Driving decision generation method and device, electronic equipment and storage medium

Abstract

The application provides a driving decision generation method and device, electronic equipment and a storage medium. Path information is obtained, the path information being a navigation path between a starting point and an ending point. Visual perception information is obtained, the visual perception information being used to represent environmental information around a vehicle. A driving decision is generated according to the path information and the visual perception information, the driving decision being used to control the vehicle to drive in a corresponding lane. In the embodiment of the application, the driving decision is generated according to the navigation path and the visual perception information. The navigation path in the embodiment of the application is a low-precision navigation, and the visual perception information is environmental information obtained by a vehicle-mounted camera. That is, the embodiment of the application does not require a high-precision map and a high-precision sensor, but only requires a low-cost navigation program and a camera provided by the vehicle, thereby reducing the cost of using the vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of assisted driving, in particular to a driving decision generation method and device, electronic equipment and a storage medium. BACKGROUND

[0002] With the continuous development of automobile technology, more and more vehicles are equipped with assisted driving functions to enhance the safety of vehicle driving. The city navigation function in assisted driving cannot be separated from effective path planning, which includes but is not limited to intersection lane selection decision and lane change decision.

[0003] In the related art, effective lane selection and lane change control are realized based on route data provided by navigation combined with laser radar perception information, so as to realize path planning.

[0004] However, the path planning scheme in the related art requires high sensors and needs to use customized navigation maps, which increases the cost of using vehicles.

[0005] It should be pointed out that the information disclosed in the background section of the present application is only intended to deepen the understanding of the general background of the present application, and should not be regarded as acknowledging or implying in any form that the information constitutes prior art known to those skilled in the art. SUMMARY

[0006] Therefore, the present application provides a driving decision generation method and device, electronic equipment and a storage medium to solve the problem of high sensor requirement and the need to use customized navigation maps in the path planning scheme in the prior art, which increases the cost of using vehicles.

[0007] In a first aspect, the embodiments of the present application provide a driving decision generation method, comprising:

[0008] obtaining path information, the path information being a navigation path between a starting point and an ending point;

[0009] obtaining visual perception information, the visual perception information being used to represent environmental information around the vehicle;

[0010] generating a driving decision according to the path information and the visual perception information, the driving decision being used to control the vehicle to drive in a corresponding lane.

[0011] In the embodiments of the present application, the driving decision is generated according to the navigation path and the visual perception information. The navigation path in the embodiments of the present application is a low-precision navigation, and the visual perception information is environmental information obtained by a vehicle-mounted camera. That is, the embodiments of the present application do not need a high-precision map and a high-precision sensor, but only need a low-cost navigation program and a camera provided by the vehicle, thereby reducing the cost of using vehicles.

[0012] In a possible implementation, the acquiring the path information comprises:

[0013] acquiring a navigation route between the start point and the end point;

[0014] dividing the navigation route according to turning information to obtain the path information, the turning information being at least one turning node in the navigation route.

[0015] In the embodiment of the application, the navigation route between the start point and the end point is divided according to the turning information to obtain the path information, and the turning information is at least one turning node in the navigation route. It can be understood that, by dividing the navigation route, accurate path information and turning nodes can be obtained, so as to facilitate the vehicle to make a lane selection decision at the turning node.

[0016] In a possible implementation, the generating the driving decision according to the path information and the visual perception information comprises:

[0017] obtaining a set of driving trajectories of the vehicle according to the visual perception information;

[0018] selecting a target driving trajectory from the set of driving trajectories according to the path information and a preset driving rule;

[0019] generating the driving decision according to the target driving trajectory.

[0020] In the embodiment of the application, the set of driving trajectories of the vehicle is obtained according to the visual perception information, and the target driving trajectory is selected from the set of driving trajectories according to the path information and the preset driving rule. It can be understood that, by the visual perception information, it can be determined which trajectories can be driven in front, and the set of trajectories is the set of driving trajectories, and then the best driving trajectory can be selected from the set of driving trajectories according to the path information and the preset driving rule.

[0021] In a possible implementation, the obtaining the set of driving trajectories of the vehicle according to the visual perception information comprises:

[0022] calculating a probability of the vehicle driving in each driving trajectory according to the visual perception information, and generating the set of driving trajectories of the vehicle.

[0023] In the embodiment of the application, after it is determined which trajectories can be driven in front according to the visual perception information, the probability of the vehicle driving in each driving trajectory can be calculated, and the set of driving trajectories of the vehicle is obtained according to the probability.

[0024] In a possible implementation, the calculating the probability of the vehicle driving in each driving trajectory according to the visual perception information comprises:

[0025] according to a formula calculating a probability of the vehicle driving on each driving trajectory, wherein p is the probability of the vehicle driving on each driving trajectory, x is a trajectory on which the vehicle can possibly drive in the future, y is one of the trajectories on which the vehicle can possibly drive in the future, and t is the number of trajectories on which the vehicle can possibly drive in the future.

[0026] In the embodiments of the present application, the probability of the vehicle driving on each trajectory that can possibly be driven in the future is calculated according to the formula, which can accelerate the calculation speed and improve the corresponding speed.

[0027] In a possible implementation, the generating the driving decision according to the path information and the visual perception information comprises:

[0028] determining whether a turn or a lane change is needed according to the path information and the visual perception information;

[0029] if the turn or the lane change is needed, generating the driving decision according to the path information and the visual perception information.

[0030] In the embodiments of the present application, before the driving decision is generated, it is determined whether the turn or the lane change is needed, and only when the turn or the lane change is needed, the driving decision is generated according to the path information and the visual perception information. It can be understood that when the vehicle can drive straight in the current lane, the vehicle does not need to be controlled additionally, and in this case, the driving decision is not generated, so that the computing power can be saved without affecting the driving safety.

[0031] In a possible implementation, the determining whether the turn or the lane change is needed according to the path information and the visual perception information comprises:

[0032] determining a current driving lane of the vehicle and a lane congestion situation according to the visual perception information;

[0033] determining whether the turn or the lane change is needed according to the path information, the current driving lane of the vehicle and the lane congestion situation.

[0034] In the embodiments of the present application, the way of determining whether the turn or the lane change is needed is to determine the lane congestion situation according to the visual perception information, so as to determine whether the turn or the lane change is needed according to the path information, the current driving lane of the vehicle and the lane congestion situation. It can be understood that whether the turn or the lane change is needed can be determined according to the road congestion situation and the path information.

[0035] In a second aspect, the embodiments of the present application provide a driving decision generation device, comprising:

[0036] a path information acquisition module configured to acquire path information, the path information being a navigation path between a starting point and an ending point;

[0037] obtain visual perception information, the visual perception information being used to represent environmental information around the vehicle;

[0038] generate a driving decision according to the path information and the visual perception information, the driving decision being used to control the vehicle to drive in a corresponding lane.

[0039] In a third aspect, an electronic device is provided, comprising:

[0040] a processor;

[0041] a memory;

[0042] a communication unit configured to establish a communication channel;

[0043] and a computer program, wherein the computer program is stored in the memory, and the computer program comprises instructions, which, when executed on the processor, cause the electronic device to perform the method of any one of the first aspect.

[0044] In a fourth aspect, a computer-readable storage medium is provided, comprising a stored program, wherein the program, when executed, controls a device on which the computer-readable storage medium is located to perform the method of any one of the first aspect.

[0045] It can be understood that the driving decision generation apparatus provided in the second aspect, the electronic device provided in the third aspect, and the computer-readable storage medium provided in the fourth aspect are used to execute the method provided in the present application. Therefore, the beneficial effects that can be achieved thereby can refer to the beneficial effects in the corresponding method, which will not be described here again. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0047] Figure 1 a driving decision generation method provided in the embodiments of the present application;

[0048] Figure 2 a path division schematic diagram provided in the embodiments of the present application;

[0049] Figure 3 a vehicle turning driving trajectory set schematic diagram provided in the embodiments of the present application;

[0050] Figure 4 A driving trajectory set diagram of vehicle lane changing provided by an embodiment of the present application;

[0051] Figure 5 A structural diagram of a driving decision generation device provided by an embodiment of the present application;

[0052] Figure 6 A structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to better understand the technical solutions of the present application, the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0054] It should be clear that the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0055] The terms used in the embodiments of the present application are only for the purpose of describing the specific embodiments, and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0056] It should be understood that the term "and / or" used herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are a "or" relationship.

[0057] With the continuous development of technology in the field of automobiles, more and more cars are equipped with auxiliary driving functions to achieve the purpose of enhancing the safe driving ability of vehicles. The city navigation function in auxiliary driving cannot be separated from effective path planning, which includes but is not limited to intersection lane selection decision and lane changing decision.

[0058] In the related art, based on the route data provided by navigation, combined with laser radar perception information, effective lane selection and lane changing control are realized, so as to realize path planning.

[0059] However, the path planning scheme in the related art requires high sensors, and needs to use customized navigation maps, which increases the cost of using vehicles.

[0060] To solve the above problems, the embodiment of the present application provides a driving decision generation method, which generates a driving decision according to a navigation path and visual perception information. The navigation path in the embodiment of the present application is low-precision navigation, and the visual perception information is environmental information obtained by a vehicle-mounted camera. That is, the embodiment of the present application does not need a high-precision map and a high-precision sensor, but only needs a low-cost navigation program and a camera provided by a vehicle, thereby reducing the cost of using a vehicle. Details are described below in combination with the drawings and specific embodiments.

[0061] Referring to Figure 1 , a flowchart of a driving decision generation method provided by the embodiment of the present application is shown. As shown in the figure, the method mainly includes the following steps. Figure 1

[0062] Step S101: Obtain path information.

[0063] Specifically, the driving decision generation device obtains path information, which is a navigation path between a starting point and a destination. The starting point is a starting point set by a user in a navigation map, and the destination is a destination set by the user in the navigation map.

[0064] In a possible implementation, the driving decision generation device obtains a navigation route between the starting point and the destination, divides the navigation route according to turning information, and obtains the path information, wherein the turning information is at least one turning node in the navigation route.

[0065] For example, a navigation route (path) is from A to B, the starting point is A, and the destination is B. The entire navigation route includes m large road segments (steps), each large road segment is connected by turning information (icon_type) of a road segment, and each large road segment includes n small road segments (links), each small road segment is connected by a main navigation action (main_action) and an auxiliary navigation action (assist_action). The main navigation action includes left turn, right turn, straight, etc., and the auxiliary navigation action includes entering a main road, entering an auxiliary road, entering a ramp, reaching a service area, etc.

[0066] It can be understood that the navigation route is divided according to the turning information to obtain m large road segments, and each large road segment is divided according to intersection information to obtain n small road segments. The m large road segments and the n small road segments can form the path information in the embodiment of the present application.

[0067] For ease of understanding, the embodiment of the present application further provides a path division schematic diagram.

[0068] Referring to Figure 2 , a path division schematic diagram provided by the embodiment of the present application is shown. As shown in the figure, Figure 2 ​The navigation route shown in a of FIG. 1 is from the start point to the end point, and includes four turning nodes, which constitute the turning information in the navigation route. According to the turning information, the navigation route is divided into five large road segments, as shown in b of FIG. 1. Figure 2 The entire navigation route is divided into five large road segments, i.e., the first large road segment step0, the second large road segment step1, the third large road segment step2, the fourth large road segment step3, and the fifth large road segment step4. Each large road segment is divided into at least one small road segment. For example, the first large road segment step0 is divided into two small road segments link0-1 (i.e., link0 and link1), the second large road segment step1 is divided into four small road segments link0-3 (i.e., link0, link1, link2, and link3), the third large road segment step2 is divided into three small road segments link0-2 (i.e., link0, link1, and link2), the fourth large road segment step3 is divided into three small road segments link0-2 (i.e., link0, link1, and link2), and the fifth large road segment step5 is divided into two small road segments link0-1 (i.e., link0 and link1). That is, the first large road segment step0 includes two intersections, the second large road segment step1 includes four intersections, the third large road segment step2 includes three intersections, the fourth large road segment step3 includes three intersections, and the fifth large road segment step5 includes two intersections.

[0069] In addition, the driving decision generation device can obtain real-time data of the vehicle driving through the navigation data, including the number of lanes of the current driving road of the vehicle, traffic light information, and the like. The real-time data can assist in determining the position of the vehicle. That is, the driving route of the vehicle can be obtained through the path information, and the actual position of the vehicle in the entire driving route can be obtained.

[0070] Step S102: Obtain visual perception information.

[0071] Specifically, during the driving of the vehicle, the vehicle-mounted camera on the vehicle obtains the surrounding information in real time, outputs a 2D image, and projects in a bird's eye perspective space, so that the driving decision generation device obtains the visual perception information from the vehicle-mounted camera. The visual perception information is used to represent the environmental information around the vehicle. In one possible implementation, the environmental information around the vehicle includes, but is not limited to, driving environment and dynamic and static obstacles.

[0072] It can be understood that by obtaining the environmental information around the vehicle, it can be determined whether it is safe around the vehicle, so as to control the vehicle to drive according to the environmental information around the vehicle under the premise of ensuring driving safety.

[0073] Step S103: generating a driving decision according to the path information and the visual perception information.

[0074] Specifically, the driving decision generation apparatus generates a driving decision according to the obtained path information and the visual perception information, the driving decision being used to control the vehicle to drive in a corresponding lane. The lane in the embodiments of the present application is a lane between two lane lines.

[0075] In a possible implementation, a set of driving trajectories of the vehicle is obtained according to the visual perception information, a target driving trajectory is selected from the set of driving trajectories according to the path information and a preset driving rule, and the driving decision is generated according to the target driving trajectory.

[0076] In a possible implementation, the driving decision generated by the driving decision generation apparatus is used to control the vehicle to turn.

[0077] Specifically, referring to Figure 3 , a set of driving trajectories of vehicle turning is provided in the embodiments of the present application. As shown in Figure 3 , the driving decision generation apparatus can determine that the vehicle is currently located at an intersection according to the visual perception information, and the driving decision generation apparatus can obtain a set of driving trajectories available for the vehicle to drive according to the visual perception information at the intersection. The set of driving trajectories includes six trajectories, i.e., trajectory 1, trajectory 2, trajectory 3, trajectory 4, trajectory 5, and trajectory 6. In the above embodiment, the vehicle should turn right in the path information, so the trajectories of the vehicle turning right at the intersection are trajectory 5 and trajectory 6. However, the driving decision generation apparatus stores a safety rule constraint, such as the safety bottom line of “prohibition of driving into an opposite lane”, trajectory 5 is excluded, and trajectory 6 is selected, so as to complete the path planning of the intersection connecting straight driving and right turning.

[0078] Similarly, if the vehicle should turn left in the path information, the trajectories of the vehicle turning left at the intersection are trajectory 1 and trajectory 2. However, the driving decision generation apparatus stores a safety rule constraint, such as the safety bottom line of “prohibition of driving into an opposite lane”, trajectory 1 is excluded, and trajectory 2 is selected, so as to complete the path planning of the intersection connecting straight driving and left turning.

[0079] In addition, in a possible implementation, the driving decision generated by the driving decision generation apparatus is used to control the vehicle to change lanes.

[0080] Specifically, referring to Figure 4 , a set of driving trajectories of vehicle changing lanes is provided in the embodiments of the present application. As shown in Figure 4As shown, the current ego vehicle is driving straight in the third lane on the left side, and according to the visual perception information, it can be determined that the third lane on the left side is the rightmost lane. When the vehicle is at a preset distance from the intersection, the driving decision generation device can determine that the vehicle needs to turn right in front of it according to the path information and the visual perception information, and determine that the right-turn lane is the rightmost lane according to the traffic rules. Therefore, the vehicle can continue to drive on the current road, i.e., according to the trajectory 9, so as to turn right at the intersection.

[0081] Similarly, if the driving decision generation device determines that the vehicle needs to turn left in front of it according to the path information and the visual perception information, it can be determined that the left-turn lane is the leftmost lane according to the traffic rules. Since the vehicle is currently driving in the rightmost lane, it needs to be controlled to change lanes to the leftmost lane, i.e., according to the trajectory 7, so as to turn left at the intersection.

[0082] In addition, in some possible implementations, if the current driving lane is relatively congested and the adjacent lane is relatively smooth, the driving decision generation device can control the vehicle to change lanes to the adjacent relatively smooth lane. Or when the current driving lane suddenly appears an obstacle, the driving decision generation device can control the vehicle to change lanes under the premise of safety to avoid colliding with the obstacle and ensure the safety of the passengers.

[0083] In one possible implementation, the probability of the vehicle driving on each driving trajectory is calculated according to the formula , wherein p is the probability of the vehicle driving on each driving trajectory, x is all trajectories in which the vehicle can possibly drive in the future, y is one of the trajectories in which the vehicle can possibly drive in the future, and t is the number of trajectories in which the vehicle can possibly drive in the future.

[0084] Of course, in actual applications, since the intersection traffic scene is more complex than the road section, the intersection trajectory mode will also increase compared with the trajectory mode on the road section, and t is not limited to 6 in Figure 3 and 3 in Figure 4 , but should be any defined multiple.

[0085] In one possible implementation, before generating the driving decision, it is determined whether a turn or a lane change is needed according to the path information and the visual perception information; if a turn or a lane change is needed, the driving decision is generated according to the path information and the visual perception information.

[0086] It can be understood that when the vehicle can drive straight in the current lane, it does not need to be controlled additionally, and at this time, the driving decision is not generated, so as to save the computing power under the premise of not affecting the driving safety.

[0087] In one possible implementation, the method for determining whether a turn or a lane change is needed is to determine the current driving lane of the vehicle and the lane congestion condition according to the visual perception information; and whether a turn or a lane change is needed is determined according to the path information, the current driving lane of the vehicle, and the lane congestion condition.

[0088] It can be understood that whether the current needs to turn or change lanes can be determined through the road congestion situation and the path information.

[0089] Corresponding to the above-mentioned embodiments, the application further provides a driving decision generation device.

[0090] Referring to Figure 5 , a structural schematic diagram of a driving decision generation device provided by the embodiments of the application is shown. As shown in the figure, the driving decision generation device includes a path information acquisition module 501, a visual perception information acquisition module 502, and a driving decision generation module 503. These components communicate through one or more buses, and those skilled in the art can understand that the structure of the electronic device shown in the figure does not constitute a limitation on the embodiments of the application. It can be a bus structure, or a star structure, and can include more or fewer components than shown in the figure, or combine some components, or different component arrangements.

[0091] The path information acquisition module 501 is configured to acquire path information, and the path information is a navigation path between a starting point and an ending point.

[0092] The visual perception information acquisition module 502 is configured to acquire visual perception information, and the visual perception information is used to represent environmental information around the vehicle.

[0093] The driving decision generation module 503 is configured to generate a driving decision according to the path information and the visual perception information, and the driving decision is used to control the vehicle to drive in a corresponding lane.

[0094] Corresponding to the above-mentioned embodiments, the application further provides an electronic device.

[0095] Referring to Figure 6 , a structural schematic diagram of an electronic device provided by the embodiments of the application is shown. As Figure 6 shown, the electronic device 600 can include a processor 601, a memory 602, and a communication unit 603. These components communicate through one or more buses, and those skilled in the art can understand that the structure of the electronic device shown in the figure does not constitute a limitation on the embodiments of the application. It can be a bus structure, or a star structure, and can include more or fewer components than shown in the figure, or combine some components, or different component arrangements.

[0096] The communication unit 603 is configured to establish a communication channel, so that the electronic device can communicate with other devices. Receive user data sent by other devices or send user data to other devices.

[0097] The processor 601 is the control center of the electronic device, connects various parts of the electronic device through various interfaces and lines, and executes various functions of the electronic device and / or processes data by running or executing software programs, instructions, and / or modules stored in the memory 602 and calling data stored in the memory. The processor can be composed of an integrated circuit (IC), for example, can be composed of a single packaged IC, or can be composed of a plurality of packaged ICs connected together. For example, the processor 601 can only include a central processing unit (CPU). In the embodiments of the present application, the CPU can be a single operation core or can include multiple operation cores.

[0098] The memory 602 is used to store the execution instructions of the processor 601. The memory 602 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0099] When the execution instructions in the memory 602 are executed by the processor 601, the electronic device 600 can perform Figure 1 some or all of the steps in the embodiments shown.

[0100] In specific implementations, the embodiments of the present application also provide a computer storage medium, wherein the computer storage medium can store a program, and the program can include some or all of the steps in the embodiments of the simulation scene generation method provided by the embodiments of the present application when executed. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0101] In specific implementations, the embodiments of the present application also provide a computer program product, wherein the computer program product contains executable instructions, and when the executable instructions are executed on a computer, the computer executes some or all of the steps in the embodiments of the simulation scene generation method provided by the embodiments of the present application.

[0102] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the cases of A alone, A and B together, and B alone. Wherein A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" and the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0103] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be realized in electronic hardware, computer software, and a combination of electronic hardware and computer software. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0105] In several embodiments provided in the present application, any function realized in the form of a software function unit and sold or used as an independent product can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0106] The same and similar parts among the various embodiments in the specification can be referred to each other. Especially, for the device embodiments and the terminal embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the related parts can refer to the description in the method embodiments.

Claims

1. A driving decision generation method characterized by, The method comprises the following steps: obtaining path information, the path information being a navigation path between a starting point and an ending point; obtaining visual perception information, the visual perception information being used to represent environmental information around the vehicle; generating a driving decision according to the path information and the visual perception information, the driving decision being used to control the vehicle to drive in a corresponding lane; the step of generating the driving decision according to the path information and the visual perception information comprises the following steps: obtaining a set of driving trajectories of the vehicle according to the visual perception information; selecting a target driving trajectory from the set of driving trajectories according to the path information and a preset driving rule; generating the driving decision according to the target driving trajectory; the step of obtaining the set of driving trajectories of the vehicle according to the visual perception information comprises the following step: calculating a probability of the vehicle driving in each driving trajectory according to the visual perception information, and generating the set of driving trajectories of the vehicle.

2. The method of claim 1, wherein, The step of obtaining the path information comprises the following steps: obtaining a navigation route between the starting point and the ending point; dividing the navigation route according to turning information to obtain the path information, the turning information being at least one turning node in the navigation route.

3. The method of claim 1, wherein, The step of calculating the probability of the vehicle driving in each driving trajectory according to the visual perception information comprises the following steps: The probability of the vehicle driving on each driving trajectory is calculated according to the formula p(x) = ∑ypt(x, y), where p is the probability of the vehicle driving on each driving trajectory, x is the trajectory that the vehicle can possibly drive in the future, y is one of the trajectories that the vehicle can possibly drive in the future, and t is the number of trajectories that the vehicle can possibly drive in the future.

4. The method of claim 1, wherein, The step of generating the driving decision according to the path information and the visual perception information comprises the following steps: judging whether turning or lane changing is needed according to the path information and the visual perception information; if turning or lane changing is needed, generating the driving decision according to the path information and the visual perception information.

5. The method of claim 4, wherein, The step of judging whether turning or lane changing is needed according to the path information and the visual perception information comprises the following steps: determining a current driving lane of the vehicle and a lane congestion condition according to the visual perception information; judging whether turning or lane changing is needed according to the path information, the current driving lane of the vehicle and the lane congestion condition.

6. A driving decision generation device characterized by comprising: The method comprises the following steps: a path information obtaining module is configured to obtain path information, the path information being a navigation path between a starting point and an ending point; a visual perception information obtaining module is configured to obtain visual perception information, the visual perception information being used to represent environmental information around the vehicle; a driving decision generating module is configured to generate a driving decision according to the path information and the visual perception information, the driving decision being used to control the vehicle to drive in a corresponding lane; the driving decision generating module is specifically configured to obtain a set of driving trajectories of the vehicle according to the visual perception information, and select a target driving trajectory from the set of driving trajectories according to the path information and a preset driving rule; generate the driving decision according to the target driving trajectory; the step of obtaining the set of driving trajectories of the vehicle according to the visual perception information comprises the following step:

7. An electronic device, comprising: calculate a probability of the vehicle driving in each driving trajectory according to the visual perception information, and generate the set of driving trajectories of the vehicle. The method comprises the following steps: a processor; a memory; a communication unit configured to establish a communication channel; and a computer program, wherein the computer program is stored in the memory, and the computer program includes instructions, which, when executed by the processor, cause the electronic device to perform the method of any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium includes a stored program, wherein the program, when executed, controls a device in which the computer readable storage medium is located to perform the method of any one of claims 1 to 5.

Images