WO2023001168A1 - 障碍物的轨迹预测方法、装置、电子设备及存储介质 - Google Patents

障碍物的轨迹预测方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2023001168A1
WO2023001168A1 PCT/CN2022/106677 CN2022106677W WO2023001168A1 WO 2023001168 A1 WO2023001168 A1 WO 2023001168A1 CN 2022106677 W CN2022106677 W CN 2022106677W WO 2023001168 A1 WO2023001168 A1 WO 2023001168A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
target obstacle
trajectory
target
lane
Prior art date
Application number
PCT/CN2022/106677
Other languages
English (en)
French (fr)
Inventor
李宇寂
王相玲
何柳
尚秉旭
王洪峰
Original Assignee
中国第一汽车股份有限公司
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 中国第一汽车股份有限公司 filed Critical 中国第一汽车股份有限公司
Publication of WO2023001168A1 publication Critical patent/WO2023001168A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/06—Road conditions

Definitions

  • the embodiments of the present application relate to the technical field of automatic driving, for example, to a method, device, electronic device, and storage medium for trajectory prediction of obstacles.
  • an autonomous vehicle In a complex traffic environment, if an autonomous vehicle wants to drive safely and quickly, it must not only plan its own path, but also dynamically plan the next driving action according to the real-time changes of surrounding obstacles, and how to accurately predict surrounding obstacles
  • the future trajectory of motion becomes particularly important.
  • the types of obstacles are complex, the density is high, and the gaps are small, which is not conducive to the accurate prediction of the surrounding environment by the vehicle, and it is prone to the situation that the accuracy of the predicted trajectory is not high, which greatly affects the automatic driving.
  • the vehicle plans its own driving trajectory, which cannot achieve efficient, stable and safe driving, and needs to be improved urgently.
  • the present application provides an obstacle trajectory prediction method, device, electronic equipment, and storage medium, so as to achieve more targeted obstacle trajectory prediction and improve prediction accuracy.
  • the embodiment of the present application provides a trajectory prediction method for obstacles, the method comprising:
  • the auxiliary reference information includes map information and positioning information
  • the characteristic information of the target obstacle includes at least the type and historical movement information of the target obstacle;
  • an obstacle trajectory prediction device which includes:
  • the perception information acquisition module is configured to acquire the perception information and auxiliary reference information of the vehicle;
  • the auxiliary reference information includes map information and positioning information;
  • a characteristic information determination module configured to determine characteristic information of the target obstacle according to the perception information and the auxiliary reference information; the characteristic information of the target obstacle includes at least the type of the target obstacle and historical motion information;
  • the trajectory prediction module is configured to predict the trajectory of the target obstacle according to the type of the target obstacle and historical movement information.
  • the embodiment of the present application also provides an electronic device, the electronic device includes:
  • memory device configured to store the program
  • the processor When the program is executed by the processor, the processor is enabled to implement the obstacle trajectory prediction method described in any embodiment of the present application.
  • the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the obstacle trajectory prediction method as described in any embodiment of the present application is implemented.
  • FIG. 1A is a flow chart of an obstacle trajectory prediction method provided in Embodiment 1 of the present application.
  • FIG. 1C is a schematic diagram of the predicted trajectory of pedestrians provided by the embodiment of the present application.
  • FIG. 2A is a flowchart of an obstacle trajectory prediction method provided in Embodiment 2 of the present application.
  • Fig. 2B is a schematic diagram of the predicted trajectory under the vehicle lane keeping condition provided by the embodiment of the present application.
  • FIG. 2C is a schematic diagram of the predicted trajectory of the motor vehicle under the lane-changing condition provided by the embodiment of the present application.
  • Figure 2D is a schematic diagram of the predicted track of a non-motor vehicle provided in the embodiment of the present application.
  • FIG. 3 is a structural block diagram of an obstacle trajectory prediction device provided in Embodiment 3 of the present application.
  • FIG. 4 is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present application.
  • FIG. 1A is a flow chart of an obstacle trajectory prediction method provided in Embodiment 1 of the present application. This embodiment is applicable to situations where an autonomous vehicle predicts the trajectory of surrounding obstacles, especially in complex traffic environments.
  • the method can be executed by the obstacle trajectory prediction device provided in the embodiment of the present application, and the device can be realized by at least one of software and hardware, and can be integrated on an electronic device.
  • the method for predicting the trajectory of an obstacle may include the following steps:
  • auxiliary reference information includes map information and positioning information.
  • Detection equipment such as cameras, lidars, and millimeter-wave radars deployed on self-driving vehicles can sense the surrounding environment of the vehicle through the deployed detection equipment, and can obtain perception information.
  • the perception information is the perception information of the sensor at the vehicle end, mainly the position, speed and acceleration of the traffic participant relative to the own vehicle, etc., and the traffic participant includes the obstacle in this embodiment.
  • Auxiliary reference information is used to predict the trajectory of target obstacles, including map information and positioning information.
  • the map information provides vehicles with rich road information, including information such as the coordinate position of the lane, the width of the lane, the heading of the lane, the restriction of the lane, and the upstream and downstream connections. Map information can be obtained through the Internet of Vehicles, or through other related methods in the field.
  • the positioning information includes the coordinate position of the vehicle itself.
  • Perceptual information and auxiliary reference information belong to the prior information of the target obstacle movement, which can be used to predict the trajectory of the target obstacle. Therefore, in order to predict the trajectory of the target obstacle, it is necessary to obtain the vehicle's perception information and auxiliary reference information, which includes map information and positioning information. That is to say, in order to predict the trajectory of the target obstacle, it is necessary to obtain the perception information, map information and positioning information of the vehicle.
  • the feature information of the target obstacle includes at least a type of the target obstacle and historical motion information.
  • the type of the target obstacle in the feature information of the target obstacle is used to classify the target obstacle, and different trajectory prediction methods are used for different types of target obstacles.
  • the type of the target obstacle may include pedestrians, and may also include vehicles.
  • vehicles may be further divided into motor vehicles and non-motor vehicles.
  • the historical motion information includes the motion information such as the heading angle, velocity and acceleration of the target obstacle before the current moment.
  • the movement characteristics of different types of target obstacles are very different. Motor vehicles usually need to keep moving in the center of the lane, non-motor vehicles have a certain degree of randomness in movement, but are usually in the lane, and pedestrians move more randomly.
  • the target obstacle is inside or outside the map road, the corresponding prediction basis changes.
  • the movement of target obstacles outside the map road is very random, and there is no map information as a reference; the movement trajectory of target obstacles inside the map road usually conforms to the constraints of the map lane, and the map lane information is used as a reference. Therefore, it is very necessary to use different trajectory prediction methods for different target obstacles.
  • the feature information of the target obstacle is determined according to the acquired perception information and auxiliary reference information, so as to determine a trajectory prediction method suitable for the target obstacle.
  • S130 Predict the movement trajectory of the target obstacle according to the type of the target obstacle and historical movement information.
  • the prediction basis when predicting the trajectory of the target obstacle, it can be judged whether the target obstacle is on the map road or not.
  • the prediction basis can be the type and historical motion information of the target obstacle; based on the judgment result of the target obstacle outside the map road, the prediction basis can be the historical motion information of the target obstacle.
  • the movement of the target obstacle has certain regularity and continuity. Motor vehicles and non-motor vehicles will continue to move forward along the historical trajectory. Movement of the face in the direction. Therefore, the short-term future trajectory of the target obstacle can be predicted based on the historical movement information of the target obstacle for a period of time.
  • the trajectory of the target obstacle can be predicted according to the type of the target obstacle and historical motion information, including: determining whether the target obstacle is located on the map according to the position of the target obstacle in the historical motion information On the road in the information; based on the judgment result that the target obstacle is on the road in the map information, the trajectory of the target obstacle can be predicted according to the vehicle type and historical motion information to which the target obstacle belongs; based on the target obstacle is not in the map information Based on the judgment results on the road, the trajectory of the target obstacle can be predicted according to the historical movement information of the target obstacle.
  • FIG. 1B it is a schematic diagram of the predicted trajectory of the vehicle.
  • the historical trajectory data curve fitting method can be used to obtain its motion trajectory equation, and the data extrapolation of the fitted trajectory equation can be obtained by combining the current speed information, heading angle information and acceleration information to obtain the possible future movement track.
  • the trajectory of the target obstacle can be predicted according to the current position, heading angle and speed of the target obstacle in the historical motion information. Due to the large randomness of pedestrian movement, map information cannot provide effective reference information. Therefore, the pedestrian trajectory prediction within the map and the pedestrian trajectory prediction outside the map use the same method. Because pedestrians’ movement is very random, it is of little significance to fit their historical trajectories. Therefore, we can combine the speed information at the current moment and perform linear data extrapolation in the direction of the heading angle to obtain the predicted trajectory, as shown in Figure 1C shown.
  • the auxiliary reference information includes map information and positioning information; according to the perception information and auxiliary reference information, the characteristic information of the target obstacle is determined; the characteristic information of the target obstacle includes at least The type of target obstacle and historical motion information; predict the trajectory of the target obstacle according to the type of target obstacle and historical motion information.
  • the technical solution of the embodiment of the present application combines high-precision map information to classify target obstacles in multiple dimensions, and applies different prediction methods for different types of target obstacles, making the trajectory prediction of target obstacles more targeted , improve the accuracy of trajectory prediction, and provide a new idea for trajectory prediction of obstacles.
  • FIG. 2A is a flow chart of an obstacle trajectory prediction method provided in Embodiment 2 of the present application. The method is modified on the basis of the above embodiment, and an introduction is given where the target obstacle is a vehicle.
  • the method includes:
  • auxiliary reference information includes map information and positioning information.
  • the characteristic information of the target obstacle includes at least a type of the target obstacle and historical movement information.
  • S230 If the target obstacle is a vehicle, determine whether the target obstacle is located on the road in the map information according to the position of the target obstacle in the historical motion information. Based on the judgment result that the target obstacle is located on the road in the map information, execute S240A; based on the judgment result that the target obstacle is not on the road in the map information, execute S240B.
  • Map information provides a wealth of road information for self-driving vehicles, and the trajectories of obstacles moving in the map usually conform to the constraints of the lanes in the map; however, obstacles outside the map (such as non-motorized vehicles outside the curb) , Pedestrians, etc.) movement is very random, and the information reference of the high-precision map cannot be obtained. Therefore, obstacles need to be divided into on-map and off-map according to their locations.
  • S240A Predict the movement trajectory of the target obstacle according to the vehicle type and historical movement information to which the target obstacle belongs.
  • the movement of obstacles has certain regularity and continuity, and the vehicle will continue to move forward along the historical trajectory. Therefore, the short-term trajectory in the future can be predicted based on the historical movement information of the obstacle.
  • polynomial fitting can be performed based on the motor vehicle position, heading angle, speed, acceleration, and centerline information of the target lane at the current moment in the historical motion information to obtain the predicted trajectory;
  • the final coordinate point of the predicted trajectory is on the centerline of the target lane.
  • the target lane centerline information of vehicle movement has great reference significance.
  • the centerline of the target lane needs to be determined.
  • the movement of non-motor vehicles has a certain degree of randomness, and usually does not move along the centerline of the lane, but it will move in the current lane, so the centerline of the lane it belongs to can provide reference information for trajectory prediction.
  • the non-motor vehicle position, heading angle, speed, acceleration, and lane centerline information at the current moment in the historical motion information can be used to maintain the lateral deviation from the lane centerline.
  • polynomial fitting is carried out to obtain the predicted trajectory. As shown in Figure 2D, the predicted trajectory maintains a constant lateral deviation from the reference lane centerline.
  • S240B Predict the movement track of the target obstacle according to the historical movement information of the target obstacle.
  • the movement of obstacles has certain regularity and continuity, and motor vehicles and non-motor vehicles will continue to move forward along the historical track. Therefore, the trajectory of obstacles in a short period of time in the future can be predicted through the statistics of the historical trajectory of obstacles for a period of time.
  • predicting the trajectory of the target obstacle based on the historical movement information of the target obstacle includes: performing trajectory data fitting on the historical movement information of the target obstacle to obtain the trajectory curve equation of the target obstacle; based on the trajectory curve equation , perform data extrapolation to predict the trajectory of the target obstacle.
  • This embodiment gives an introduction to the situation that the obstacle is a vehicle. First, it is judged whether the vehicle is on the road in the map information, and the vehicles on the road are classified, and the corresponding prediction method is adopted to make the trajectory prediction of the obstacle more targeted. can improve the accuracy of obstacle trajectory prediction.
  • Fig. 3 is a schematic structural diagram of an obstacle trajectory prediction device provided in Embodiment 3 of the present application.
  • the device is suitable for implementing the obstacle trajectory prediction method provided in the embodiment of the present application, and can predict the obstacle trajectory more clearly. Targeted, improve the accuracy of forecasting.
  • the device includes a perception information acquisition module 310 , a feature information determination module 320 and a trajectory prediction module 330 .
  • the sensing information acquisition module 310 is configured to acquire sensing information and auxiliary reference information of the vehicle;
  • the auxiliary reference information includes map information and positioning information;
  • the characteristic information determining module 320 is configured to determine characteristic information of the target obstacle according to the perception information and auxiliary reference information; the characteristic information of the target obstacle includes at least the type and historical motion information of the target obstacle;
  • the trajectory prediction module 330 is configured to predict the trajectory of the target obstacle according to the type of the target obstacle and historical movement information.
  • the sensory information and auxiliary reference information of the vehicle are obtained; the auxiliary reference information includes map information and positioning information; according to the sensory information and auxiliary reference information, the characteristic information of the target obstacle is determined; the characteristic information of the target obstacle includes at least the target obstacle The type of object and historical motion information; according to the type of target obstacle and historical motion information, predict the trajectory of the target obstacle, combined with high-precision map information, classify obstacles in multiple dimensions, and apply to different types of obstacles Different prediction methods make the trajectory prediction of obstacles more targeted, improve the accuracy of obstacle trajectory prediction, and provide a new idea for obstacle trajectory prediction.
  • the trajectory prediction module 330 includes a vehicle trajectory prediction submodule and a pedestrian trajectory prediction submodule.
  • the vehicle trajectory prediction sub-module includes: a position judgment unit and a trajectory prediction unit.
  • the position judging unit is configured to determine whether the target obstacle is located on the road in the map information according to the position of the target obstacle in the historical motion information;
  • the trajectory prediction unit is configured to locate the target obstacle in the map information based on According to the judgment result on the road of the target obstacle, the trajectory of the target obstacle is predicted according to the vehicle type and historical motion information to which the target obstacle belongs; based on the judgment result that the target obstacle is not on the road in the map information, according to the Historical motion information to predict the trajectory of the target obstacle.
  • the above-mentioned prediction of the trajectory of the target obstacle based on the historical movement information of the target obstacle includes:
  • the above trajectory prediction unit includes: a motor vehicle trajectory prediction subunit and a non-motor vehicle trajectory prediction subunit.
  • the motor vehicle trajectory prediction subunit is configured to use the motor vehicle position, heading angle, speed, acceleration and target lane centerline information at the current moment in the historical motion information when the vehicle type to which the target obstacle belongs is a motor vehicle, Perform polynomial fitting to obtain the predicted trajectory; wherein, the final coordinate point of the predicted trajectory is on the centerline of the target lane.
  • the non-motor vehicle trajectory prediction subunit is set under the condition that the vehicle type to which the target obstacle belongs is a non-motor vehicle, based on the position, heading angle, speed, acceleration and lane centerline information of the non-motor vehicle at the current moment in the historical motion information , under the premise of keeping the lateral offset from the centerline of the lane unchanged, perform polynomial fitting to obtain the predicted trajectory.
  • determine the centerline of the target lane including:
  • the centerline of the target lane is determined to be the centerline of the current lane and the centerline of the lane to be turned;
  • the centerline of the target lane is determined to be the centerline of the current lane and the centerline of the lane to be turned.
  • the obstacle trajectory prediction device provided in the embodiments of the present application can execute the obstacle trajectory prediction method provided in any embodiment of the present application, and has corresponding functional modules and beneficial effects for executing the method.
  • FIG. 4 is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present application.
  • FIG. 4 shows a block diagram of an exemplary electronic device 12 suitable for implementing embodiments of the present application.
  • the electronic device 12 shown in FIG. 4 is an example.
  • electronic device 12 takes the form of a general-purpose computing device.
  • Components of electronic device 12 may include one or more processors or processing units 16, system memory 28, bus 18 connecting various system components including system memory 28 and processing unit 16.
  • Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures.
  • bus structures include, for example, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MCA) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) ) Local bus and Peripheral Component Interconnect (PCI) bus.
  • ISA Industry Standard Architecture
  • MCA Micro Channel Architecture
  • VESA Video Electronics Standards Association
  • PCI Peripheral Component Interconnect
  • Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12 and include both volatile and nonvolatile media, removable and non-removable media.
  • System memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32 .
  • Electronic device 12 may include other removable/non-removable, volatile/nonvolatile computer system storage media.
  • storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"), and may be Disk drives that read and write, and optical drives that read and write to removable non-volatile optical discs. In these cases, each drive may be connected to bus 18 via one or more data media interfaces.
  • System memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present application.
  • a program/utility 40 may be stored, for example, in system memory 28 as a set (at least one) of program modules 42, such program modules 42 including an operating system, one or more application programs, other program modules, and program data, which Each or some combination of the examples may include the implementation of a network environment.
  • the program module 42 generally executes the functions or methods in the embodiments described in this application.
  • the electronic device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, pointing device, display 24, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 12, and/or communicate with Any device (eg, network card, modem, etc.) that enables the electronic device 12 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interface 22 .
  • the electronic device 12 can also communicate with one or more networks (such as a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN) and/or a public network, such as the Internet) through the network adapter 20.
  • networks such as a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN) and/or a public network, such as the Internet
  • network adapter 20 communicates with other modules of electronic device 12 via bus 18 .
  • other hardware and/or software modules may be used in conjunction with the electronic device 12, including: microcode, device drivers, redundant processing units, external disk drive arrays, and disk arrays (Redundant Arrays of Independent Disks, RAID) system , tape drives, and data backup storage systems.
  • the processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28 , for example, implementing the obstacle trajectory prediction method provided by the embodiment of the present application.
  • Embodiment 5 of the present application also provides a computer-readable storage medium, on which a computer program is stored.
  • the program is executed by a processor, the trajectory prediction method of an obstacle as provided in any embodiment of the present application is implemented.
  • the computer storage medium in the embodiments of the present application may use any combination of one or more computer-readable media.
  • the computer readable medium may be a computer readable signal medium or a computer readable storage medium.
  • a computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof.
  • Computer-readable storage media include: electrical connections with one or more conductors, portable computer disks, hard disks, random-access memory (RAM), read-only memory (Read-Only Memory, ROM), erasable programmable read-only Memory (Erasable Programmable Read-Only Memory, EPROM or flash memory), optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above .
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer readable signal medium may include a data signal carrying computer readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. .
  • the program code contained on the computer readable medium may be transmitted by any appropriate medium, including wireless, electric wire, optical cable, radio frequency (Radio Frequency Identification, RF), etc., or any suitable combination of the above.
  • any appropriate medium including wireless, electric wire, optical cable, radio frequency (Radio Frequency Identification, RF), etc., or any suitable combination of the above.
  • Computer program codes for performing the operations of the present application may be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional Procedural Programming Language - such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer may be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g. via the Internet using an Internet Service Provider). .
  • LAN local area network
  • WAN wide area network
  • Internet Service Provider e.g. via the Internet using an Internet Service Provider

Landscapes

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

Abstract

本申请公开了一种障碍物的轨迹预测方法、装置、电子设备及存储介质，该方法包括：获取车辆的感知信息和辅助参考信息；所述辅助参考信息包括地图信息和定位信息；根据所述感知信息和所述辅助参考信息，确定目标障碍物的特征信息；所述目标障碍物的特征信息至少包括目标障碍物的类型和历史运动信息；根据所述目标障碍物的类型和历史运动信息，预测所述目标障碍物的运动轨迹。

Description

障碍物的轨迹预测方法、装置、电子设备及存储介质
本申请要求在2021年07月20日提交中国专利局、申请号为202110820872.2的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及自动驾驶技术领域，例如涉及一种障碍物的轨迹预测方法、装置、电子设备及存储介质。
背景技术
随着互联网和智能终端技术的发展，自动驾驶车辆逐渐走入人们的视野，为人们的生活提供了极大的便利。
在复杂的交通环境中，自动驾驶车辆要想安全快速行驶，不光要规划好自身的路径，更要根据周围障碍物的实时变化，动态的规划接下来的驾驶动作，如何准确的预测周围障碍物的未来运动轨迹变得尤其重要。在城市的复杂道路状况下，障碍物种类复杂、密度高、间隙小，不利于自车对周边环境的准确预测，容易出现预测的运动轨迹准确性不高的情况，进而极大的影响自动驾驶车辆规划自己的行驶轨迹，无法实现高效、平稳、安全地行驶，亟需改进。
发明内容
本申请提供一种障碍物的轨迹预测方法、装置、电子设备及存储介质，以实现对障碍物的轨迹预测更有针对性，提高预测的准确性。
第一方面，本申请实施例提供了一种障碍物的轨迹预测方法，该方法包括：
获取车辆的感知信息和辅助参考信息；所述辅助参考信息包括地图信息和定位信息；
根据所述感知信息和所述辅助参考信息，确定目标障碍物的特征信息；所述目标障碍物的特征信息至少包括目标障碍物的类型和历史运动信息；
根据所述目标障碍物的类型和历史运动信息，预测所述目标障碍物的运动轨迹。
第二方面，本申请实施例还提供了一种障碍物的轨迹预测装置，该装置包括：
感知信息获取模块，被设置为获取车辆的感知信息和辅助参考信息；所述辅助参考信息包括地图信息和定位信息；
特征信息确定模块，被设置为根据所述感知信息和所述辅助参考信息，确定目标障碍物的特征信息；所述目标障碍物的特征信息至少包括目标障碍物的类型和历史运动信息；
轨迹预测模块，被设置为根据所述目标障碍物的类型和历史运动信息，预测所述目标障碍物的运动轨迹。
第三方面，本申请实施例还提供了一种电子设备，该电子设备包括：
处理器；
存储装置，被设置为存储程序，
当所述程序被所述处理器执行，使得所述处理器实现本申请任意实施例所述的障碍物的轨迹预测方法。
第四方面，本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请任意实施例所述的障碍物的轨迹预测方法。
附图说明
图1A为本申请实施例一提供的一种障碍物的轨迹预测方法的流程图；
图1B为本申请实施例提供的车辆的预测轨迹示意图；
图1C为本申请实施例提供的行人的预测轨迹示意图；
图2A是本申请实施例二提供的一种障碍物的轨迹预测方法的流程图；
图2B为本申请实施例提供的机动车车道保持工况下的预测轨迹示意图；
图2C为本申请实施例提供的机动车变道工况下的预测轨迹示意图；
图2D为本申请实施例提供的非机动车的预测轨迹示意图；
图3是本申请实施例三提供的一种障碍物的轨迹预测装置结构框图；
图4是本申请实施例四提供的一种电子设备的结构示意图。
具体实施方式
下面结合附图和实施例对本申请作说明。可以理解的是，此处所描述的实 施例用于解释本申请。另外还需要说明的是，为了便于描述，附图中仅示出了与本申请相关的部分而非全部结构。
实施例一
图1A为本申请实施例一提供的一种障碍物的轨迹预测方法的流程图，本实施例可适用于自动驾驶车辆预测周围障碍物运动轨迹的情况，尤其适用于复杂的交通环境。该方法可以由本申请实施例提供的障碍物的轨迹预测装置来执行，该装置可以采用软件和硬件中的至少一种方式实现，并可集成在电子设备上。
在一实施例中，如图1A所示，本申请实施例提供的障碍物的轨迹预测方法，可以包括如下步骤：
S110、获取车辆的感知信息和辅助参考信息；辅助参考信息包括地图信息和定位信息。
在自动驾驶车辆上部署的摄像头、激光雷达、毫米波雷达等探测设备，通过部署的探测设备对车辆周边环境进行感知，可以得到感知信息。感知信息是车端传感器的感知信息，主要为交通参与者相对自车的位置、速度和加速度等，交通参与者包括本实施例中的障碍物。辅助参考信息，作为感知信息的补充，用于预测目标障碍物的运动轨迹，包括地图信息和定位信息。其中，地图信息为车辆提供丰富的道路信息，包括车道的坐标位置、车道宽度、车道航向、车道限制及上下游连接等信息。地图信息可以通过车联网获取，也可以通过本领域其他相关方式获取。定位信息包括车辆自身的坐标位置。
感知信息和辅助参考信息，都属于目标障碍物运动的先验信息，可以用于预测目标障碍物的运动轨迹。因此，为了预测目标障碍物的运动轨迹，需要获取车辆的感知信息和辅助参考信息，辅助参考信息包括地图信息和定位信息。也就是说，为了预测目标障碍物的运动轨迹，需要获取车辆的感知信息、地图信息和定位信息。
S120、根据感知信息和辅助参考信息，确定目标障碍物的特征信息；目标障碍物的特征信息至少包括目标障碍物的类型和历史运动信息。
本实施例中，目标障碍物的特征信息中的目标障碍物的类型，用于对目标障碍物进行分类，针对不同分类的目标障碍物，采用不同的轨迹预测方法。示例性的，目标障碍物的类型可以包括行人，也可以包括车辆，可选的，车辆还可以分为机动车和非机动车。历史运动信息则包括目标障碍物在当前时刻之前的运动航向角、速度和加速度等运动信息。
不同类型目标障碍物的运动特性有着很大的差别，机动车通常需要保持在车道中心运动，非机动车运动有一定随机性但通常会在车道内，行人的运动随 机性更大。另外，目标障碍物处于地图道路内外时，对应的预测依据有所变化。地图道路外的目标障碍物，运动随机性很大，没有地图信息作为参考；地图道路内的目标障碍物，其运动轨迹通常符合地图车道的约束，有地图的车道信息作为参考。因此，对不同的目标障碍物分别用不同的轨迹预测方法是非常必要的。
本实施例中，根据获取的感知信息和辅助参考信息，确定目标障碍物的特征信息，从而确定适用于目标障碍物的轨迹预测方法。
S130、根据目标障碍物的类型和历史运动信息，预测目标障碍物的运动轨迹。
由于目标障碍物处于地图内和地图外时，对应的预测依据有区别，在本实施例一个可选的实施方式中，在预测目标障碍物的运动轨迹时，可以判断目标障碍物是否在地图道路内。基于目标障碍物在地图道路内的判断结果，预测依据可以为目标障碍物的类型和历史运动信息；基于目标障碍物在地图道路外的判断结果，预测依据可以为目标障碍物的历史运动信息。
由于不同类型目标障碍物的运动特性有很大的差别，如机动车通常运动速度较快，并且会沿着车道中心线运动；非机动车通常运动速度较慢，有一定随机性，但会在车道内；行人的运动速度很慢，但随机性很大。为了有针对性的进行运动轨迹预测，提高预测的准确性，在本实施例另一个可选的实施方式中，可以对不同类型的目标障碍物采用不同的预测方法。
在本实施例又一可选的实施方式中，为了有针对性的进行轨迹预测，还可以依据地图内外和目标障碍物类型对目标障碍物进行多维度的分类，从而按照更细化的类别，有针对性进行轨迹预测。
通常情况下，目标障碍物的运动有一定的规律性和延续性，机动车和非机动车会沿着历史轨迹继续向前，行人的运动随机性很大，但其短时间内通常会以当前面部朝向方向运动。因此，可以通过根据目标障碍物一段时间历史运动信息来预测其未来短时间的轨迹。
在目标障碍物为车辆的情况下，可以根据目标障碍物的类型和历史运动信息，预测目标障碍物的运动轨迹，包括：根据历史运动信息中目标障碍物的位置，确定目标障碍物是否位于地图信息中的道路上；基于目标障碍物位于地图信息中的道路上的判断结果，可以根据目标障碍物所属的车辆类型和历史运动信息，预测目标障碍物的运动轨迹；基于目标障碍物不在地图信息中的道路上的判断结果，可以根据目标障碍物的历史运动信息，预测目标障碍物的运动轨迹。
如图1B所示，为车辆的预测轨迹示意图。对于车辆，可以采用历史轨迹数据曲线拟合的方法来获得其运动轨迹方程，并结合当前时刻的速度信息、航向角信息及加速度信息对拟合的轨迹方程进行数据外推来获得未来的可能运动轨迹。
在目标障碍物类型为行人的情况下，可以根据历史运动信息中目标障碍物在当前时刻的位置、航向角和速度预测目标障碍物的运动轨迹。由于行人运动的随机性很大，地图信息无法提供有效的参考信息，因此，地图内的行人轨迹预测与地图外的行人轨迹预测采用相同的方法。由于行人的运动随机性很大，对其历史轨迹的拟合参考意义不大，因此，可以结合当前时刻的速度信息，在航向角的方向上进行直线数据外推，获得预测轨迹，如图1C所示。
本实施例中，通过获取车辆的感知信息和辅助参考信息；辅助参考信息包括地图信息和定位信息；根据感知信息和辅助参考信息，确定目标障碍物的特征信息；目标障碍物的特征信息至少包括目标障碍物的类型和历史运动信息；根据目标障碍物的类型和历史运动信息，预测目标障碍物的运动轨迹。本申请实施例的技术方案，结合了高精地图信息，将目标障碍物进行多维度的分类，针对不同类型的目标障碍物应用不同的预测方法，使得对目标障碍物的轨迹预测更有针对性，提高轨迹预测的准确性，为障碍物的轨迹预测提供了一种新思路。
实施例二
图2A为本申请实施例二提供的一种障碍物的轨迹预测方法的流程图，该方法在上述实施例的基础上进行改动，给出了目标障碍物为车辆的情况介绍。
在一实施例中，如图2A所示，该方法包括：
S210、获取车辆的感知信息和辅助参考信息；辅助参考信息包括地图信息和定位信息。
S220、根据感知信息和辅助参考信息，确定目标障碍物的特征信息；目标障碍物的特征信息至少包括目标障碍物的类型和历史运动信息。
S230、在目标障碍物为车辆的情况下，根据历史运动信息中目标障碍物的位置，确定目标障碍物是否位于地图信息中的道路上。基于目标障碍物位于地图信息中的道路上的判断结果，执行S240A；基于目标障碍物不在地图信息中的道路上的判断结果，执行S240B。
地图信息为自动驾驶车辆提供了丰富的道路信息，运动在地图内的障碍物其运动轨迹通常也会符合地图中车道的约束；但是在地图外的障碍物(如在马 路牙以外的非机动车、行人等)运动随机性很大，也无法得到高精地图的信息参考，因此需要将障碍物根据所处位置区分为地图内和地图外。
S240A、根据目标障碍物所属的车辆类型和历史运动信息，预测目标障碍物的运动轨迹。
通常情况下，障碍物的运动有一定的规律性和延续性，车辆会沿着历史轨迹继续向前动。因此，可以通过根据障碍物的历史运动信息来预测其未来短时间的轨迹。
不同类型的目标障碍物其运动特性有很大差别，如机动车通常运动速度较快，并且会沿着车道中心线运动；非机动车运动速度较慢，通常不会沿着车道中心线，但会在车道内运动；行人运动的速度很慢，但其随机性非常大，地图车道对其约束性很小。因此，针对不同类型的目标障碍物，设计不同的轨迹预测算法。
在目标障碍物所属的车辆类型为机动车的情况下，可以以历史运动信息中当前时刻的机动车位置、航向角、速度、加速度和目标车道中心线信息，进行多项式拟合，得到预测轨迹；预测轨迹的最终坐标点在目标车道中心线上。
机动车在车道内通常沿着车道中心线运动，即使当前时刻不处于车道中心线，未来的趋势也是沿着车道中心线，因此，车辆运动的目标车道中心线信息有很大的参考意义。可选的，在进行多项式拟合得到预测轨迹之前，需要确定目标车道中心线。如图2B所示，在机动车处于车道保持工况的情况下，确定目标车道中心线为当前所处车道中心线；如图2C所示，在机动车处于变道工况的情况下，确定目标车道中心线为当前所处车道中心线和待变车道的中心线；在机动车处于转弯工况的情况下，确定目标车道中心线为当前所处车道中心线和待转弯车道的中心线；在机动车处于掉头工况的情况下，确定目标车道中心线为当前所处车道中心线和待掉头车道的中心线。
非机动车的运动有一定的随机性，通常不会沿着车道中心线运动，但其会在当前车道内运动，因此所属车道中心线可以对轨迹预测提供参考信息。
在目标障碍物所属的车辆类型为非机动车的情况下，可以以历史运动信息中当前时刻的非机动车位置、航向角、速度、加速度和车道中心线信息，在保持与车道中心线横向偏移不变的前提下，进行多项式拟合，得到预测轨迹。如图2D所示，预测轨迹与参考车道中心线保持横向偏差不变。
S240B、根据目标障碍物的历史运动信息，预测目标障碍物的运动轨迹。
通常情况下，障碍物的运动有一定的规律性和延续性，机动车和非机动车会沿着历史轨迹继续向前。因此可以通过对障碍物一段时间历史轨迹的统计来 预测其未来短时间的轨迹。
可选的，根据目标障碍物的历史运动信息，预测目标障碍物的运动轨迹，包括：对目标障碍物的历史运动信息进行轨迹数据拟合，得到目标障碍物的轨迹曲线方程；基于轨迹曲线方程，进行数据外插来预测目标障碍物的运动轨迹。
本实施例给出了障碍物为车辆的情况介绍，首先判断车辆是否处于地图信息中的道路上，并对道路上的车辆分类，采用对应的预测方法，使得对障碍物的轨迹预测更有针对性，可以提高障碍物轨迹预测的准确性。
实施例三
图3是本申请实施例三所提供的一种障碍物的轨迹预测装置的结构示意图，该装置适用于执行本申请实施例提供的障碍物的轨迹预测方法，可以对障碍物的轨迹预测更有针对性，提高预测的准确性。如图3所示，该装置包括感知信息获取模块310、特征信息确定模块320和轨迹预测模块330。
本实施例中，感知信息获取模块310，被设置为获取车辆的感知信息和辅助参考信息；辅助参考信息包括地图信息和定位信息；
特征信息确定模块320，被设置为根据感知信息和辅助参考信息，确定目标障碍物的特征信息；目标障碍物的特征信息至少包括目标障碍物的类型和历史运动信息；
轨迹预测模块330，被设置为根据目标障碍物的类型和历史运动信息，预测目标障碍物的运动轨迹。
本实施例通过获取车辆的感知信息和辅助参考信息；辅助参考信息包括地图信息和定位信息；根据感知信息和辅助参考信息，确定目标障碍物的特征信息；目标障碍物的特征信息至少包括目标障碍物的类型和历史运动信息；根据目标障碍物的类型和历史运动信息，预测目标障碍物的运动轨迹，结合了高精地图信息，将障碍物进行多维度的分类，针对不同类型的障碍物应用不同的预测方法，使得对障碍物的轨迹预测更有针对性，提高障碍物轨迹预测的准确性，为障碍物的轨迹预测提供了一种新思路。
可选的，上述轨迹预测模块330包括车辆轨迹预测子模块和行人轨迹预测子模块。
可选的，车辆轨迹预测子模块包括：位置判断单元和轨迹预测单元。其中，位置判断单元，被设置为根据历史运动信息中目标障碍物的位置，确定目标障碍物是否位于地图信息中的道路上；轨迹预测单元，被设置为基于所述目标障 碍物位于地图信息中的道路上的判断结果，根据目标障碍物所属的车辆类型和历史运动信息，预测目标障碍物的运动轨迹；基于所述目标障碍物不在地图信息中的道路上的判断结果，根据目标障碍物的历史运动信息，预测目标障碍物的运动轨迹。
可选的，上述根据目标障碍物的历史运动信息，预测目标障碍物的运动轨迹，包括：
对目标障碍物的历史运动信息进行轨迹数据拟合，得到目标障碍物的轨迹曲线方程；
基于轨迹曲线方程，进行数据外插来预测目标障碍物的运动轨迹。
可选的，上述轨迹预测单元，包括：机动车轨迹预测子单元和非机动车轨迹预测子单元。其中，
机动车轨迹预测子单元，被设置为在目标障碍物所属的车辆类型为机动车的情况下，以历史运动信息中当前时刻的机动车位置、航向角、速度、加速度和目标车道中心线信息，进行多项式拟合，得到预测轨迹；其中，预测轨迹的最终坐标点在目标车道中心线上。
非机动车轨迹预测子单元，被设置在目标障碍物所属的车辆类型为非机动车的情况下，以历史运动信息中当前时刻的非机动车位置、航向角、速度、加速度和车道中心线信息，在保持与车道中心线横向偏移不变的前提下，进行多项式拟合，得到预测轨迹。
可选的，在进行多项式拟合之前，确定目标车道中心线，包括：
在机动车处于车道保持工况的情况下，确定目标车道中心线为当前所处车道中心线；
在机动车处于变道工况的情况下，确定目标车道中心线为当前所处车道中心线和待变车道的中心线；
在机动车处于转弯工况的情况下，确定目标车道中心线为当前所处车道中心线和待转弯车道的中心线；
在机动车处于掉头工况的情况下，确定目标车道中心线为当前所处车道中心线和待掉头车道的中心线。
本申请实施例所提供的障碍物的轨迹预测装置可执行本申请任意实施例所提供的障碍物的轨迹预测方法，具备执行方法相应的功能模块和有益效果。
实施例四
图4为本申请实施例四提供的一种电子设备的结构示意图。图4示出了适于用来实现本申请实施方式的示例性电子设备12的框图。图4显示的电子设备12是一个示例。
如图4所示，电子设备12以通用计算设备的形式表现。电子设备12的组件可以包括：一个或者多个处理器或者处理单元16，系统存储器28，连接不同系统组件(包括系统存储器28和处理单元16)的总线18。
总线18表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括工业标准体系结构(Industry Standard Architecture，ISA)总线，微通道体系结构(Micro Channel Architecture，MCA)总线，增强型ISA总线、视频电子标准协会(Video Electronics Standards Association，VESA)局域总线以及外围组件互连(Peripheral Component Interconnect，PCI)总线。
电子设备12典型地包括多种计算机系统可读介质。这些介质可以是任何能够被电子设备12访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。
系统存储器28可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(Random Access Memory，RAM)30和/或高速缓存存储器32。电子设备12可以包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统34可以用于读写不可移动的、非易失性磁介质(通常称为“硬盘驱动器”)，可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘读写的光盘驱动器。在这些情况下，每个驱动器可以通过一个或者多个数据介质接口与总线18相连。系统存储器28可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本申请各实施例的功能。
具有一组(至少一个)程序模块42的程序/实用工具40，可以存储在例如系统存储器28中，这样的程序模块42包括操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。程序模块42通常执行本申请所描述的实施例中的功能或方法。
电子设备12也可以与一个或多个外部设备14(例如键盘、指向设备、显示器24等)通信，还可与一个或者多个使得用户能与该电子设备12交互的设备通信，和/或与使得该电子设备12能与一个或多个其它计算设备进行通信的任何设备(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口22进行。并且，电子设备12还可以通过网络适配器20与一个或者多个网 络(例如局域网(Local Area Network，LAN)，广域网(Wide Area Network，WAN)和/或公共网络，例如因特网)通信。如图所示，网络适配器20通过总线18与电子设备12的其它模块通信。在一实施例中，可以结合电子设备12使用其它硬件和/或软件模块，包括：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、磁盘阵列(Redundant Arrays of Independent Disks，RAID)系统、磁带驱动器以及数据备份存储系统等。
处理单元16通过运行存储在系统存储器28中的程序，从而执行各种功能应用以及数据处理，例如实现本申请实施例所提供的障碍物的轨迹预测方法。
实施例五
本申请实施例五还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请任意申请实施例提供的障碍物的轨迹预测方法。
本申请实施例的计算机存储介质，可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质包括：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(Read-Only Memory，ROM)、可擦式可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括无线、电线、光缆、无线射频(Radio Frequency Identification，RF)等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言，诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络包括局域网(LAN)或广域网(WAN)连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。

Claims (10)

  1. 一种障碍物的轨迹预测方法，包括：
    获取车辆的感知信息和辅助参考信息；所述辅助参考信息包括地图信息和定位信息；
    根据所述感知信息和所述辅助参考信息，确定目标障碍物的特征信息；所述目标障碍物的特征信息至少包括目标障碍物的类型和历史运动信息；
    根据所述目标障碍物的类型和历史运动信息，预测所述目标障碍物的运动轨迹。
  2. 根据权利要求1所述的方法，其中，根据所述目标障碍物的类型和历史运动信息，预测所述目标障碍物的运动轨迹，包括：
    在所述目标障碍物为车辆的情况下，根据所述历史运动信息中目标障碍物的位置，确定所述目标障碍物是否位于地图信息中的道路上；
    基于所述目标障碍物位于地图信息中的道路上的判断结果，根据所述目标障碍物所属的车辆类型和历史运动信息，预测所述目标障碍物的运动轨迹；
    基于所述目标障碍物不在地图信息中的道路上的判断结果，根据所述目标障碍物的历史运动信息，预测所述目标障碍物的运动轨迹。
  3. 根据权利要求2所述的方法，其中，根据所述目标障碍物的历史运动信息，预测所述目标障碍物的运动轨迹，包括：
    对所述目标障碍物的历史运动信息进行轨迹数据拟合，得到所述目标障碍物的轨迹曲线方程；
    基于所述轨迹曲线方程，进行数据外插来预测所述目标障碍物的运动轨迹。
  4. 根据权利要求2所述的方法，其中，根据所述目标障碍物所属的车辆类型和历史运动信息，预测所述目标障碍物的运动轨迹，包括：
    在所述目标障碍物所属的车辆类型为机动车的情况下，以所述历史运动信息中当前时刻的机动车位置、航向角、速度、加速度和目标车道中心线信息，进行多项式拟合，得到预测轨迹；
    其中，所述预测轨迹的最终坐标点在目标车道中心线上。
  5. 根据权利要求4所述的方法，在进行多项式拟合之前，还包括：确定所述目标车道中心线；
    所述确定所述目标车道中心线，包括：
    在机动车处于车道保持工况的情况下，确定所述目标车道中心线为当前所处车道中心线；
    在机动车处于变道工况的情况下，确定所述目标车道中心线为当前所处车道中心线和待变车道的中心线；
    在机动车处于转弯工况的情况下，确定所述目标车道中心线为当前所处车道中心线和待转弯车道的中心线；
    在机动车处于掉头工况的情况下，确定所述目标车道中心线为当前所处车道中心线和待掉头车道的中心线。
  6. 根据权利要求2所述的方法，其中，根据所述目标障碍物所属的车辆类型和历史运动信息，预测所述目标障碍物的运动轨迹，包括：
    在所述目标障碍物所属的车辆类型为非机动车的情况下，以所述历史运动信息中当前时刻的非机动车位置、航向角、速度、加速度和车道中心线信息，在保持与所述车道中心线横向偏移不变的前提下，进行多项式拟合，得到预测轨迹。
  7. 根据权利要求1所述的方法，其中，根据所述目标障碍物的类型和历史运动信息，预测所述目标障碍物的运动轨迹，包括：
    在所述目标障碍物类型为行人的情况下，根据所述历史运动信息中目标障碍物在当前时刻的位置、航向角和速度预测目标障碍物的运动轨迹。
  8. 一种障碍物的轨迹预测装置，所述装置包括：
    感知信息获取模块，被设置为获取车辆的感知信息和辅助参考信息；所述辅助参考信息包括地图信息和定位信息；
    特征信息确定模块，被设置为根据所述感知信息和所述辅助参考信息，确定目标障碍物的特征信息；所述目标障碍物的特征信息至少包括目标障碍物的类型和历史运动信息；
    轨迹预测模块，被设置为根据所述目标障碍物的类型和历史运动信息，预测所述目标障碍物的运动轨迹。
  9. 一种电子设备，所述设备包括：
    处理器；
    存储装置，被设置为存储程序，
    当所述程序被所述处理器执行，使得所述处理器实现如权利要求1-7中任一所述的障碍物的轨迹预测方法。
  10. 一种计算机可读存储介质，所述存储介质上存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1-7中任一所述的障碍物的轨迹预 测方法。
PCT/CN2022/106677 2021-07-20 2022-07-20 障碍物的轨迹预测方法、装置、电子设备及存储介质 WO2023001168A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110820872.2A CN113335276A (zh) 2021-07-20 2021-07-20 障碍物的轨迹预测方法、装置、电子设备及存储介质
CN202110820872.2 2021-07-20

Publications (1)

Publication Number Publication Date
WO2023001168A1 true WO2023001168A1 (zh) 2023-01-26

Family

ID=77480059

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/106677 WO2023001168A1 (zh) 2021-07-20 2022-07-20 障碍物的轨迹预测方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN113335276A (zh)
WO (1) WO2023001168A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116309689A (zh) * 2023-05-17 2023-06-23 上海木蚁机器人科技有限公司 障碍物轨迹预测方法、装置、设备和介质
CN116734882A (zh) * 2023-08-14 2023-09-12 禾昆科技(北京)有限公司 车辆路径规划方法、装置、电子设备和计算机可读介质
CN117962932A (zh) * 2024-04-02 2024-05-03 福瑞泰克智能系统有限公司 障碍物的行驶轨迹生成方法、装置和存储介质及电子设备

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115246416B (zh) * 2021-05-13 2023-09-26 上海仙途智能科技有限公司 轨迹预测方法、装置、设备及计算机可读存储介质
CN113335276A (zh) * 2021-07-20 2021-09-03 中国第一汽车股份有限公司 障碍物的轨迹预测方法、装置、电子设备及存储介质
CN113963537A (zh) * 2021-10-19 2022-01-21 东软睿驰汽车技术（上海）有限公司 一种针对路口的车辆轨迹预测方法和相关装置
CN113815620B (zh) * 2021-10-26 2023-03-14 中国第一汽车股份有限公司 一种车辆安全行驶的评估方法、装置、设备及存储介质
CN115230688B (zh) * 2021-12-07 2023-08-25 上海仙途智能科技有限公司 障碍物轨迹预测方法、系统和计算机可读存储介质
CN114212110B (zh) * 2022-01-28 2024-05-03 中国第一汽车股份有限公司 障碍物轨迹预测方法、装置、电子设备及存储介质
CN115060280B (zh) * 2022-06-21 2023-07-25 湖南大学无锡智能控制研究院 一种车辆轨迹预测方法和装置
CN115148025B (zh) * 2022-06-28 2023-10-20 重庆长安汽车股份有限公司 一种交通目标轨迹预测方法及可读存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109885066A (zh) * 2019-03-26 2019-06-14 北京经纬恒润科技有限公司 一种运动轨迹预测方法及装置
CN111126362A (zh) * 2020-03-26 2020-05-08 北京三快在线科技有限公司 一种预测障碍物轨迹的方法及装置
CN111178286A (zh) * 2019-12-31 2020-05-19 智车优行科技（上海）有限公司 姿态轨迹预测方法、装置及电子设备
CN111982143A (zh) * 2020-08-11 2020-11-24 北京汽车研究总院有限公司 车辆及车辆路径规划方法、装置
US20200377085A1 (en) * 2019-06-03 2020-12-03 Realtime Robotics, Inc. Apparatus, methods and articles to facilitate motion planning in environments having dynamic obstacles
CN112233417A (zh) * 2020-09-17 2021-01-15 新石器慧义知行智驰(北京)科技有限公司 车辆轨迹预测方法、控制装置及无人车
CN113335276A (zh) * 2021-07-20 2021-09-03 中国第一汽车股份有限公司 障碍物的轨迹预测方法、装置、电子设备及存储介质

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010083314A (ja) * 2008-09-30 2010-04-15 Fuji Heavy Ind Ltd 車両の運転支援装置
DE102016009763A1 (de) * 2016-08-11 2018-02-15 Trw Automotive Gmbh Steuerungssystem und Steuerungsverfahren zum Bestimmen einer Trajektorie und zum Erzeugen von zugehörigen Signalen oder Steuerbefehlen
JP6600878B2 (ja) * 2017-12-21 2019-11-06 本田技研工業株式会社 車両制御装置、車両制御方法、およびプログラム
DE112019001421T5 (de) * 2018-03-20 2021-02-18 Mobileye Vision Technologies Ltd. Systeme und verfahren zum navigieren eines fahrzeugs
CN109747638B (zh) * 2018-12-25 2020-06-16 东软睿驰汽车技术（沈阳）有限公司 一种车辆行驶意图识别方法及装置
US20200310448A1 (en) * 2019-03-26 2020-10-01 GM Global Technology Operations LLC Behavioral path-planning for a vehicle
US11662730B2 (en) * 2019-07-01 2023-05-30 Baidu Usa Llc Hierarchical path decision system for planning a path for an autonomous driving vehicle
US11276179B2 (en) * 2019-12-18 2022-03-15 Zoox, Inc. Prediction on top-down scenes based on object motion
CN112015178B (zh) * 2020-08-20 2022-10-21 中国第一汽车股份有限公司 一种控制方法、装置、设备及存储介质
CN112020014B (zh) * 2020-08-24 2022-08-19 中国第一汽车股份有限公司 一种换道轨迹规划方法、装置、服务器及存储介质
CN113085895B (zh) * 2021-04-19 2022-07-22 陕西理工大学 车辆换道轨迹规划方法、装置、设备、存储介质及车辆

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109885066A (zh) * 2019-03-26 2019-06-14 北京经纬恒润科技有限公司 一种运动轨迹预测方法及装置
US20200377085A1 (en) * 2019-06-03 2020-12-03 Realtime Robotics, Inc. Apparatus, methods and articles to facilitate motion planning in environments having dynamic obstacles
CN111178286A (zh) * 2019-12-31 2020-05-19 智车优行科技（上海）有限公司 姿态轨迹预测方法、装置及电子设备
CN111126362A (zh) * 2020-03-26 2020-05-08 北京三快在线科技有限公司 一种预测障碍物轨迹的方法及装置
CN111982143A (zh) * 2020-08-11 2020-11-24 北京汽车研究总院有限公司 车辆及车辆路径规划方法、装置
CN112233417A (zh) * 2020-09-17 2021-01-15 新石器慧义知行智驰(北京)科技有限公司 车辆轨迹预测方法、控制装置及无人车
CN113335276A (zh) * 2021-07-20 2021-09-03 中国第一汽车股份有限公司 障碍物的轨迹预测方法、装置、电子设备及存储介质

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116309689A (zh) * 2023-05-17 2023-06-23 上海木蚁机器人科技有限公司 障碍物轨迹预测方法、装置、设备和介质
CN116309689B (zh) * 2023-05-17 2023-07-28 上海木蚁机器人科技有限公司 障碍物轨迹预测方法、装置、设备和介质
CN116734882A (zh) * 2023-08-14 2023-09-12 禾昆科技(北京)有限公司 车辆路径规划方法、装置、电子设备和计算机可读介质
CN116734882B (zh) * 2023-08-14 2023-11-24 禾昆科技(北京)有限公司 车辆路径规划方法、装置、电子设备和计算机可读介质
CN117962932A (zh) * 2024-04-02 2024-05-03 福瑞泰克智能系统有限公司 障碍物的行驶轨迹生成方法、装置和存储介质及电子设备
CN117962932B (zh) * 2024-04-02 2024-06-11 福瑞泰克智能系统有限公司 障碍物的行驶轨迹生成方法、装置和存储介质及电子设备

Also Published As

Publication number Publication date
CN113335276A (zh) 2021-09-03

Similar Documents

Publication Publication Date Title
WO2023001168A1 (zh) 障碍物的轨迹预测方法、装置、电子设备及存储介质
JP7082151B2 (ja) 地図軌跡マッチングデータの品質決定方法、装置、サーバ及び媒体
JP6754856B2 (ja) 自動運転車両のためのセンサー集約フレームワーク
JP6892464B2 (ja) 自動運転車両に用いられる検知支援
JP6722280B2 (ja) 自律走行車の交通予測における予測軌跡の評価フレームワーク
CN108253975B (zh) 一种建立地图信息及车辆定位的方法与设备
JP7072581B2 (ja) 自動運転車両の経路計画のための運転シナリオに基づく車線ガイドライン
US11372098B2 (en) Method, apparatus, device, and medium for determining angle of yaw
US20220309920A1 (en) Controlling vehicle-infrastructure cooperated autonomous driving
JP7266627B2 (ja) 早期警報方法、装置、電子機器、記録媒体及びコンピュータプログラム製品
US20170307384A1 (en) Storing trajectory
JP2018084573A (ja) 頑健で効率的な車両測位用のアルゴリズム及びインフラ
CN107945562B (zh) 停车场信息的推荐方法、服务器设备及可读介质
US20190374151A1 (en) Focus-Based Tagging Of Sensor Data
JP2021182418A (ja) 車両測位方法、装置、電子デバイス、記憶媒体及びプログラム
CN113537362A (zh) 一种基于车路协同的感知融合方法、装置、设备及介质
CN114212110B (zh) 障碍物轨迹预测方法、装置、电子设备及存储介质
CN109635861B (zh) 一种数据融合方法、装置、电子设备及存储介质
CN111380546A (zh) 基于平行道路的车辆定位方法、装置、电子设备和介质
JP2021082300A (ja) 車両測位方法、装置、電子機器、車両及び記憶媒体
WO2023142813A1 (zh) 基于多传感器的数据融合方法、装置、设备及介质
WO2023025007A1 (zh) 车辆避让方法、装置、车载设备及存储介质
CN114475656B (zh) 行驶轨迹预测方法、装置、电子设备以及存储介质
CN111354217A (zh) 停车路线确定方法、装置、设备及介质
JP6935507B2 (ja) 自動運転のための自己反転線の相互回避アルゴリズム

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: 22845333

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE