生成算法，根据在所述Ta时刻，所述每段异常区域中的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息，辨识Tb时刻所述每段异常区域的车辆数量、所述每段异常区域包括的每辆车的位置信息和速度信息。
  10. 根据权利要求9所述的终端设备，其特征在于，所述处理单元具体用于：
    计算所述每段异常区域中的车辆数量为K时，所述目标车辆的理论行驶轨迹和实际行驶轨迹的均方根误差RMSE，其中，K∈{1,…,N}，N为所述每段异常区域包括的车辆数量的最大值N，K遍历1到N的每个值；
    当所述RMSE符合第一条件时，获取所述异常区域中每辆车的位置信息信息和速度信息；
    在Ta时刻，从确定的N个RMSE中确定符合第二条件的RMSE对应的车辆数量、每辆车的位置信息信息和速度信息。
  11. 根据权利要求9或10所述的终端设备，其特征在于，所述处理单元具体用于：
    获取所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的实际行驶轨迹，所述Tc时刻为所述目标车辆历史行驶过程中的标定时刻；
    计算所述目标车辆前方多个智能网联汽车在Tc时刻至Tb时刻的理论行驶轨迹；
    计算所述多个智能网联汽车中的每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差；
    根据所述每个智能网联汽车的理论行驶轨迹和实际行驶轨迹的差与第一阈值，确定Tb时刻所述目标车辆的前方包括的所述至少一段异常区域。
  12. 根据权利要求9至11中任一项所述的终端设备，其特征在于，当所述智能网联车队的每个智能网联汽车的车头配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车到所述每段异常区域的尾部相邻的前方车辆之间的区域。
  13. 根据权利要求9至12中任一项所述的终端设备，其特征在于，当所述智能网联车队的每个智能网联汽车的车头和车尾均配置有雷达或者摄像头时，所述至少一段异常区域中的每段异常区域的距离为所述每段异常区域首部相邻的第一辆智能网联汽车的相邻后车到所述每段异常区域的尾部相邻的前方车辆之间的区域。
  14. 根据权利要求10至13中任一项所述的终端设备，其特征在于，所述处理单元具体用于：
    在Ta时刻所述异常区域车辆数量为K时，随机生成所述异常区域中的每一辆车在Ta时刻的位置信息、速度信息；
    根据车辆轨迹生成算法，计算出所述目标车辆的相邻的前方车辆从Ta时刻到Tb时刻的理论轨迹；
    根据所述目标车辆的相邻的前方车辆从Ta到Tb的实际轨迹和理论轨迹，计算所述目标车辆的相邻的前方车辆的理论行驶轨迹和实际行驶轨迹的RMSE。
  15. 根据权利要求10至14中任一项所述的终端设备，其特征在于，所述处理单元还用于：
    确定所述Ta时刻所述异常区域的长度；
    根据所述异常区域的长度、车辆平均长度和相邻两辆车的最小车间距，确定所述异常区域中最大的车辆数量N。
  16. 根据权利要求9至15中任一项所述的终端设备，其特征在于，所述处理单元还用于：
    确定不同驾驶场景下的车辆轨迹生成算法，所述车辆轨迹生成算法包括城市道路车辆轨迹生成算法和高速公路车辆轨迹生成算法。
  17. 一种终端设备，包括处理器，所述处理器与存储器相连，所述存储器用于存储计算机程序，所述处理器用于执行所述存储器中存储的计算机程序，以使得所述装置执行如权利要求1至8中任一项所述的方法。
  18. 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存储有计算机 程序，当所述计算机程序被运行时，实现如权利要求1至8中任一项所述的方法。
  19. 一种芯片，其特征在于，包括处理器和接口；
    所述处理器用于读取指令以执行权利要求1至8中任一项所述的方法。
PCT/CN2020/093532 2020-05-29 2020-05-29 一种辨识车辆列队中异常车辆参数的方法和终端设备 WO2021237745A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP20937270.5A EP4145340A4 (en) 2020-05-29 2020-05-29 METHOD OF IDENTIFYING ABNORMAL VEHICLE PARAMETERS IN A VEHICLE CONvoy AND TERMINAL DEVICE
CN202080004923.8A CN112673406B (zh) 2020-05-29 2020-05-29 一种辨识车辆列队中异常车辆参数的方法和终端设备
PCT/CN2020/093532 WO2021237745A1 (zh) 2020-05-29 2020-05-29 一种辨识车辆列队中异常车辆参数的方法和终端设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/093532 WO2021237745A1 (zh) 2020-05-29 2020-05-29 一种辨识车辆列队中异常车辆参数的方法和终端设备

Publications (1)

Publication Number Publication Date
WO2021237745A1 true WO2021237745A1 (zh) 2021-12-02

Family

ID=75413941

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/093532 WO2021237745A1 (zh) 2020-05-29 2020-05-29 一种辨识车辆列队中异常车辆参数的方法和终端设备

Country Status (3)

Country Link
EP (1) EP4145340A4 (zh)
CN (1) CN112673406B (zh)
WO (1) WO2021237745A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114841679A (zh) * 2022-06-29 2022-08-02 陕西省君凯电子科技有限公司 车辆行驶数据的智能管理系统
CN115223357A (zh) * 2022-04-07 2022-10-21 港珠澳大桥管理局 一种交通信息处理系统、方法、装置和计算机设备
CN117875813A (zh) * 2024-03-11 2024-04-12 北京中交兴路信息科技股份有限公司 行驶轨迹的可信度分析方法、装置、存储介质及电子设备

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113538936B (zh) * 2021-05-28 2022-07-22 东南大学 一种车路协同环境下的信号协同控制方法、装置及存储介质
CN114677779B (zh) * 2022-03-30 2024-05-28 广州文远知行科技有限公司 车辆配置状态监测方法、装置、存储介质、计算机设备
CN115099128B (zh) * 2022-05-30 2023-07-07 同济大学 一种异常驾驶行为识别与致因分析方法和系统
CN115620543B (zh) * 2022-09-29 2023-06-27 斯润天朗（北京）科技有限公司 交通路口多车协同通行方法、装置及计算机设备
CN116189477B (zh) * 2023-02-17 2023-11-21 东南大学 一种智能网联汽车数据异常环境的安全控制方法及设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107644206A (zh) * 2017-09-20 2018-01-30 深圳市晟达机械设计有限公司 一种道路异常行为动作检测装置
CN107826118A (zh) * 2017-11-01 2018-03-23 南京阿尔特交通科技有限公司 一种判别异常驾驶行为的方法及装置
CN108932843A (zh) * 2018-08-06 2018-12-04 百度在线网络技术（北京）有限公司 用于生成信息的方法和装置
US10497258B1 (en) * 2018-09-10 2019-12-03 Sony Corporation Vehicle tracking and license plate recognition based on group of pictures (GOP) structure
CN110992677A (zh) * 2019-11-20 2020-04-10 北方工业大学 一种应对通信异常的智能网联汽车编队控制方法及系统

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105774800B (zh) * 2016-03-28 2018-06-26 清华大学 一种混合车辆队列中车辆间的碰撞缓解方法及装置
US11082511B2 (en) * 2016-12-21 2021-08-03 Allstate Solutions Private Limited Highway detection system for generating customized notifications
US10482767B2 (en) * 2016-12-30 2019-11-19 Bendix Commercial Vehicle Systems Llc Detection of extra-platoon vehicle intermediate or adjacent to platoon member vehicles
US10936917B2 (en) * 2017-01-31 2021-03-02 Verizon Connect Ireland Limited System and method for detecting and classifying recurrent stops of a vehicle fleet
CN107609633B (zh) * 2017-05-03 2020-08-14 同济大学 车联网复杂网络中基于深度学习的车辆行驶影响因素的位置预测模型构造方法
CN108986471B (zh) * 2018-06-22 2020-08-21 长安大学 混合交通条件下交叉口车辆引导方法
EP3614353B1 (en) * 2018-08-23 2022-12-21 Volkswagen Aktiengesellschaft Apparatuses, methods and computer programs for a leading vehicle of a group of vehicles and for a vehicle
CN111200799B (zh) * 2018-11-20 2021-06-15 华为技术有限公司 一种车联网的异常行为检测方法、装置和系统
CN109947081B (zh) * 2019-03-25 2020-12-01 钛马信息网络技术有限公司 网联车辆控制方法及装置
CN110400023A (zh) * 2019-07-31 2019-11-01 北京三快在线科技有限公司 一种轨迹规划算法的切换方法及装置
CN110503743B (zh) * 2019-08-12 2021-09-14 浙江吉利汽车研究院有限公司 一种自动驾驶车辆的异常检测方法、装置和设备
CN110784825B (zh) * 2019-08-26 2021-07-13 腾讯科技（深圳）有限公司 车辆行驶轨迹的生成方法、装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107644206A (zh) * 2017-09-20 2018-01-30 深圳市晟达机械设计有限公司 一种道路异常行为动作检测装置
CN107826118A (zh) * 2017-11-01 2018-03-23 南京阿尔特交通科技有限公司 一种判别异常驾驶行为的方法及装置
CN108932843A (zh) * 2018-08-06 2018-12-04 百度在线网络技术（北京）有限公司 用于生成信息的方法和装置
US10497258B1 (en) * 2018-09-10 2019-12-03 Sony Corporation Vehicle tracking and license plate recognition based on group of pictures (GOP) structure
CN110992677A (zh) * 2019-11-20 2020-04-10 北方工业大学 一种应对通信异常的智能网联汽车编队控制方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4145340A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115223357A (zh) * 2022-04-07 2022-10-21 港珠澳大桥管理局 一种交通信息处理系统、方法、装置和计算机设备
CN114841679A (zh) * 2022-06-29 2022-08-02 陕西省君凯电子科技有限公司 车辆行驶数据的智能管理系统
CN114841679B (zh) * 2022-06-29 2022-10-18 陕西省君凯电子科技有限公司 车辆行驶数据的智能管理系统
CN117875813A (zh) * 2024-03-11 2024-04-12 北京中交兴路信息科技股份有限公司 行驶轨迹的可信度分析方法、装置、存储介质及电子设备

Also Published As

Publication number Publication date
CN112673406A (zh) 2021-04-16
CN112673406B (zh) 2022-02-18
EP4145340A4 (en) 2023-06-21
EP4145340A1 (en) 2023-03-08

Similar Documents

Publication Publication Date Title
WO2021237745A1 (zh) 一种辨识车辆列队中异常车辆参数的方法和终端设备
CN111123933B (zh) 车辆轨迹规划的方法、装置、智能驾驶域控制器和智能车
CN108495330B (zh) 一种车-车信息交互通信的碰撞预警可靠性测试方法
US11984028B2 (en) Method, device and electronic equipment for vehicle cooperative decision-making and computer storage medium
Khayatian et al. RIM: Robust intersection management for connected autonomous vehicles
JP7303307B2 (ja) 自動運転車両隊列の隊列編入方法、装置及びシステム
JP2018534693A (ja) 車両の車線変更のために２車両間の交通空隙を特定する方法および制御システム
WO2019030916A1 (ja) 車線情報管理方法、走行制御方法及び車線情報管理装置
Mo et al. Simulation and analysis on overtaking safety assistance system based on vehicle-to-vehicle communication
CN107045794B (zh) 路况处理方法及装置
CN108153854A (zh) 弯道分类方法、路侧单元、车载终端及电子设备
CN112712729B (zh) 预测运动轨迹的方法和系统
US20210056854A1 (en) Hierarchical ai assisted safe and efficient platooning
US20230073151A1 (en) Early detection of abnormal driving behavior
CN114248799A (zh) 车辆到一切消息的不当行为检测
CN104875740B (zh) 用于管理跟随空间的方法、主车辆以及跟随空间管理单元
US20220327935A1 (en) Systems and methods for cooperatively managing mixed traffic at an intersection
Wang et al. Cluster-wise cooperative eco-approach and departure application along signalized arterials
Dao et al. A strategy for optimisation of cooperative platoon formation
KR102157084B1 (ko) 차량의 군집 형성 장치 및 그 방법
KR102062595B1 (ko) 군집주행 차량의 에코드라이빙 제어 방법 및 장치
US11877217B2 (en) Message processing for wireless messages based on value of information
CN116552559A (zh) 在自动驾驶系统基于融合数据检测异常行为的系统和方法
CN112399347B (zh) 一种报文处理方法及设备
Stanchev et al. Autonomous cars. History. State of art. Research problems

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: 20937270

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020937270

Country of ref document: EP

Effective date: 20221201

NENP Non-entry into the national phase

Ref country code: DE