CN117707172A - Decision-making method and device for automatic driving vehicle, equipment and medium - Google Patents

Abstract

The disclosure provides a decision-making method, device, equipment and medium for an automatic driving vehicle, relates to the technical field of artificial intelligence, and particularly relates to the technical field of automatic driving. The implementation scheme is as follows: acquiring scene characteristics of a current driving scene of the automatic driving vehicle; acquiring a track evaluation function based on scene characteristics; determining a plurality of first planned trajectories for the autonomous vehicle by solving a plurality of extrema of the trajectory evaluation function; determining, for each of a plurality of first planned trajectories, an approximation function of a trajectory evaluation function at the first planned trajectory, wherein the approximation function has an extremum; determining a second planned trajectory by solving an extremum of the approximation function based on the first planned trajectory; determining a target planned trajectory from the plurality of second planned trajectories based on the trajectory evaluation function; and determining a control decision for the autonomous vehicle based on the target planned trajectory.

Description

Decision-making method and device for automatic driving vehicle, equipment and medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly to the field of autopilot technology, and in particular to a decision making method, apparatus, vehicle, electronic device, computer readable storage medium and computer program product for autopilot vehicles.

Background

Artificial intelligence is the discipline of studying the process of making a computer mimic certain mental processes and intelligent behaviors (e.g., learning, reasoning, thinking, planning, etc.) of a person, both hardware-level and software-level techniques. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge graph technology and the like.

In the running process of the automatic driving vehicle, a corresponding control decision is needed to be obtained by utilizing an automatic driving decision algorithm according to the current road condition, so that the vehicle can perform reasonable driving operation.

The approaches described in this section are not necessarily approaches that have been previously conceived or pursued. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, the problems mentioned in this section should not be considered as having been recognized in any prior art unless otherwise indicated.

Disclosure of Invention

The present disclosure provides a decision making method, apparatus, vehicle, electronic device, computer readable storage medium and computer program product for an autonomous vehicle.

According to an aspect of the present disclosure, there is provided a decision method of an autonomous vehicle, including: acquiring scene characteristics of a current driving scene of the automatic driving vehicle; acquiring a track evaluation function based on the scene characteristics, wherein the track evaluation function is used for calculating a score of a planned track of the automatic driving vehicle, the score is used for indicating whether the running behavior of the automatic driving vehicle in the current running scene based on the planned track meets a preset condition or not, and the track evaluation function has a plurality of extreme values; determining a plurality of first planned trajectories for the autonomous vehicle by solving a plurality of extrema of the trajectory evaluation function; determining, for each of the plurality of first planned trajectories, an approximation function of the trajectory evaluation function at the first planned trajectory, wherein the approximation function has an extremum; determining a second planned trajectory by solving an extremum of the approximation function based on the first planned trajectory; determining a target planned trajectory from a plurality of second planned trajectories based on the trajectory evaluation function; and determining a control decision for the autonomous vehicle based on the target planned trajectory.

According to an aspect of the present disclosure, there is provided a decision making apparatus of an autonomous vehicle, including: a first acquisition unit configured to acquire scene features of a current driving scene of the autonomous vehicle; a second acquisition unit configured to acquire a trajectory evaluation function based on the scene feature, the trajectory evaluation function being for calculating a score of a planned trajectory of the autonomous vehicle, the score being for indicating whether a traveling behavior of the autonomous vehicle in the current traveling scene based on the planned trajectory satisfies a preset condition, and the trajectory evaluation function having a plurality of extrema; a first determination unit configured to determine a plurality of first planned trajectories for the autonomous vehicle by solving a plurality of extrema of the trajectory evaluation function; a second determining unit configured to determine, for each of the plurality of first planned trajectories, an approximation function of the trajectory evaluation function at the first planned trajectory, wherein the approximation function has one extremum; a third determination unit configured to determine a second planned trajectory by solving an extremum of the approximation function based on the first planned trajectory; a fourth determination unit configured to determine a target planned trajectory from a plurality of second planned trajectories based on the trajectory evaluation function; and a decision unit configured to determine a control decision for the autonomous vehicle based on the target planned trajectory.

According to an aspect of the present disclosure, there is provided an autonomous vehicle comprising a decision making device of an autonomous vehicle as described above.

According to an aspect of the present disclosure, there is provided an electronic apparatus including: 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 automated vehicle decision method described above.

According to an aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the above-described decision method of automatically driving a vehicle.

According to an aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program, when being executed by a processor, is capable of implementing the above-mentioned method of decision making for an autonomous vehicle.

According to one or more embodiments of the present disclosure, the decision accuracy of an autonomous vehicle may be improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The accompanying drawings illustrate exemplary embodiments and, together with the description, serve to explain exemplary implementations of the embodiments. The illustrated embodiments are for exemplary purposes only and do not limit the scope of the claims. Throughout the drawings, identical reference numerals designate similar, but not necessarily identical, elements.

FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, according to an exemplary embodiment of the present disclosure;

FIG. 2 illustrates a flow chart of a decision method for automatically driving a vehicle in accordance with an exemplary embodiment of the present disclosure;

FIG. 3 illustrates a block diagram of a decision making device of an autonomous vehicle according to an exemplary embodiment of the present disclosure;

fig. 4 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one 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 of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the present disclosure, the use of the terms "first," "second," and the like to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of the elements, unless otherwise indicated, and such terms are merely used to distinguish one element from another. In some examples, a first element and a second element may refer to the same instance of the element, and in some cases, they may also refer to different instances based on the description of the context.

The terminology used in the description of the various illustrated examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, the elements may be one or more if the number of the elements is not specifically limited. Furthermore, the term "and/or" as used in this disclosure encompasses any and all possible combinations of the listed items.

In the related art, an optimal trajectory solving problem of an automatic driving vehicle is usually modeled as a convex optimization problem, namely, a trajectory evaluation function in a convex function form is constructed, and then extreme points of the trajectory evaluation function are solved based on a convex optimization algorithm, namely, an optimal planning trajectory can be obtained, and a control decision for the automatic driving vehicle is determined based on the optimal planning trajectory. Because the complexity of the convex function is low, the difficulty of extremum solving is low, and the planned track can be obtained more quickly and efficiently in an automatic driving scene, but the convex function is difficult to accurately and comprehensively represent the track optimization index of the automatic driving vehicle, and the indicated convex solution space is not perfect enough, so that the quality of the planned track of the automatic driving vehicle is poor, and the accuracy of an automatic driving decision is influenced.

Based on the above, the present disclosure provides a control method for an automatic driving vehicle, which constructs a more comprehensive and accurate track evaluation function based on a non-convex function form, initially obtains a plurality of first planned tracks by solving extremum of the track evaluation function, optimizes each first planned track by applying a convex optimization algorithm to obtain a plurality of second planned tracks with higher accuracy, further determines an optimal planned track from the plurality of second planned tracks, and determines a control decision for the automatic driving vehicle efficiently and accurately based on the optimal planned track.

Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented, in accordance with an embodiment of the present disclosure. Referring to fig. 1, the system 100 includes a motor vehicle 110, a server 120, and one or more communication networks 130 coupling the motor vehicle 110 to the server 120.

In an embodiment of the present disclosure, motor vehicle 110 may include a computing device in accordance with an embodiment of the present disclosure and/or be configured to perform a method in accordance with an embodiment of the present disclosure.

The server 120 may run one or more services or software applications that enable the decision making method of automatically driving the vehicle. In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual environments and virtual environments. In the configuration shown in fig. 1, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or a combination thereof that are executable by one or more processors. A user of motor vehicle 110 may in turn utilize one or more client applications to interact with server 120 to utilize the services provided by these components. It should be appreciated that a variety of different system configurations are possible, which may differ from system 100. Accordingly, FIG. 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture that involves virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain virtual storage devices of the server). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

The computing units in server 120 may run one or more operating systems including any of the operating systems described above as well as any commercially available server operating systems. Server 120 may also run any of a variety of additional server applications and/or middle tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and/or event updates received from motor vehicle 110. Server 120 may also include one or more applications to display data feeds and/or real-time events via one or more display devices of motor vehicle 110.

Network 130 may be any type of network known to those skilled in the art that may support data communications using any of a number of available protocols, including but not limited to TCP/IP, SNA, IPX, etc. By way of example only, the one or more networks 130 may be a satellite communications network, a Local Area Network (LAN), an ethernet-based network, a token ring, a Wide Area Network (WAN), the internet, a virtual network, a Virtual Private Network (VPN), an intranet, an extranet, a blockchain network, a Public Switched Telephone Network (PSTN), an infrared network, a wireless network (including, for example, bluetooth, wiFi), and/or any combination of these with other networks.

The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of databases 130 may be used to store information such as audio files and video files. Database 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. Database 130 may be of different types. In some embodiments, the database used by server 120 may be a database, such as a relational database. One or more of these databases may store, update, and retrieve the databases and data from the databases in response to the commands.

In some embodiments, one or more of databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key value stores, object stores, or conventional stores supported by the file system.

Motor vehicle 110 may include a sensor 111 for sensing the surrounding environment. The sensors 111 may include one or more of the following: visual cameras, infrared cameras, ultrasonic sensors, millimeter wave radar, and laser radar (LiDAR). Different sensors may provide different detection accuracy and range. The camera may be mounted in front of, behind or other locations on the vehicle. The vision cameras can capture the conditions inside and outside the vehicle in real time and present them to the driver and/or passengers. In addition, by analyzing the captured images of the visual camera, information such as traffic light indication, intersection situation, other vehicle running state, etc. can be acquired. The infrared camera can capture objects under night vision. The ultrasonic sensor can be arranged around the vehicle and is used for measuring the distance between an object outside the vehicle and the vehicle by utilizing the characteristics of strong ultrasonic directivity and the like. The millimeter wave radar may be installed in front of, behind, or other locations of the vehicle for measuring the distance of an object outside the vehicle from the vehicle using the characteristics of electromagnetic waves. Lidar may be mounted in front of, behind, or other locations on the vehicle for detecting object edges, shape information for object identification and tracking. The radar apparatus may also measure a change in the speed of the vehicle and the moving object due to the doppler effect.

Motor vehicle 110 may also include a communication device 112. The communication device 112 may include a satellite positioning module capable of receiving satellite positioning signals (e.g., beidou, GPS, GLONASS, and GALILEO) from satellites 141 and generating coordinates based on these signals. The communication device 112 may also include a module for communicating with the mobile communication base station 142, and the mobile communication network may implement any suitable communication technology, such as the current or evolving wireless communication technology (e.g., 5G technology) such as GSM/GPRS, CDMA, LTE. The communication device 112 may also have a Vehicle-to-Everything (V2X) module configured to enable, for example, vehicle-to-Vehicle (V2V) communication with other vehicles 143 and Vehicle-to-Infrastructure (V2I) communication with Infrastructure 144. In addition, the communication device 112 may also have a module configured to communicate with a user terminal 145 (including but not limited to a smart phone, tablet computer, or wearable device such as a watch), for example, by using a wireless local area network or bluetooth of the IEEE802.11 standard. With the communication device 112, the motor vehicle 110 can also access the server 120 via the network 130.

Motor vehicle 110 may also include a control device 113. The control device 113 may include a processor, such as a Central Processing Unit (CPU) or a Graphics Processing Unit (GPU), or other special purpose processor, etc., in communication with various types of computer readable storage devices or mediums. The control device 113 may include an autopilot system for automatically controlling various actuators in the vehicle. The autopilot system is configured to control a powertrain, steering system, braking system, etc. of a motor vehicle 110 (not shown) via a plurality of actuators in response to inputs from a plurality of sensors 111 or other input devices to control acceleration, steering, and braking, respectively, without human intervention or limited human intervention. Part of the processing functions of the control device 113 may be implemented by cloud computing. For example, some of the processing may be performed using an onboard processor while other processing may be performed using cloud computing resources. The control device 113 may be configured to perform a method according to the present disclosure. Furthermore, the control means 113 may be implemented as one example of a computing device on the motor vehicle side (client) according to the present disclosure.

The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with the present disclosure.

Fig. 2 shows a flow chart of a decision method 200 of an autonomous vehicle according to an exemplary embodiment of the present disclosure. As shown in fig. 2, the method 200 includes:

step S201, obtaining scene characteristics of a current running scene of the automatic driving vehicle;

step S202, acquiring a track evaluation function based on the scene characteristics, wherein the track evaluation function is used for calculating a score of a planned track of the automatic driving vehicle, the score is used for indicating whether the running behavior of the automatic driving vehicle in the current running scene based on the planned track meets a preset condition, and the track evaluation function has a plurality of extreme values;

step S203, determining a plurality of first planned trajectories for the autonomous vehicle by solving a plurality of extrema of the trajectory evaluation function;

step S204, for each first planned track in the plurality of first planned tracks, determining an approximate function of the track evaluation function at the first planned track, wherein the approximate function has an extreme value;

step S205, determining a second planning track by solving the extreme value of the approximation function based on the first planning track;

step S206, determining a target planned track from a plurality of second planned tracks based on the track evaluation function; and

Step S207, determining a control decision for the autonomous vehicle based on the target planned trajectory.

By applying the above-described method 200, it is possible to more comprehensively and accurately indicate the evaluation index of the trajectory of the autonomous vehicle using the trajectory evaluation function in the form of a non-convex function, i.e., calculate the score of the trajectory more accurately based on the function. The plurality of first planning tracks are obtained by initially solving a plurality of extremums of the track evaluation function, the plurality of first planning tracks can be used for indicating a plurality of local optimal solutions of the function, then an approximate function in a convex function form is constructed for each first planning track, and a second planning track with higher accuracy can be further optimized on the basis of the first planning track by solving the extremums of the approximate function, so that the plurality of second planning tracks can be used for indicating the plurality of local optimal solutions of the track evaluation function. On the basis, the global optimal solution of the track evaluation function can be determined from the plurality of second planning tracks to obtain an optimal target planning track, and the control decision accuracy of the automatic driving vehicle is improved based on the optimal target planning track.

Generally, the solution of the global optimal solution of the non-convex function is difficult and occupies more computing resources, while the convex function is more convenient for solving the optimal solution. By applying the method 200, the optimal planning track can be obtained by combining the non-convex function solving calculation based on the track evaluation function and the convex function solving calculation based on the approximate function, the solution space of the planning track is more accurately indicated by using the non-convex track evaluation function, the optimizing efficiency is improved, the hardware resources are saved, and the requirement on the planning efficiency in the automatic driving application scene is fully met.

In some examples, the planned trajectory of the autonomous vehicle may include information of a planned position and a planned speed of the vehicle for a predetermined length of time in the future.

In some examples, the scene features in step S201 may include information of a position, a speed, an orientation angle, a wheel rotation angle, etc. of the autonomous vehicle itself, and may further include environmental perception information acquired by various types of sensors carried by the autonomous vehicle, such as road shape data, movement state data of other surrounding traffic objects (e.g., vehicles, pedestrians, etc.), traffic guidance signal data, etc. In some examples, the scene characteristics may also include obstacle prediction information for the current driving scene, such as a predicted trajectory of the obstacle, and the like. The present disclosure is not limited to the specific content and form of the scene features as long as the control decisions of the autonomous vehicle can be influenced.

In some examples, scene features may be encoded as feature vectors using a particular encoding scheme to project the scene features in raw form into a high-dimensional space for modeling and solving using various types of algorithms.

In some examples, acquiring the trajectory evaluation function in step S202 may include: and constructing a track evaluation function under the current driving scene based on the scene characteristics. In this case, the planned trajectory of the autonomous vehicle may be used as a function argument, and the trajectory scoring rule may be indicated by the trajectory evaluation function, so that the trajectory scoring dependent variable can be calculated based on the planned trajectory.

In some examples, an initial template of the track evaluation function may be pre-constructed, and the scene characteristics of the driving scene and the planned track of the automatic driving vehicle are taken as function arguments. In this case, in step S202, an initial template of the track evaluation function may be obtained first, and after substituting the scene features of the current driving scene, the track evaluation function only including the planned track variable may be obtained, and based on this, further solution may be performed, so that the efficiency may be improved.

In some examples, the preset conditions that the autonomous vehicle needs to meet based on the planned trajectory's driving behavior may cover dimensions of whether the vehicle complies with regulations, the actual ride quality of the vehicle, the vehicle driving safety factor, the vehicle intelligent reaction speed, and the like. For example, the preset condition may include: the vehicles do not run the red light, the vehicles do not brake suddenly, the vehicles do not run out of the road, and the like.

According to some embodiments, the similarity between any two first planned trajectories of the plurality of first planned trajectories is not greater than a second preset threshold. Therefore, two or more first planning tracks can be prevented from falling into the same local preferred domain of the non-convex function, so that a plurality of first planning tracks can more accurately indicate a plurality of local preferred solutions of the track evaluation function, and the solving accuracy is improved.

According to some embodiments, determining a plurality of first planned trajectories for the autonomous vehicle by solving a plurality of extrema of the trajectory evaluation function in step S203 comprises: solving extremum of the track evaluation function by using a heuristic algorithm to obtain a plurality of candidate tracks; and determining the plurality of first planned trajectories from the plurality of candidate trajectories, wherein each of the plurality of first planned trajectories satisfies the following condition: and at least one similar track corresponding to the first planning track exists in the plurality of candidate tracks, wherein the similarity between the similar track and the first planning track is not smaller than a third preset threshold value. The initial solution set formed by a plurality of candidate tracks can be more conveniently and accurately defined by solving the non-convex function through the heuristic algorithm, the local preferred domain of the track evaluation function is primarily indicated through the initial solution set, then a more similar solution is selected in the local preferred domain, the range of the local preferred solution is more accurately indicated through the similarity between the initial solutions, the first planning track is more conveniently and efficiently determined from the range, the iteration times of the heuristic algorithm can be reduced while the comprehensiveness and accuracy of the solution of the heuristic algorithm are fully utilized, and the first planning track is more efficiently determined through fewer hardware resources.

According to some embodiments, the heuristic algorithm comprises at least one of: evolutionary algorithm, particle swarm algorithm, simulated annealing algorithm, immune algorithm, and ant colony algorithm. By applying a heuristic algorithm based on a random search principle to solve a non-convex track cost function, possible local preferred domains can be more efficiently and comprehensively found, and the solving accuracy is improved.

In some examples, when a genetic algorithm is used to solve a locally optimal solution of the trajectory evaluation function, the initial randomly planned trajectory may be processed by an encoding operator, a crossover operator, a mutation operator, and a selection operator, and iterated to obtain an initial solution. On this basis, the similarity between the solutions (i.e., the individuals in the genetic algorithm) obtained by iteration may be used as a termination condition of the genetic algorithm, and when there are multiple groups of individuals satisfying a preset similarity condition (for example, the similarity may be not less than a third preset threshold), multiple first planned trajectories corresponding to the multiple groups of individuals may be determined.

In some examples, multiple computing units may be used to concurrently compute the evaluation function of each feasible solution in the heuristic algorithm (e.g., fitness function of individuals in each population in the genetic algorithm) so as to improve the solution efficiency and adapt to the requirement for the decision efficiency in the autopilot application scenario.

According to some embodiments, determining an approximation function of the trajectory evaluation function at the first planned trajectory in step S2044 comprises: determining a second-order taylor series of the trajectory evaluation function at the first planned trajectory; and determining the approximation function based on the second-order taylor series. Thus, each first planned trajectory can be used as an expansion point, and the second-order taylor expansion can be applied to the expansion point to obtain an approximate function which can approximate the trajectory evaluation function, so that the method is simpler and more efficient.

In some examples, the approximation function capable of approximating the trajectory evaluation function near each first planned trajectory may be determined by other means, and may be determined based on an exponential function or may be obtained by applying a relaxation variable method, for example, in addition to the convex function in the form of a polynomial using taylor expansion.

According to some embodiments, solving the extremum of the approximation function based on the first planned trajectory in step S205, determining a second planned trajectory comprises: determining a first optimization step based on derivative values of the approximation function at a first planned trajectory; determining a first iteration track based on the first planned track and the first optimization step; and determining the second planned trajectory from the first planned trajectory and the first iterative trajectory based on the trajectory evaluation function. Therefore, the optimizing step length of the convex optimization can be determined based on the derivative value, optimizing efficiency is improved, and meanwhile the error of an optimal solution is avoided.

In some examples, the determining of the optimization step may be repeated based on the above manner to iterate through multiple rounds, and the optimal point is determined based on the function values corresponding to the multiple iteration points, so as to improve the solving accuracy.

In some examples, the optimization step may be determined based on second derivative information of the approximation function, thereby converging more quickly to an optimal point. In some examples, the second derivative information of the function may also be approximated by constructing a quasi-newton matrix to further enhance computational efficiency.

According to some embodiments, the determining a first iteration trajectory based on the first planned trajectory and the first optimization step comprises: determining an initial iteration track based on the first planned track and the first optimization step; in response to determining that a difference between the track evaluation function value corresponding to the first planned track and the track evaluation function value corresponding to the initial iterative track is less than a first preset threshold, reducing the first optimization step; determining the updated first iterative track based on the first planned track and the reduced first optimization step; and determining the initial iteration track as the first iteration track in response to determining that a difference value between the track evaluation function value corresponding to the first planning track and the track evaluation function value corresponding to the initial iteration track is not smaller than the first preset threshold. Therefore, the optimization step length can be limited based on the enough descending condition of the function value, the function value obtained by a new iteration point (namely, the initial iteration point) can be fully descended, the rationality of the optimization step length is improved as much as possible, and the optimizing efficiency is improved.

In some examples, the optimization step may be further defined based on a curvature condition between an initial point (e.g., the first planned trajectory in the above step) and an iterative point (e.g., the first iterative trajectory in the above step), that is, an iterative curvature is calculated based on a difference between the initial point and the iterative point and a difference between a function value of the initial point and a function value of the iterative point, and the rationality of the optimization step is improved by configuring a preset rule to define that the iterative curvature corresponding to each iterative step satisfies a certain condition, so that the efficiency and accuracy of the optimization solution are improved.

In some examples, determining the target planned trajectory from the plurality of second planned trajectories based on the trajectory evaluation function in step S206 may include: and calculating the score corresponding to each second planning track based on the track evaluation function, and determining the second planning track with the highest score as the target planning track.

In some examples, the second planned trajectory may be further checked based on a certain preset condition, so as to eliminate the second planned trajectory that does not meet the requirement, thereby improving the decision accuracy.

According to an aspect of the present disclosure, there is also provided a decision making apparatus of an autonomous vehicle. Fig. 3 shows a block diagram of a decision making apparatus 300 of an autonomous vehicle according to an exemplary embodiment of the present disclosure. As shown in fig. 3, the apparatus 300 includes:

A first acquisition unit 301 configured to acquire scene features of a current driving scene of the autonomous vehicle;

a second obtaining unit 302 configured to obtain a trajectory evaluation function based on the scene feature, the trajectory evaluation function being used to calculate a score of a planned trajectory of the autonomous vehicle, the score being used to indicate whether a driving behavior of the autonomous vehicle in the current driving scene based on the planned trajectory satisfies a preset condition, and the trajectory evaluation function having a plurality of extrema;

a first determining unit 303 configured to determine a plurality of first planned trajectories for the autonomous vehicle by solving a plurality of extrema of the trajectory evaluation function;

a second determining unit 304 configured to determine, for each of the plurality of first planned trajectories, an approximation function of the trajectory evaluation function at the first planned trajectory, wherein the approximation function has one extremum;

a third determining unit 305 configured to determine a second planned trajectory by solving an extremum of the approximation function based on the first planned trajectory;

a fourth determining unit 306 configured to determine a target planned trajectory from a plurality of second planned trajectories based on the trajectory evaluation function; and

A decision unit 307 configured to determine a control decision for the autonomous vehicle based on the target planned trajectory.

According to some embodiments, the similarity between any two first planned trajectories of the plurality of first planned trajectories is not greater than a second preset threshold.

According to some embodiments, the first determining unit 303 comprises: a solving subunit configured to solve the extremum of the trajectory evaluation function using a heuristic algorithm to obtain a plurality of candidate trajectories; and a determining subunit configured to determine the plurality of first planned trajectories from the plurality of candidate trajectories, wherein each of the plurality of first planned trajectories satisfies the following condition: and at least one similar track corresponding to the first planning track exists in the plurality of candidate tracks, wherein the similarity between the similar track and the first planning track is not smaller than a third preset threshold value.

According to some embodiments, the heuristic algorithm comprises at least one of: evolutionary algorithm, particle swarm algorithm, simulated annealing algorithm, immune algorithm, and ant colony algorithm.

According to some embodiments, the second determining unit 304 comprises: a second determination subunit configured to determine a second order taylor series of the trajectory evaluation function at the first planned trajectory; and a third determination subunit configured to determine the approximation function based on the second-order taylor series.

According to some embodiments, the third determining unit 305 comprises: a fourth determination subunit configured to determine a first optimization step based on derivative values of the approximation function at the first planned trajectory; a fifth determination subunit configured to determine a first iteration track based on the first planned track and the first optimization step; and a sixth determination subunit configured to determine the second planned trajectory from the first planned trajectory and the first iterative trajectory based on the trajectory evaluation function.

According to some embodiments, the fifth determining subunit is configured to: determining an initial iteration track based on the first planned track and the first optimization step; in response to determining that a difference between the track evaluation function value corresponding to the first planned track and the track evaluation function value corresponding to the initial iterative track is less than a first preset threshold, reducing the first optimization step; determining the updated first iterative track based on the first planned track and the reduced first optimization step; and determining the initial iteration track as the first iteration track in response to determining that a difference value between the track evaluation function value corresponding to the first planning track and the track evaluation function value corresponding to the initial iteration track is not smaller than the first preset threshold.

The operation of the units 301-307 of the decision device 300 for autonomous vehicles is similar to the operation of the steps S201-S207 described above and will not be described in detail here.

According to an aspect of the present disclosure, there is also provided an autonomous vehicle comprising the decision device 300 of an autonomous vehicle as described above.

According to an aspect of the present disclosure, there is also provided an electronic apparatus including: 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 automated vehicle decision method described above.

According to an aspect of the present disclosure, there is also provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the above-described method of determining an autonomous vehicle.

According to an aspect of the present disclosure, there is also provided a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned method of determining an autonomous vehicle.

Referring to fig. 4, a block diagram of an electronic device 400 that may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, 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. 4, the apparatus 400 includes a computing unit 401 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 402 or a computer program loaded from a storage unit 408 into a Random Access Memory (RAM) 403. In RAM 403, various programs and data required for the operation of device 400 may also be stored. The computing unit 401, ROM 402, and RAM 403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

Various components in device 400 are connected to I/O interface 405, including: an input unit 406, an output unit 407, a storage unit 408, and a communication unit 409. The input unit 406 may be any type of device capable of inputting information to the device 400, the input unit 406 may receive input numeric or character information and generate key signal inputs related to user settings and/or function control of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone, and/or a remote control. The output unit 407 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, video/audio output terminals, vibrators, and/or printers. Storage unit 408 may include, but is not limited to, magnetic disks, optical disks. The communication unit 409 allows the device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth devices, 802.11 devices, wiFi devices, wiMax devices, cellular communication devices, and/or the like.

The computing unit 401 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 401 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the decision method of an autonomous vehicle. For example, in some embodiments, the decision-making method of automatically driving the vehicle may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 400 via the ROM 402 and/or the communication unit 409. When the computer program is loaded into RAM 403 and executed by computing unit 401, one or more steps of the above-described autonomous vehicle decision method may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the decision method of the autonomous vehicle by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On 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, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code 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 code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. 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. The 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 pointing device (e.g., a mouse or 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 may 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 input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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), the internet, and blockchain networks.

The computer system may include a client and a server. The client and server are typically 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 incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

While embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the methods, systems, and apparatus described above are merely illustrative embodiments or examples and that the scope of the present disclosure is not limited by these embodiments or examples. Various elements of the embodiments or examples may be omitted or replaced with equivalent elements thereof. Furthermore, the steps may be performed in a different order than described in the present disclosure. Further, various elements of the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced by equivalent elements that appear after the disclosure.

Claims (18)

1. A method of automatically driving a vehicle, comprising:

acquiring scene characteristics of a current driving scene of the automatic driving vehicle;

Acquiring a track evaluation function based on the scene characteristics, wherein the track evaluation function is used for calculating a score of a planned track of the automatic driving vehicle, the score is used for indicating whether the running behavior of the automatic driving vehicle in the current running scene based on the planned track meets a preset condition or not, and the track evaluation function has a plurality of extreme values;

determining a plurality of first planned trajectories for the autonomous vehicle by solving a plurality of extrema of the trajectory evaluation function;

for each first planned trajectory of the plurality of first planned trajectories,

determining an approximation function of the trajectory evaluation function at the first planned trajectory, wherein the approximation function has an extremum;

determining a second planned trajectory by solving an extremum of the approximation function based on the first planned trajectory;

determining a target planned trajectory from a plurality of second planned trajectories based on the trajectory evaluation function; and

a control decision for the autonomous vehicle is determined based on the target planned trajectory.

2. The method of claim 1, wherein a similarity between any two of the plurality of first planned trajectories is not greater than a second preset threshold.

3. The method of claim 1 or 2, wherein the determining a plurality of first planned trajectories for the autonomous vehicle by solving a plurality of extrema of the trajectory evaluation function comprises:

solving extremum of the track evaluation function by using a heuristic algorithm to obtain a plurality of candidate tracks; and

determining the plurality of first planned trajectories from the plurality of candidate trajectories, wherein each of the plurality of first planned trajectories satisfies the following condition:

and at least one similar track corresponding to the first planning track exists in the plurality of candidate tracks, wherein the similarity between the similar track and the first planning track is not smaller than a third preset threshold value.

4. The method of claim 3, wherein the heuristic algorithm comprises at least one of:

evolutionary algorithm, particle swarm algorithm, simulated annealing algorithm, immune algorithm, and ant colony algorithm.

5. The method of any of claims 1-4, wherein said determining an approximation function of said trajectory evaluation function at the first planned trajectory comprises:

determining a second-order taylor series of the trajectory evaluation function at the first planned trajectory; and

The approximation function is determined based on the second-order taylor series.

6. The method of any of claims 1-5, wherein said solving the extremum of the approximation function based on the first planned trajectory, determining a second planned trajectory comprises:

determining a first optimization step based on derivative values of the approximation function at a first planned trajectory;

determining a first iteration track based on the first planned track and the first optimization step; and

the second planned trajectory is determined from the first planned trajectory and the first iterative trajectory based on the trajectory evaluation function.

7. The method of claim 6, wherein the determining a first iteration track based on the first planned track and the first optimization step comprises:

determining an initial iteration track based on the first planned track and the first optimization step;

in response to determining that a difference between the trajectory evaluation function value corresponding to the first planned trajectory and the trajectory evaluation function value corresponding to the initial iterative trajectory is less than a first preset threshold,

reducing the first optimization step;

determining the updated first iterative track based on the first planned track and the reduced first optimization step; and

And determining the initial iterative track as the first iterative track in response to determining that a difference value between the track evaluation function value corresponding to the first planning track and the track evaluation function value corresponding to the initial iterative track is not smaller than the first preset threshold.

8. A decision making device for an autonomous vehicle, comprising:

a first acquisition unit configured to acquire scene features of a current driving scene of the autonomous vehicle;

a second acquisition unit configured to acquire a trajectory evaluation function based on the scene feature, the trajectory evaluation function being for calculating a score of a planned trajectory of the autonomous vehicle, the score being for indicating whether a traveling behavior of the autonomous vehicle in the current traveling scene based on the planned trajectory satisfies a preset condition, and the trajectory evaluation function having a plurality of extrema;

a first determination unit configured to determine a plurality of first planned trajectories for the autonomous vehicle by solving a plurality of extrema of the trajectory evaluation function;

a second determining unit configured to determine, for each of the plurality of first planned trajectories, an approximation function of the trajectory evaluation function at the first planned trajectory, wherein the approximation function has one extremum;

A third determination unit configured to determine a second planned trajectory by solving an extremum of the approximation function based on the first planned trajectory;

a fourth determination unit configured to determine a target planned trajectory from a plurality of second planned trajectories based on the trajectory evaluation function; and

a decision unit configured to determine a control decision for the autonomous vehicle based on the target planned trajectory.

9. The apparatus of claim 8, wherein a similarity between any two of the plurality of first planned trajectories is not greater than a second preset threshold.

10. The apparatus of claim 8 or 9, wherein the first determining unit comprises:

a solving subunit configured to solve the extremum of the trajectory evaluation function using a heuristic algorithm to obtain a plurality of candidate trajectories; and

a determining subunit configured to determine the plurality of first planned trajectories from the plurality of candidate trajectories, wherein each of the plurality of first planned trajectories satisfies the following condition:

and at least one similar track corresponding to the first planning track exists in the plurality of candidate tracks, wherein the similarity between the similar track and the first planning track is not smaller than a third preset threshold value.

11. The apparatus of claim 10, wherein the heuristic algorithm comprises at least one of:

evolutionary algorithm, particle swarm algorithm, simulated annealing algorithm, immune algorithm, and ant colony algorithm.

12. The apparatus of any of claims 8-11, wherein the second determining unit comprises:

a second determination subunit configured to determine a second order taylor series of the trajectory evaluation function at the first planned trajectory; and

a third determination subunit configured to determine the approximation function based on the second-order taylor series.

13. The apparatus of any of claims 8-12, wherein the third determination unit comprises:

a fourth determination subunit configured to determine a first optimization step based on derivative values of the approximation function at the first planned trajectory;

a fifth determination subunit configured to determine a first iteration track based on the first planned track and the first optimization step; and

a sixth determination subunit configured to determine the second planned trajectory from the first planned trajectory and the first iterative trajectory based on the trajectory evaluation function.

14. The apparatus of claim 13, wherein the fifth determination subunit is configured to:

Determining an initial iteration track based on the first planned track and the first optimization step;

in response to determining that a difference between the trajectory evaluation function value corresponding to the first planned trajectory and the trajectory evaluation function value corresponding to the initial iterative trajectory is less than a first preset threshold,

reducing the first optimization step;

determining the updated first iterative track based on the first planned track and the reduced first optimization step; and

and determining the initial iterative track as the first iterative track in response to determining that a difference value between the track evaluation function value corresponding to the first planning track and the track evaluation function value corresponding to the initial iterative track is not smaller than the first preset threshold.

15. An autonomous vehicle comprising the apparatus of any of claims 8-14.

16. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the method comprises the steps of

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 1-7.

17. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-7.

18. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method according to any of claims 1-7.