CN115112138A

CN115112138A - Trajectory planning information generation method and device, electronic equipment and storage medium

Info

Publication number: CN115112138A
Application number: CN202210508071.7A
Authority: CN
Inventors: 李赓; 张健; 郭正龙; 杨凡; 王鲲; 张雯; 胡茂洋; 骆乃瑞
Original assignee: Apollo Zhilian Beijing Technology Co Ltd
Current assignee: Apollo Zhilian Beijing Technology Co Ltd
Priority date: 2022-05-10
Filing date: 2022-05-10
Publication date: 2022-09-27

Abstract

The invention provides a track planning information generation method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical fields of automatic driving, intelligent transportation, high-precision maps, autonomous parking, cloud service, Internet of vehicles and intelligent cabins. The specific implementation scheme is as follows: generating at least one candidate track planning information of the automatically driven vehicle according to the vehicle road cloud cooperative perception information and the optimized behavior decision information corresponding to the automatically driven vehicle, wherein the vehicle road cloud cooperative perception information is determined according to at least one of vehicle end perception information, road end perception information and cloud end perception information related to the automatically driven vehicle; determining optimized trajectory planning information for the autonomous vehicle from the at least one candidate trajectory planning information based on the trajectory evaluation information.

Description

Trajectory planning information generation method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly to the field of automated driving, intelligent transportation, high-precision maps, and autonomous parking, cloud services, internet of vehicles, and intelligent cockpit technologies. In particular, the invention relates to a trajectory planning information generation method, a trajectory planning information generation device, an electronic device and a storage medium.

Background

With the development of artificial intelligence technology, automatic driving technology has also been developed. The automatic driving technology refers to a technology which can assist or replace a driver to steer and keep driving on a road without manual operation by means of a computer and an artificial intelligence technology, and realizes a series of operations such as following, braking, changing lanes and the like based on decision planning.

Disclosure of Invention

The disclosure provides a trajectory planning information generation method, a trajectory planning information generation device, an electronic device and a storage medium.

According to an aspect of the present disclosure, there is provided a trajectory planning information generating method, including: generating at least one candidate trajectory planning information of an autonomous vehicle according to vehicle road cloud cooperative sensing information and optimization behavior decision information corresponding to the autonomous vehicle, wherein the vehicle road cloud cooperative sensing information is determined according to at least one of vehicle end sensing information, road end sensing information and cloud end sensing information related to the autonomous vehicle; and determining optimized trajectory planning information for the autonomous vehicle from the at least one candidate trajectory planning information based on the trajectory evaluation information.

According to another aspect of the present disclosure, there is provided a trajectory planning information generating apparatus including: the generation module is used for generating at least one candidate track planning information of the automatic driving vehicle according to vehicle road cloud cooperative sensing information and optimized behavior decision information corresponding to the automatic driving vehicle, wherein the vehicle road cloud cooperative sensing information is determined according to at least one of vehicle end sensing information, road end sensing information and cloud end sensing information related to the automatic driving vehicle; and a determining module for determining optimized trajectory planning information for the autonomous vehicle from the at least one candidate trajectory planning information according to the trajectory evaluation information.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of the present disclosure.

According to another aspect of the disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of the disclosure.

According to another aspect of the present disclosure, there is provided an autonomous vehicle comprising an electronic device according to the present disclosure.

According to another aspect of the present disclosure, there is provided a roadside apparatus including the electronic apparatus according to the present disclosure.

According to another aspect of the present disclosure, a cloud server is provided, which includes the electronic device according to the present disclosure.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become readily apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 schematically illustrates an exemplary system architecture to which trajectory planning information generation methods and apparatus may be applied, according to an embodiment of the disclosure;

FIG. 2 schematically shows a flow chart of a trajectory planning information generation method according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates a schematic diagram of a trajectory planning information generation method according to an embodiment of the present disclosure;

fig. 4A schematically illustrates an example schematic diagram of a motion plan for a lane-free area blocking scene according to an embodiment of the disclosure;

FIG. 4B schematically illustrates an example schematic diagram of a narrow traffic profile and a motion plan for a dense traffic scenario, in accordance with an embodiment of the disclosure;

FIG. 4C schematically illustrates an example schematic diagram of a motion plan for a remote control driving trajectory planning scenario, in accordance with an embodiment of the disclosure;

FIG. 5 schematically shows a block diagram of a trajectory planning information generation apparatus according to an embodiment of the present disclosure; and

fig. 6 schematically shows a block diagram of an electronic device adapted to implement a trajectory planning information generation method according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Decision planning is one of the main parts of automated driving technology. The Decision plan may include a global path plan (i.e., Routing) section, a behavioral Decision (i.e., Decision) section, and a motion plan (i.e., Planning) section. And the global path planning part is used for obtaining global optimization path planning information. The behavior decision part and the motion planning part obtain the local optimized path planning information on the basis of the global optimized path planning information. The locally optimized path planning information may refer to optimized trajectory planning information.

The embodiment of the disclosure provides a track planning information generation scheme based on vehicle-road cloud integration. For example, at least one candidate trajectory planning information for the autonomous vehicle is generated based on the vehicle road cloud collaborative awareness information and the optimization behavior decision information corresponding to the autonomous vehicle. The vehicle road cloud cooperative sensing information is determined according to at least one of vehicle end sensing information, road end sensing information and cloud end sensing information related to the automatic driving vehicle. Determining optimized trajectory planning information for the autonomous vehicle from the at least one candidate trajectory planning information based on the trajectory evaluation information.

According to the embodiment of the disclosure, the vehicle path cloud cooperative sensing information is determined according to at least one of vehicle end sensing information, road end sensing information and cloud end sensing information related to the autonomous vehicle, so that the vehicle path cloud cooperative sensing information integrates multiple dimension information, and therefore, based on the vehicle path cloud cooperative sensing information, at least one candidate trajectory planning information of the autonomous vehicle is generated by combining with the optimization behavior decision information, and then the optimized trajectory planning information of the autonomous vehicle is determined from the at least one candidate trajectory planning information by combining with the trajectory evaluation information, so that the accuracy and precision of the generated optimized trajectory planning information can be improved.

Fig. 1 schematically illustrates an exemplary system architecture to which trajectory planning information generation methods and apparatus may be applied, according to an embodiment of the present disclosure.

It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios. The system architecture of the embodiment of the present disclosure may also be implemented in other ways according to implementation requirements.

As shown in fig. 1, the system architecture 100 according to the embodiment may be a vehicle-road-cloud integrated system architecture. The vehicle-road-cloud integrated system architecture may include a vehicle end 101, a road end 102, and a cloud end 103. The vehicle end 101, the road end 102 and the cloud end 103 may be in communication connection with each other through various communication connection types. For example, the communication connection type may include at least one of: wired communication and wireless communication. For example, the wireless communication may include Vehicle to X (V2X). For example, the vehicular wireless communication may include at least one of: vehicle radio Communication based on Dedicated Short Range Communication (DSRC) and vehicle radio Communication based on Cellular mobile Communication (Cellular V2X, C-V2X). The cellular mobile communication-based wireless communication for vehicles may include at least one of: vehicle wireless communication based on LTE-V2X (Long Term Evolution V2X) and fourth generation mobile communication (The 4) ^th Generation Mobile Communication Technology, 4G) and fifth-Generation Mobile Communication-based (The 5) ^th Generation Mobile Communication Technology, 5G).

The vehicle end 101 may include N autonomous vehicles, which may refer to vehicles configured in an autonomous mode. The autonomous vehicle may include a vehicle-end sensor unit, a vehicle-end sensing unit, a vehicle-end positioning unit, and a vehicle-end decision unit. For example, the vehicle end sensor unit may include at least one of: vehicle-end vision sensor, vehicle-end laser radar and vehicle-end radar. The visual sensor may comprise a camera. The vehicle-end radar may include at least one of: vehicle-end millisecond wave radar and vehicle-end ultrasonic radar. The vehicle-end sensing unit may include a hardware subunit and a software subunit. The hardware subunits may include a processor and a memory. The software subunit may include an operating system and planning and routing threads. The vehicle-end locating unit may include at least one of: global Positioning System (GPS), BeiDou Navigation Satellite System (BDS), Global Navigation Satellite System (GNSS), GLONASS, Inertial Measurement Unit (IMU), vision sensor, vehicle-end laser radar, and vehicle-end radar. Additionally, the autonomous vehicle may also include a software application. The software application may include at least one of: navigation type applications, entertainment type applications, and instant messaging type applications. For example, the N autonomous vehicles may include autonomous vehicle 101_1, autonomous vehicle 101_2, an. N may be an integer greater than or equal to 1. N ∈ {1, 2., (N-1), N }.

The route end 102 may include M Road Side devices (RSCs) and various types of application service systems. The roadside apparatus may include a roadside sensor Unit, a roadside sensing Unit, and a roadside Computing Unit (RSCU). The roadside computing unit can be a small server which is improved to meet extreme conditions of low voltage, high temperature, high humidity and the like of a roadside lamp post. Furthermore, the roadside calculation unit may be replaced with an edge calculation unit. The deployment mode of the road side equipment can be determined according to the actual service requirement. For example, the roadside sensor may include at least one of: roadside vision sensors, roadside radars, and roadside lidar. The roadside sensing unit may include a processor and a memory. In another system architecture, the roadside sensing unit itself may include computational functionality. For example, the M roadside devices may include roadside devices 102_1, #. # r, autonomous vehicles 102_ M, # r. M may be an integer greater than or equal to 1. M may be equal to or different from N. M ∈ {1, 2., (M-1), M }.

The cloud 103 may include at least one of: a cloud controlled platform 103_1 and a third party platform 103_ 2. The cloud controlled platform 103_1 may include at least one of: the system comprises an edge cloud control platform, a region cloud control platform and a center cloud control platform. The cloud control platform 103_1 may be a cloud server or a collection of cloud servers. The cloud-side Server is a host product in a cloud computing service system, and overcomes the defects of high management difficulty and weak service extensibility in the traditional physical host and VPS (Virtual Private Server, VPS). The third party platform 103_2 may include at least one of: a traffic management platform, a map platform, a travel service platform, a vehicle management platform and an Original Equipment Manufacturer (OEM) platform.

It should be noted that the trajectory planning information generation method provided by the embodiment of the present disclosure may be executed by the vehicle end 101. Correspondingly, the trajectory planning information generation device provided by the embodiment of the present disclosure may also be disposed in the vehicle end 101.

Alternatively, the track planning information generation method provided by the embodiment of the present disclosure may be executed by the router 102. Correspondingly, the trajectory planning information generation device provided by the embodiment of the present disclosure may also be disposed in the road end 102.

Alternatively, the trajectory planning information generation method provided by the embodiment of the present disclosure may also be executed by the cloud 103. Correspondingly, the trajectory planning information generation device provided by the embodiment of the present disclosure may be disposed in the cloud 103. For example, the cloud platform 103_1 in the cloud 103.

Or, the trajectory planning information generation method provided by the embodiment of the present disclosure may also be executed by a vehicle-road-cloud integrated system. Correspondingly, the trajectory planning information generation device provided by the embodiment of the disclosure can also be arranged in a vehicle-road cloud integrated system.

It should be noted that the sequence numbers of the respective operations in the following methods are merely used as representations of the operations for description, and should not be construed as representing the execution order of the respective operations. The method need not be performed in the exact order shown, unless explicitly stated.

Fig. 2 schematically shows a flow chart of a trajectory planning information generation method according to an embodiment of the present disclosure.

As shown in FIG. 2, the method 200 includes operations S210-S220.

In operation S210, at least one candidate trajectory planning information of the autonomous vehicle is generated according to the road cloud collaborative awareness information and the optimization behavior decision information corresponding to the autonomous vehicle. The vehicle road cloud cooperative sensing information is determined according to at least one of vehicle end sensing information, road end sensing information and cloud end sensing information related to the automatic driving vehicle.

In operation S220, optimized trajectory planning information for the autonomous vehicle is determined from the at least one candidate trajectory planning information according to the trajectory evaluation information.

According to an embodiment of the present disclosure, the optimized behavior decision information may be generated by determining the autonomous vehicle from a behavior decision information set according to the decision evaluation information, the road cloud collaborative awareness information corresponding to the autonomous vehicle, and the global optimized path planning information. The decision evaluation information may include at least one of: the driving condition information includes evaluation information related to a driving task, evaluation information related to driving prior knowledge, evaluation information related to traffic regulations, and evaluation information related to historical behavior decision information. The behavioral decision information set may include at least one of: the system comprises a bypassing strategy, a lane changing strategy, a car following strategy, a parking strategy, an avoidance strategy, a passing strategy, a turning strategy, a passing order arbitration strategy and a strategy for applying for taking over and getting rid of difficulties. The detour policy may include at least one of: a lane-borrowing detour strategy and a recommended trajectory-based detour strategy. The lane-change strategy may include at least one of: an advance lane change strategy and a continuous lane change strategy.

According to embodiments of the present disclosure, trajectory evaluation information may be used to evaluate candidate trajectory planning information. The trajectory estimation information may include at least one of: driving comfort evaluation information, accessibility evaluation information, safety evaluation information, and traffic efficiency evaluation information. The trajectory planning information may include local path planning information and travel speed. The candidate trajectory planning information may include candidate local path planning information and candidate travel speeds. The optimized trajectory planning information may include optimized local path planning information and optimized driving speed.

According to embodiments of the present disclosure, the perception information may be determined from sensor information. Sensor information may refer to information related to a perception object collected using a sensor. For example, the perception information may be obtained by processing sensor information using a perception algorithm. The sensor may include at least one of: vision sensors, lidar and radar. The radar may include at least one of: millimeter wave radars and ultrasonic radars. The sensor information may include at least one of: visual sensor information, laser radar information, and radar information. The visual sensor information may include image information. The lidar information may include laser point cloud information. The perception algorithm may include at least one of: a perception algorithm based on point cloud information and a perception algorithm based on visual information.

According to an embodiment of the present disclosure, the perception object may include at least one of: an autonomous vehicle, an interactive object, an object related to a travel path, and an object related to a travel environment. An interactive object may refer to an object that has an interactive relationship with an autonomous vehicle. The interaction may include at least one of: interactive conflicts and road congestion. The interactive object may be referred to as an obstacle. The interactive object may include at least one of: static interactive objects and dynamic interactive objects. A static interactive object may refer to an interactive object that is in a static state. A dynamic interactive object may refer to an interactive object that is in motion. The object related to the travel path may include at least one of: can pass roads, signboards, traffic lights and lane lines. The object associated with the driving environment may include at least one of: road information and weather information.

According to an embodiment of the disclosure, the sensor information may include vehicle-end sensor information and road-side sensor information. The vehicle-end sensor information may be information related to a perception object collected by the vehicle-end sensor. The roadside sensor information may be information related to a perception object collected by a roadside sensor. The vehicle-end sensor information may include at least one of: sensor information of the autonomous vehicle itself and sensor information of other autonomous vehicles.

According to an embodiment of the present disclosure, the perception information may include at least one of: object information, road event information, and traffic situation information. The road event information may include at least one of: road event type, road event location, and event impact range information. The object information may include at least one of: object state information and object intent information. The object state information may include at least one of: object type, object location, and object velocity. The object may include at least one of: autonomous vehicles and interactive objects.

According to the embodiment of the disclosure, for the vehicle-road cloud integrated system, the vehicle-road cloud cooperative sensing information can be determined according to the vehicle-side sensing information and the road-side sensing information. The vehicle-end sensing information can be obtained by processing vehicle-end sensor information. The road-end sensing information can be obtained by processing road-end sensor information.

According to an embodiment of the disclosure, the vehicle road cloud collaborative awareness information may include at least one of: the vehicle-end related perception information, the road-end related perception information and the cloud-end related perception information. The vehicle-end related awareness information may include at least one of: perception information of the automatic driving vehicle, perception information of other automatic driving vehicles, road side perception information, cloud side perception information and vehicle side fusion perception information. The vehicle-side fusion perception information can be obtained by fusing at least two items of perception information of the automatic driving vehicle, perception information of other automatic driving vehicles, road-side perception information and cloud perception information.

According to an embodiment of the present disclosure, the end-of-road related awareness information may include at least one of: the system comprises road end sensing information, sensing information of automatic driving vehicles, sensing information of other automatic driving vehicles, cloud sensing information and road end fusion sensing information. The road-end fusion perception information can be obtained by fusing at least two items of road-end perception information, perception information of the automatic driving vehicle, perception information of other automatic driving vehicles and cloud perception information.

According to an embodiment of the present disclosure, the cloud-related awareness information may include at least one of: and the cloud end perception information and the cloud end fusion perception information. The cloud awareness information may include at least one of: perception information of the autonomous vehicle, perception information of other autonomous driving processes, and roadside perception information. The cloud fusion perception information can be obtained by fusing at least two items of perception information of the automatic driving vehicle, perception information of other automatic driving vehicles and road side perception information.

According to the embodiment of the disclosure, vehicle-end state space information can be constructed according to the behavior decision related information. And constructing road cloud state space information according to the behavior decision related information and the cloud access information. The vehicle-end state space information may include at least one of: the method comprises the following steps of predicting the behavior track of the key obstacle, referring to track line information, scene tree information and the like. The road cloud state space information may include at least one of: key obstacle intention information, scene semantic understanding information, a conflict arbitration strategy, a multi-vehicle cooperation strategy and the like.

According to the embodiment of the disclosure, the optimized behavior decision information of the autonomous vehicle can be determined from the behavior decision information set based on a behavior decision algorithm according to the decision evaluation information, the behavior decision related information and the global optimized path planning information. For example, the behavioral decision algorithm may include one of: a behavior decision algorithm based on a finite state machine model, a behavior decision algorithm based on a decision tree model, a behavior decision algorithm based on a knowledge reasoning decision model and a behavior decision algorithm based on a value model. For example, the value model-based behavioral decision algorithm may include a Markov decision process-based behavioral decision algorithm.

According to the embodiment of the disclosure, the optimized behavior decision information of the autonomous vehicle can be determined from the behavior decision information set based on a behavior decision algorithm according to the decision evaluation information, the vehicle end state space information, the road cloud state space information and the global optimized path planning information.

For example, for an interaction conflict class event, where the interactive object is a motor vehicle, the optimization behavior decision information may include a traffic order arbitration policy between the autonomous vehicle and the interactive object. The interactive object includes at least one of: non-motor vehicles and pedestrians, the optimization behavior decision information may include at least one of: a deceleration avoidance strategy, a detour passing strategy and a normal driving passing strategy.

For example, for a road congestion type event, the road congestion event includes at least one of: the method comprises the following steps of vehicle blocking traffic events, traffic accident blocking traffic events, construction area blocking traffic events and road closing blocking traffic events. In the event that the road congestion event is a vehicle congestion traffic event, the optimized behavior decision information includes a primary vehicle traffic strategy. The master traffic strategy may include at least one of: a follow-ahead vehicle queuing strategy and a bypass-ahead vehicle strategy. The optimized behavior decision information may include a primary detour strategy in the event that the road congestion event includes at least one of a traffic accident congestion traffic event, a construction area congestion traffic event, and a road closure congestion traffic event. The primary detour strategy may include at least one of: the method comprises the following steps of an advance lane changing strategy, a continuous lane changing strategy, a lane detouring strategy by opposite directions, a track detouring strategy based on recommendation and a taking-over and escaping strategy.

According to the embodiment of the disclosure, the auxiliary traffic flow track information can be determined according to the vehicle road cloud coordination perception information corresponding to the automatic driving vehicle. And generating at least one candidate track planning information according to the vehicle road cloud cooperative perception information, the auxiliary vehicle flow track information and the optimization behavior decision information. And determining optimized track planning information from at least one candidate track planning information according to the track evaluation information. The autonomous vehicle may travel according to the optimized trajectory planning information.

For example, according to an embodiment of the present disclosure, the trajectory planning information generation method provided by the embodiment of the present disclosure may be performed by one of: vehicle end, road end and high in the clouds.

According to an embodiment of the present disclosure, the lane-level globally optimized path planning information of the autonomous vehicle, if performed by the vehicle end, may be generated by the vehicle end from the vehicle end high-precision map information and the received globally optimized path planning information from the first other end. The global optimized path planning information may be generated by the first other end according to the global path planning related information and the driving demand information of the set of autonomous vehicles. The first other end may include at least: cloud and way end.

According to the embodiment of the disclosure, in a case of execution by a vehicle end, determining optimized behavior decision information from a behavior decision information set according to decision evaluation information, and vehicle route cloud collaborative awareness information and global optimized path planning information corresponding to an autonomous vehicle may include: the vehicle end can determine optimized behavior decision information from the behavior decision information set according to the vehicle road cloud collaborative perception information and the lane-level global optimized path planning information based on the decision evaluation information. The vehicle end may determine, based on the decision evaluation information, optimized behavior decision information from the behavior decision information set according to the vehicle road cloud collaborative awareness information and the lane-level global optimized path planning information, and may include: the vehicle end can determine optimized behavior decision information from the behavior decision information set according to the vehicle end state space information, the lane-level global optimized path planning information and the received road cloud state space information from the first other end based on the decision evaluation information. The vehicle-end state space information can be constructed by the vehicle end according to the behavior decision related information. Alternatively, the vehicle-end state space information may be constructed by the first other end according to the behavior decision related information. The behavior decision related information comprises vehicle road cloud cooperative perception information. The road cloud state space information can be constructed by the first other end according to the vehicle-road cloud cooperative perception information. Determining optimized behavior decision information from the behavior decision information set according to the vehicle end state space information, the lane-level global optimized path planning information and the received road cloud state space information from the first other end based on the decision evaluation information, which may include: and based on the decision evaluation information, determining optimized behavior decision information from the behavior decision information set according to the vehicle end state space information received from the first other end, the lane-level global optimized path planning information and the road cloud state space information received from the first other end.

According to the embodiment of the disclosure, under the condition of execution by a vehicle end, generating optimized trajectory planning information of an autonomous vehicle according to trajectory evaluation information, and road cloud cooperative perception information and optimized behavior decision information corresponding to the autonomous vehicle may include: the vehicle end can generate optimized track planning information of the automatic driving vehicle according to the vehicle road cloud collaborative perception information and the optimized behavior decision information based on the track evaluation information. The vehicle end may generate optimized trajectory planning information of the autonomous vehicle according to the vehicle road cloud collaborative awareness information and the optimized behavior decision information based on the trajectory evaluation information, and may include: the vehicle end can generate optimized track planning information of the automatic driving vehicle according to the optimized behavior decision information, the vehicle road cloud cooperative sensing information and the received at least one candidate track planning information from the first other end based on the track evaluation information.

According to an embodiment of the disclosure, in the case of execution by the cloud, the lane-level globally optimal path planning information for the autonomous vehicle may be generated by the cloud according to the globally optimal path planning information and the received vehicle-side high-precision map information from the second other side. Alternatively, the lane-level globally optimized path plan information for the autonomous vehicle may be the lane-level globally optimized path plan information received in the cloud from the second other end. The global optimized path planning information may be generated by the cloud based on the global path planning-related information and the driving demand information of the set of autonomous vehicles. The second other end may include at least: road end and car end.

According to the embodiment of the disclosure, under the condition of execution by a cloud, determining optimized behavior decision information from a behavior decision information set according to decision evaluation information, and vehicle route cloud cooperative perception information and global optimized path planning information corresponding to an autonomous vehicle, may include: the cloud end can determine optimized behavior decision information from the behavior decision information set according to the vehicle road cloud collaborative perception information and the lane-level global optimized path planning information based on the decision evaluation information. The cloud end may determine, based on the decision evaluation information, optimized behavior decision information from the behavior decision information set according to the vehicle road cloud collaborative perception information and the lane-level global optimized path planning information, and may include: the cloud end can determine optimized behavior decision information from the behavior decision information set according to the received vehicle end state space information, lane-level global optimized path planning information and road cloud state space information from the vehicle end based on the decision evaluation information. The vehicle-end state space information can be constructed by the vehicle end according to the behavior decision related information. The behavior decision related information comprises vehicle road cloud cooperative perception information. The road cloud state space information can be constructed by the cloud according to the vehicle road cloud cooperative sensing information. Alternatively, the road cloud state space information may be constructed by the received information from the second other end according to the vehicle-road cloud cooperative sensing information.

According to the embodiment of the disclosure, under the condition of execution by a cloud end, generating the optimized trajectory planning information of the autonomous vehicle according to the trajectory evaluation information and the road cloud cooperative perception information and the optimized behavior decision information corresponding to the autonomous vehicle may include: the cloud end can generate optimized track planning information of the automatic driving vehicle according to the vehicle road cloud cooperative perception information and the optimized behavior decision information based on the track evaluation information. The cloud end can be based on the track assessment information, and according to vehicle road cloud collaborative perception information and optimization behavior decision information, generate the optimization track planning information of the automatic driving vehicle, and can include: the cloud end can generate optimized track planning information of the automatic driving vehicle according to the optimized behavior decision information, the vehicle road cloud collaborative sensing information and the at least one candidate track planning information based on the track evaluation information.

According to an embodiment of the present disclosure, the lane-level globally optimized path planning information of the autonomous vehicle, if performed by the road-end, may be generated by the road-end according to the globally optimized path planning information and the received vehicle-end high-precision map information from the third other end. Alternatively, the lane-level global optimized path plan information for the autonomous vehicle may be lane-level global optimized path plan information from a third other end received by the road end. The global optimized path planning information may be generated by the road-side based on the global path planning related information and the driving demand information of the set of autonomous vehicles. The third other end may include at least: vehicle end and high in the clouds.

According to the embodiment of the disclosure, in a case of being executed by a route end, determining optimized behavior decision information from a behavior decision information set according to decision evaluation information, and vehicle route cloud collaborative awareness information and global optimized path planning information corresponding to an autonomous vehicle, may include: the road end can determine optimized behavior decision information from the behavior decision information set according to the vehicle road cloud collaborative perception information and the lane-level global optimized path planning information based on the decision evaluation information. The road end may determine, based on the decision evaluation information, optimized behavior decision information from the behavior decision information set according to the vehicle road cloud collaborative perception information and the lane-level global optimized path planning information, and may include: the road end can determine optimized behavior decision information from the behavior decision information set according to the received vehicle end state space information, lane-level global optimized path planning information and road cloud state space information from the vehicle end based on the decision evaluation information. The road cloud state space information may be road cloud state space information received from a third other end. The vehicle-end state space information can be constructed by the vehicle end according to the behavior decision related information. The behavior decision related information comprises vehicle road cloud cooperative perception information. The road cloud state space information can be constructed by the road end according to the vehicle-road cloud cooperative sensing information. Alternatively, the road cloud state space information may be received from a third other end and constructed according to the vehicle-road cloud cooperative sensing information.

According to the embodiment of the disclosure, in the case of being executed by a route end, generating optimized trajectory planning information of an autonomous vehicle according to trajectory evaluation information, and road cloud cooperative perception information and optimized behavior decision information corresponding to the autonomous vehicle may include: and the road end can generate optimized track planning information of the automatic driving vehicle according to the vehicle road cloud collaborative perception information and the optimized behavior decision information based on the track evaluation information. The road end may generate optimized trajectory planning information of the autonomous vehicle according to the vehicle road cloud collaborative awareness information and the optimized behavior decision information based on the trajectory evaluation information, and may include: the road end can generate optimized track planning information of the automatic driving vehicle according to the optimized behavior decision information, the vehicle road cloud collaborative sensing information and the at least one candidate track planning information based on the track evaluation information.

For example, the vehicle end may generate lane-level global optimized path planning information according to the vehicle end high-precision map information and the global optimized path planning information in response to receiving the global optimized path planning information from the first other end.

The vehicle end can determine optimized behavior decision information of the automatic driving vehicle from the behavior decision information set according to the vehicle road cloud cooperative perception information and the lane-level global optimized path planning information based on the decision evaluation information. For example, the vehicle end may determine optimized behavior decision information of the autonomous vehicle from the behavior decision information set according to the lane-level global optimized path planning information, the vehicle end state space information, and the received road cloud state space information from the first other end based on the decision evaluation information. The vehicle end state space information can be constructed by the vehicle end according to the vehicle road cloud cooperative sensing information. The road cloud state space information can be constructed by the first other end according to the vehicle-road cloud cooperative sensing information.

The vehicle end can generate optimized track planning information of the automatic driving vehicle according to the vehicle road cloud collaborative perception information and the optimized behavior decision information based on the track evaluation information. For example, the vehicle end may generate optimized trajectory planning information for the autonomous vehicle based on the trajectory assessment information and based on the optimized behavior decision information and the received at least one candidate trajectory planning information from the first other end. The at least one candidate trajectory planning information may be generated by the first other end according to the road cloud state space information and the vehicle road cloud cooperative sensing information.

The following further describes the trajectory planning information generating method according to the present disclosure with reference to fig. 3 and fig. 4A to 4C, in combination with a specific embodiment. Fig. 3 illustrates an overall scheme of an embodiment of the present disclosure. Fig. 4A to 4C are explained with respect to the exercise planning section.

Fig. 3 schematically illustrates a schematic diagram of a trajectory planning information generation method according to an embodiment of the present disclosure.

As shown in fig. 3, for the global path planning section, global optimized path planning information 303 for autonomous vehicles may be generated 300 from global path planning related information 301 and driving demand information 302 for a set of autonomous vehicles including the autonomous vehicles.

For the behavior decision part, vehicle-end state space information 305 and road cloud state space information 306 may be constructed according to behavior decision related information 304 corresponding to the autonomous driving vehicle. The behavioral decision-related information 304 may include vehicle road cloud collaborative awareness information 311. The state space information includes vehicle-end state space information 305 and road cloud state space information 306. Optimized behavior decision information 309 for the autonomous vehicle may be determined from the behavior decision information set 307 based on the decision evaluation information 308, the state space information, and the global optimized path plan information 303.

For the motion planning part, the optimized trajectory planning information 312 of the autonomous vehicle may be determined according to the trajectory evaluation information 310, and the road cloud collaborative awareness information 311 and the optimized behavior decision information 309 corresponding to the autonomous vehicle.

According to the embodiment of the disclosure, the motion planning part can be used for solving the problems in interactive conflict scenes and road blocking scenes, and realizing local path optimization. The foregoing will be described with reference to the accompanying drawings and tables in conjunction with specific embodiments.

Table 1 schematically shows the scenarios to which the motion planning part is applicable and the decision planning strategy for the respective scenarios. Referring to fig. 4A to 4C, the motion planning section according to the embodiment of the present disclosure in table 1 will be described with reference to specific embodiments.

TABLE 1

According to an embodiment of the present disclosure, the vehicle cloud collaborative awareness information may include road traffic situation information and road event location information.

According to an embodiment of the present disclosure, operation S210 may include the following operations.

And acquiring auxiliary traffic flow track information corresponding to the automatic driving vehicle according to the road event position information. And generating at least one candidate track planning information of the automatic driving vehicle according to the auxiliary traffic flow track information and the road traffic situation information.

According to embodiments of the present disclosure, road traffic situation information may be used to characterize traffic situation information for a travel road associated with an autonomous vehicle. The road event location information may characterize the road event occurrence area. For example, the road event location information may include one of: an interactive collision event occurrence area and a road blocking event occurrence area.

According to embodiments of the present disclosure, the auxiliary traffic trajectory information may characterize peripheral traffic trajectory information of a predetermined area in front of the autonomous vehicle. The auxiliary traffic trajectory information may include at least one of: autonomous traffic trajectory information and non-autonomous traffic trajectory information. The automatically driven traffic trajectory information may be traffic trajectory information formed by the historical automatically driven vehicle via an area corresponding to the road event location information. The non-autonomous driving traffic trajectory information may be traffic trajectory information formed by the non-autonomous driving vehicle via an area corresponding to the road event location information.

According to the embodiment of the present disclosure, the auxiliary traffic trajectory information may be acquired from the historical auxiliary traffic trajectory information according to the road event location. And generating at least one candidate track planning information according to the road traffic situation information and the auxiliary traffic flow track information.

For example, where performed by a vehicle end, the vehicle end may determine optimized trajectory planning information for the autonomous vehicle from the received at least one candidate trajectory planning information from the first other end based on the trajectory assessment information. The at least one candidate trajectory planning information may be generated by the first other end according to the vehicle road cloud collaborative awareness information and the optimization behavior decision information corresponding to the autonomous vehicle.

According to an embodiment of the present disclosure, acquiring the auxiliary traffic trajectory information corresponding to the autonomous vehicle according to the road event location information may include the following operations.

And determining the cooperative perception information of the vehicle road cloud to be analyzed related to the road event position information from the historical vehicle road cloud cooperative perception information. And obtaining auxiliary traffic flow track information corresponding to the automatic driving vehicle according to the road cloud collaborative perception information to be analyzed.

According to the embodiment of the disclosure, the cooperative perception information of the vehicle road cloud to be analyzed, which is related to the road event position, can be determined from the historical cooperative perception information of the vehicle road cloud. And then processing the vehicle road cloud collaborative perception information to be analyzed to obtain auxiliary traffic flow track information.

According to the embodiment of the disclosure, obtaining the auxiliary traffic flow track information corresponding to the automatic driving vehicle according to the to-be-analyzed vehicle road cloud collaborative perception information may include the following operations.

According to the embodiment of the disclosure, candidate vehicle track information corresponding to the automatic driving vehicle is obtained according to the vehicle road cloud collaborative perception information to be analyzed. The candidate traffic flow trajectory information may include a plurality of candidate trajectories. And determining the similarity among the candidate tracks to obtain a plurality of similarities. Determining at least one auxiliary track from the plurality of candidate tracks according to the plurality of similarities to obtain auxiliary vehicle track information corresponding to the automatic driving vehicle

According to the embodiment of the disclosure, the vehicle road cloud collaborative perception information to be analyzed can be analyzed, and candidate traffic flow track information comprising a plurality of candidate tracks can be obtained. The similarity between the candidate trajectories may be determined, resulting in a plurality of similarities. At least one auxiliary track can be determined from the multiple candidate tracks according to a sequencing result obtained by sequencing the multiple similarities, so that auxiliary traffic flow track information is obtained. Alternatively, at least one auxiliary track may be determined from the plurality of candidate tracks according to the plurality of similarities and a predetermined similarity threshold, so as to obtain auxiliary traffic track information. The predetermined similarity threshold may be configured according to actual service requirements, and is not limited herein.

According to an embodiment of the present disclosure, the vehicle road cloud collaborative awareness information may include road state information.

According to an embodiment of the present disclosure, generating at least one candidate trajectory planning information for an autonomous vehicle based on the auxiliary traffic flow trajectory information and the road traffic situation information may include the following operations.

And determining the accessibility of the path according to the auxiliary traffic track information under the condition that the road blocking event is determined to occur in the expected road area according to the road state information. The path reachability characterizes a likelihood of the autonomous vehicle to pass through a congested area corresponding to a road congestion event based on the current path. And under the condition that the path is determined to be accessible, generating decision information for recommending that the automatic driving vehicle detours through the blocked area according to the road traffic situation information. In response to receiving the decision information, generating at least one candidate trajectory planning information for the autonomous vehicle in accordance with the auxiliary traffic stream trajectory information.

In accordance with embodiments of the present disclosure, the expected road region may include at least one of: road blocking events occur in narrow traffic cross-section areas, in areas with dense oncoming traffic and in areas where no lane lines are depicted.

According to the embodiment of the disclosure, the road blocking area type, the blocking area range and the blocking area distribution condition can be determined according to the vehicle road cloud cooperative sensing information corresponding to the automatic driving vehicle. In the case where it is determined that the congested area is an expected road area based on the type of the road congested area, the congested area range, and the congested area distribution. And acquiring peripheral traffic flow track information of a blocking area in front of the automatic driving vehicle, and generating auxiliary traffic flow track information through big data accumulation. And under the condition that the traffic flow trajectory information is used for determining that the traffic jam area has accessibility under the condition that the automatic driving vehicle does not borrow the lane, generating recommended trajectory detour passing decision information according to the road traffic situation information. In the case of determining the decision information, the determining of the optimized trajectory planning information may be a reference recommended trajectory detour according to the auxiliary traffic flow trajectory information.

According to an embodiment of the present disclosure, determining optimized trajectory planning information for an autonomous vehicle from at least one candidate trajectory planning information based on the trajectory evaluation information may include the following operations.

And evaluating the at least one candidate track planning information according to the track evaluation information to obtain at least one evaluation result. The trajectory estimation information includes at least one of: driving comfort evaluation information, accessibility evaluation information, safety evaluation information, and traffic efficiency evaluation information. And determining an optimized evaluation result according to the at least one evaluation result. And determining candidate track planning information corresponding to the optimization evaluation result as the optimized track planning information of the automatic driving vehicle.

According to the embodiment of the disclosure, for candidate trajectory planning information in at least one candidate trajectory planning information, the candidate trajectory planning information may be evaluated by using the trajectory evaluation information to obtain an evaluation result. The evaluation result may be an evaluation value. Thereby, evaluation results each corresponding to at least one candidate trajectory planning information can be obtained.

According to an embodiment of the present disclosure, after obtaining the evaluation results corresponding to each of the at least one candidate trajectory planning information, an optimized evaluation result may be determined from the at least one evaluation result according to the at least one evaluation result and a predetermined evaluation condition. For example, the at least one evaluation result may be sorted to obtain a sorted result. And determining an optimized evaluation result from the at least one evaluation result according to the sequencing result. Alternatively, an optimized evaluation result may be determined from the at least one evaluation result based on the at least one evaluation result and a predetermined evaluation threshold. The predetermined evaluation threshold may be configured according to actual traffic demands, and is not limited herein.

According to an embodiment of the present disclosure, determining an optimized evaluation result according to at least one evaluation result may include the following operations.

And sequencing at least one evaluation result to obtain a sequencing result. And determining an optimized evaluation result from the at least one evaluation result according to the sequencing result.

According to the embodiment of the disclosure, at least one evaluation result can be ranked to obtain a ranking result. And determining an optimized evaluation result from the at least one evaluation result according to the sequencing result. The sorting may be in the order of the evaluation results from small to large or in the order of large to small. For example, if the ranks are in the order of the evaluation results from small to large, the evaluation result of the last rank may be determined as the optimized evaluation result.

According to the embodiment of the present disclosure, the cooperative vehicle route and cloud awareness information is determined according to at least one of vehicle end awareness information, road end awareness information, and cloud awareness information related to the autonomous driving vehicle, and may include:

the vehicle-road cloud collaborative awareness information may include vehicle-end related awareness information, road-end related awareness information, and cloud-end related awareness information.

With reference to fig. 4A to fig. 4C, a behavior decision for an interactive conflict class scenario according to an embodiment of the present disclosure is further described with reference to specific embodiments.

Fig. 4A schematically illustrates an example schematic diagram of a motion plan for a lane-free area blocking scene according to an embodiment of the disclosure.

As shown in fig. 4A, in 400A, in the case where the location of the congestion event is a road area without a lane line depiction, after the vehicle-road-cloud integrated system determines the optimized trajectory planning information, in the case where the trajectory route planning of the main vehicle is difficult to complete the lane change or the detour strategy, the vehicle is likely to be unreasonably stopped or taken over. The area of the roadway free of lane markings may include a central area of the intersection.

Therefore, the road blocking area type, the blocking area range and the blocking area distribution condition are determined according to the vehicle road cloud cooperative perception information corresponding to the automatic driving vehicle 401. And determining the area of the road without the lane line where the blockage occurs according to the type of the road blockage area, the range of the blockage area and the distribution condition of the blockage area. Peripheral traffic flow trajectory information of a congestion area in front of the autonomous vehicle 401 is acquired, and auxiliary traffic flow trajectory information is formed by large data accumulation. And determining the optimized track planning information according to the road traffic situation information and the auxiliary traffic track information, wherein the optimized track planning information can be the reference recommended track bypassing.

Autonomous vehicle 401 may travel along path 402 smoothly through intersection-blocking areas.

Fig. 4B schematically illustrates an example schematic diagram of a narrow traffic profile and a motion plan for a dense traffic scene, according to an embodiment of the disclosure.

As shown in fig. 4B, in 400B, when a traffic jam occurs on a road with a narrow traffic section and a dense oncoming traffic flow, and the available space is limited, if the traffic jam passes by lane change or detour, the oncoming traffic flow is greatly affected.

For this purpose, the road blocking area type, the blocking area range, and the blocking area distribution are determined according to the vehicle road cloud cooperative sensing information corresponding to the autonomous vehicle 403. And determining that the blockage occurs in a narrow traffic section and the opposite traffic flow is dense according to the type of the road blockage area, the range of the blockage area and the distribution condition of the blockage area. The peripheral traffic trajectory information of the congested area in front of the autonomous vehicle 403 is acquired, and the auxiliary traffic trajectory information is formed by large data accumulation. Determining from the auxiliary traffic trajectory information that the congested area is accessible without the autonomous vehicle 403 borrowing a lane. And determining a recommended track bypassing decision according to the road traffic situation information. And under the condition of determining the recommended track bypassing decision, determining the optimized track planning information according to the auxiliary traffic flow track information, wherein the optimized track bypassing decision can be the reference recommended track bypassing decision.

The autonomous vehicle 403 can travel along the path 404 smoothly through the lane-obstruction area without affecting the flow of traffic to the opposite lane.

Fig. 4C schematically illustrates an example schematic diagram of a motion plan for a remote control driving trajectory planning scenario according to an embodiment of this disclosure.

As shown in fig. 4C, in 400C, in the case that the 5G network condition is not met, the vehicle end is difficult to upload the vehicle-mounted video to the cloud in real time, and a remote security officer in remote driving is difficult to obtain a vehicle end view angle video reference required for effectively taking over the vehicle, so that the vehicle needs to be assisted to complete a driving behavior by issuing a trajectory guide line.

For example, in fig. 4C, the same traffic lane in front of the lane where the autonomous vehicle 405 is located is blocked, the autonomous vehicle needs to get rid of the trouble by using the opposite lane, and the remote control driving decision system gives two suggestions for changing lanes to get rid of the trouble by crossing the solid line. Blocking the same flow direction lane ahead of the lane may include a half way road closure.

To do so, the autonomous vehicle 405 generates a bailout clearance request for the vehicle encountering a road closure condition. The automatic driving vehicle 405 sends a escaping request to the cloud end, so that the cloud end responds to the escaping request, and a remote control driving safety worker determines a safety path for escaping the vehicle according to the road environment and the traffic situation of the automatic driving vehicle 405 in the road-side uploaded video. And the cloud remote control driving safety worker finishes manual drawing aiming at the local track guide line according to the safety path to obtain the recommended track. If it is determined that the recommended trajectory check passes, the cloud sends the recommended trajectory to the autonomous vehicle 405. The autonomous vehicle 405 may complete the stranded trip according to the recommended trajectory. For example, autonomous vehicle 405 may travel along path 406.

This completes the description of the motion planning section.

Based on the above, the vehicle-road-cloud integrated planning has advantages in the following aspects for interactive conflict type scenes.

In a road blocking scene, the scene composition of a blocking area is complex, and the blocking area is influenced by frequent shielding of traffic flow, so that the road blocking state and the road event type are effectively identified, and the support of more dimensional information is required. The track planning information generation method provided by the embodiment of the disclosure can provide multi-dimensional information.

The driving area and the path are drawn at the position of the partial road blocking event without lane lines, and the complexity of the blocking area is difficult for a driver to pass, so that the reachable path needs to be determined to pass. For example, a lane-free delineation driving region may include an intersection center region lane-free as a reference.

Part road jam incident takes place on the road that the traffic is intensive or the section of passing is narrow, and the accessible space is limited, meets the condition of lane change or detour, is difficult to pass with the help of the opposite side lane, needs to refine and confirms the regional influence scope width that blocks, confirms whether the vehicle can effectively pass through.

Based on the above contents, the vehicle-road cloud integrated system can effectively exert the advantages of long-term observation of road sides, information multi-dimension and global visual angle, perform full sensing and positioning on road traffic situation and surrounding traffic participants through an integrated sensing means, accurately capture the traffic flow track around the front blocking area of the main vehicle, form a candidate track guide line and speed through large data accumulation, and serve as a global optimization passage suggestion of the main vehicle. By introducing the input of the driver's behavior as a reference, the host vehicle is guided to pass through the lane-blocking area in accordance with the driving behavior of the driver.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.

The above is only an exemplary embodiment, but is not limited thereto, and other trajectory planning information generation methods known in the art may be included as long as the trajectory planning information can be generated.

Fig. 5 schematically shows a block diagram of a trajectory planning information generation apparatus according to an embodiment of the present disclosure.

As shown in fig. 5, the trajectory planning information generating apparatus 500 may include a generating module 510 and a determining module 520.

The generating module 510 is configured to generate at least one candidate trajectory planning information of the autonomous vehicle according to the vehicle road cloud collaborative awareness information and the optimization behavior decision information corresponding to the autonomous vehicle. The vehicle road cloud cooperative sensing information is determined according to at least one of vehicle end sensing information, road end sensing information and cloud end sensing information related to the automatic driving vehicle.

A determining module 520 configured to determine optimized trajectory planning information for the autonomous vehicle from the at least one candidate trajectory planning information according to the trajectory evaluation information.

According to the embodiment of the disclosure, the vehicle cloud collaborative awareness information comprises road traffic situation information and road event position information.

According to an embodiment of the present disclosure, the generation module 510 may include an acquisition sub-module and a generation sub-module.

And the acquisition submodule is used for acquiring auxiliary traffic flow track information corresponding to the automatic driving vehicle according to the road event position information.

And the generation submodule is used for generating at least one candidate track planning information of the automatic driving vehicle according to the auxiliary traffic flow track information and the road traffic situation information.

According to an embodiment of the present disclosure, the acquisition sub-module may include a first determination unit and a first acquisition unit.

The first determining unit is used for determining the to-be-analyzed vehicle road cloud collaborative perception information related to the road event position information from the historical vehicle road cloud collaborative perception information.

The first obtaining unit is used for obtaining auxiliary traffic flow track information corresponding to the automatic driving vehicle according to the road cloud collaborative perception information to be analyzed.

According to an embodiment of the present disclosure, the first obtaining unit may include a first obtaining subunit, a second obtaining subunit, and a third obtaining subunit.

The first obtaining subunit is used for obtaining candidate vehicle track information corresponding to the automatic driving vehicle according to the vehicle road cloud collaborative perception information to be analyzed. The candidate traffic flow trajectory information includes a plurality of candidate trajectories.

And the second obtaining subunit is used for determining the similarity among the candidate tracks to obtain a plurality of similarities.

And the third obtaining subunit is used for determining at least one auxiliary track from the plurality of candidate tracks according to the plurality of similarities, and obtaining auxiliary vehicle track information corresponding to the automatic driving vehicle.

According to the embodiment of the disclosure, the vehicle road cloud collaborative awareness information includes road state information.

According to an embodiment of the present disclosure, the generation submodule may include a second determination unit, a first generation unit, and a second generation unit.

And a second determination unit for determining the route reachability from the auxiliary traffic stream trajectory information in a case where it is determined from the road state information that the road congestion event has occurred in the expected road area. The path reachability characterizes a likelihood of the autonomous vehicle to pass through a congestion area corresponding to a road congestion event based on the current path.

And the first generating unit is used for generating decision information for suggesting the automatic driving vehicle to detour through the blocking area by referring to the recommended track according to the road traffic situation information under the condition of determining that the path is reachable.

And the second generation unit is used for responding to the received decision information and generating at least one candidate track planning information aiming at the automatic driving vehicle according to the auxiliary traffic flow track information.

According to an embodiment of the present disclosure, the determining module 510 may include an obtaining sub-module, a first determining sub-module, and a second determining sub-module.

And the obtaining sub-module is used for evaluating the at least one candidate trajectory planning information according to the trajectory evaluation information to obtain at least one evaluation result. The trajectory estimation information includes at least one of: driving comfort degree evaluation information, reachability evaluation information, safety evaluation information, and traffic efficiency evaluation information.

And the first determining submodule is used for determining an optimized evaluation result according to at least one evaluation result.

And the second determining submodule is used for determining the candidate track planning information corresponding to the optimization evaluation result as the optimized track planning information of the automatic driving vehicle.

According to an embodiment of the present disclosure, the first determination submodule may include a second obtaining unit and a third determining unit.

And the second obtaining unit is used for sequencing at least one evaluation result to obtain a sequencing result.

And the third determining unit is used for determining an optimized evaluation result from the at least one evaluation result according to the sequencing result.

the vehicle-road cloud cooperative sensing information comprises vehicle-end related sensing information, road-end related sensing information and cloud-end related sensing information.

The present disclosure also provides an electronic device, a readable storage medium, a computer program product, an autonomous vehicle, a roadside device, and a cloud-side server according to embodiments of the present disclosure.

According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described above.

According to an embodiment of the present disclosure, a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method as described above.

According to an embodiment of the disclosure, a computer program product comprising a computer program which, when executed by a processor, implements the method as described above.

Fig. 6 illustrates a schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the electronic device 600 comprises a computing unit 601, which may perform various suitable actions and processes according to a computer program stored in a read-only memory (ROM)602 or loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Various components in the electronic device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, a mouse, or the like; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the electronic device 600 to exchange information/data with other devices through a computer network such as an internet and/or various telecommunication networks.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, computing units running various machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 601 performs the respective methods and processes described above, such as the trajectory planning information generation method. For example, in some embodiments, the trajectory planning information generation method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the trajectory planning information generation method described above may be performed. Alternatively, in other embodiments, the calculation unit 601 may be configured to perform the trajectory planning information generation method in any other suitable way (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

According to an embodiment of the present disclosure, there is provided an autonomous vehicle including the electronic device according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, there is provided a roadside apparatus including the electronic apparatus according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a cloud server is provided, which includes the electronic device according to the embodiment of the present disclosure.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server combining a blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A trajectory planning information generation method includes:

generating at least one candidate trajectory planning information of an autonomous vehicle according to vehicle road cloud cooperative sensing information and optimization behavior decision information corresponding to the autonomous vehicle, wherein the vehicle road cloud cooperative sensing information is determined according to at least one of vehicle end sensing information, road end sensing information and cloud end sensing information related to the autonomous vehicle; and

determining optimized trajectory planning information for the autonomous vehicle from the at least one candidate trajectory planning information based on the trajectory evaluation information.

2. The method of claim 1, wherein the vehicle cloud collaborative awareness information includes road traffic situation information and road event location information;

the generating at least one candidate trajectory planning information of the automatic driving vehicle according to the vehicle road cloud collaborative perception information and the optimization behavior decision information corresponding to the automatic driving vehicle comprises the following steps:

acquiring auxiliary traffic flow track information corresponding to the automatic driving vehicle according to the road event position information; and

and generating at least one candidate track planning information of the automatic driving vehicle according to the auxiliary traffic flow track information and the road traffic situation information.

3. The method of claim 2, wherein the obtaining auxiliary traffic trajectory information corresponding to the autonomous vehicle from the road event location information comprises:

determining vehicle road cloud cooperative sensing information to be analyzed related to the road event position information from historical vehicle road cloud cooperative sensing information; and

and obtaining auxiliary traffic flow track information corresponding to the automatic driving vehicle according to the to-be-analyzed vehicle road cloud collaborative perception information.

4. The method according to claim 3, wherein obtaining auxiliary traffic flow trajectory information corresponding to the autonomous vehicle according to the to-be-analyzed vehicle road cloud collaborative awareness information comprises:

obtaining candidate vehicle track information corresponding to the automatic driving vehicle according to the to-be-analyzed vehicle road cloud collaborative perception information, wherein the candidate vehicle flow track information comprises a plurality of candidate tracks;

determining the similarity among the candidate tracks to obtain a plurality of similarities; and

and determining at least one auxiliary track from the candidate tracks according to the similarity to obtain auxiliary vehicle track information corresponding to the automatic driving vehicle.

5. The method according to any one of claims 2-4, wherein the vehicle road cloud collaborative awareness information includes road status information;

wherein the generating at least one candidate trajectory planning information of the autonomous vehicle according to the auxiliary traffic flow trajectory information and the road traffic situation information comprises:

determining, in the event that a road congestion event is determined to occur in an expected road region from the road state information, a path reachability from the auxiliary traffic stream trajectory information, wherein the path reachability characterizes a likelihood of the autonomous vehicle to pass through a congestion region corresponding to the road congestion event based on a current path;

under the condition that the path is determined to be accessible, generating decision information for suggesting the automatic driving vehicle to detour through the blocking area according to the road traffic situation information; and

in response to receiving the decision information, generating at least one candidate trajectory planning information for the autonomous vehicle in accordance with the auxiliary traffic flow trajectory information.

6. The method of any of claims 1-5, wherein the determining optimized trajectory planning information for the autonomous vehicle from the at least one candidate trajectory planning information based on the trajectory assessment information comprises:

evaluating the at least one candidate trajectory planning information according to the trajectory evaluation information to obtain at least one evaluation result, wherein the trajectory evaluation information includes at least one of: driving comfort evaluation information, accessibility evaluation information, safety evaluation information, and traffic efficiency evaluation information;

determining an optimized evaluation result according to the at least one evaluation result; and

and determining candidate track planning information corresponding to the optimization evaluation result as the optimized track planning information of the automatic driving vehicle.

7. The method of claim 6, wherein said determining an optimized evaluation result from said at least one evaluation result comprises:

sequencing the at least one evaluation result to obtain a sequencing result; and

and determining the optimized evaluation result from the at least one evaluation result according to the sequencing result.

8. The method of any of claims 1-7, wherein the vehicle-to-road cloud collaborative awareness information is determined from at least one of vehicle-side awareness information, road-side awareness information, and cloud-side awareness information related to the autonomous vehicle, including:

the vehicle road cloud cooperative perception information comprises vehicle end related perception information, road end related perception information and cloud end related perception information.

9. A trajectory planning information generating apparatus comprising:

the generation module is used for generating at least one candidate track planning information of the automatic driving vehicle according to vehicle road cloud cooperative sensing information and optimized behavior decision information corresponding to the automatic driving vehicle, wherein the vehicle road cloud cooperative sensing information is determined according to at least one of vehicle end sensing information, road end sensing information and cloud end sensing information related to the automatic driving vehicle; and

a determination module to determine optimized trajectory planning information for the autonomous vehicle from the at least one candidate trajectory planning information based on the trajectory evaluation information.

10. The apparatus of claim 9, wherein the vehicle cloud collaborative awareness information includes road traffic situation information and road event location information;

wherein the generating module comprises:

the acquisition sub-module is used for acquiring auxiliary traffic flow track information corresponding to the automatic driving vehicle according to the road event position information; and

11. The apparatus of claim 10, wherein the acquisition submodule comprises:

the first determining unit is used for determining to-be-analyzed vehicle road cloud cooperative sensing information related to the road event position information from historical vehicle road cloud cooperative sensing information; and

and the first obtaining unit is used for obtaining auxiliary traffic flow track information corresponding to the automatic driving vehicle according to the to-be-analyzed vehicle road cloud collaborative perception information.

12. The apparatus of claim 11, wherein the first obtaining unit comprises:

the first obtaining subunit is configured to obtain candidate vehicle trajectory information corresponding to the autonomous vehicle according to the to-be-analyzed vehicle road cloud collaborative awareness information, where the candidate vehicle trajectory information includes multiple candidate trajectories;

the second obtaining subunit is configured to determine similarities between the multiple candidate tracks, so as to obtain multiple similarities; and

and the third obtaining subunit is configured to determine at least one auxiliary track from the plurality of candidate tracks according to the plurality of similarities, and obtain auxiliary vehicle track information corresponding to the autonomous vehicle.

13. The device according to any one of claims 10-12, wherein the vehicle road cloud collaborative awareness information includes road state information;

wherein the generating sub-module comprises:

a second determination unit configured to determine, in a case where it is determined from the road state information that a road congestion event occurs in an expected road area, a path reachability from the auxiliary traffic stream trajectory information, wherein the path reachability represents a possibility that the autonomous vehicle passes through a congestion area corresponding to the road congestion event based on a current path;

the first generation unit is used for generating decision information for suggesting the automatic driving vehicle to detour through the blocking area by referring to the recommended track according to the road traffic situation information under the condition that the path is determined to be reachable; and

a second generating unit, configured to generate, in response to receiving the decision information, at least one candidate trajectory planning information for the autonomous vehicle according to the auxiliary traffic flow trajectory information.

14. The apparatus of any of claims 9-13, wherein the means for determining comprises:

an obtaining sub-module, configured to evaluate the at least one candidate trajectory planning information according to the trajectory evaluation information to obtain at least one evaluation result, where the trajectory evaluation information includes at least one of: driving comfort evaluation information, accessibility evaluation information, safety evaluation information, and traffic efficiency evaluation information;

the first determining submodule is used for determining an optimized evaluation result according to the at least one evaluation result; and

and the second determining submodule is used for determining candidate track planning information corresponding to the optimization evaluation result as the optimized track planning information of the automatic driving vehicle.

15. The apparatus of claim 14, wherein the first determination submodule comprises:

a second obtaining unit, configured to rank the at least one evaluation result to obtain a ranking result; and

a third determining unit, configured to determine the optimized evaluation result from the at least one evaluation result according to the sorting result.

16. The apparatus of any of claims 9-15, wherein the vehicle-to-road cloud collaborative awareness information is determined from at least one of vehicle-side awareness information, road-side awareness information, and cloud-side awareness information related to the autonomous vehicle, including:

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any of claims 1-8.

19. A computer program product comprising a computer program which, when executed by a processor, implements a method according to any one of claims 1 to 8.

20. An autonomous vehicle comprising the electronic device of claim 17.

21. A roadside apparatus comprising the electronic apparatus of claim 17.

22. A cloud server comprising the electronic device of claim 17.