CN118082873A

CN118082873A - Method for driving autonomous vehicle and autonomous vehicle

Info

Publication number: CN118082873A
Application number: CN202211430981.4A
Authority: CN
Inventors: 何毅晨; 华旎; 李潇; 王乃峥
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2022-11-15
Filing date: 2022-11-15
Publication date: 2024-05-28

Abstract

The application discloses an automatic driving vehicle driving method and an automatic driving vehicle, and belongs to the technical field of automatic driving. The method comprises the following steps: under the condition that the reverse dynamic obstacle is detected, determining a target meeting area of the automatic driving vehicle and the reverse dynamic obstacle; selecting a target obstacle based on the target meeting area; determining a plurality of sets of viable control parameters based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle; and selecting a target control parameter from the plurality of groups of feasible control parameters, and controlling the automatic driving vehicle to run through the target meeting area based on the target control parameter. The method can improve the meeting effect of the automatic driving vehicle and the reverse dynamic obstacle meeting.

Description

Method for driving autonomous vehicle and autonomous vehicle

Technical Field

The application relates to the technical field of automatic driving, in particular to a driving method of an automatic driving vehicle and the automatic driving vehicle.

Background

Along with the improvement of the automatic driving capability of the automatic driving vehicle, the application range of the automatic driving vehicle is enlarged, and the encountered complex scenes are increased. Among them, a scene where an autonomous vehicle meets a reverse dynamic obstacle (e.g., an oncoming vehicle of the autonomous vehicle) on a narrow road is one of complex scenes that an autonomous vehicle is often encountering at present.

Disclosure of Invention

The embodiment of the application provides an automatic driving vehicle driving method and an automatic driving vehicle, which can improve the meeting effect of the automatic driving vehicle and a reverse dynamic obstacle meeting. The technical scheme is as follows:

in one aspect, there is provided a method of driving an autonomous vehicle, the method comprising:

Under the condition that a reverse dynamic obstacle is detected, determining a target meeting area of an automatic driving vehicle and the reverse dynamic obstacle, wherein the target meeting area is an area where the automatic driving vehicle and the reverse dynamic obstacle cannot pass through at the same time, and the reverse dynamic obstacle is a dynamic obstacle with a driving direction opposite to that of the automatic driving vehicle;

selecting a target obstacle based on the target meeting area;

Determining a plurality of sets of viable control parameters based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle;

and selecting a target control parameter from the plurality of groups of feasible control parameters, and controlling the automatic driving vehicle to run through the target meeting area based on the target control parameter.

In one possible implementation manner, the determining a plurality of sets of feasible control parameters based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the prediction information of the target obstacle includes:

Determining a plurality of first trajectories of the autonomous vehicle based on first state information of the autonomous vehicle, the first trajectories being trajectories of the autonomous vehicle traveling through the target meeting area;

Determining a second track of the target obstacle based on the second state information of the target obstacle and the prediction information of the target obstacle, wherein the second track is a track of the target obstacle running through the target meeting area;

And determining a plurality of feasible tracks from the plurality of first tracks based on the second tracks, and determining control parameters corresponding to the plurality of feasible tracks as the plurality of groups of feasible control parameters, wherein the feasible tracks are tracks without overlapping points with the second tracks.

In one aspect, there is provided an autonomous vehicle driving apparatus, the apparatus comprising:

The device comprises a region determining module, a driving control module and a driving control module, wherein the region determining module is used for determining a target meeting region of an automatic driving vehicle and a reverse dynamic obstacle under the condition that the reverse dynamic obstacle is detected, the target meeting region is a region which can not be passed through by the automatic driving vehicle and the reverse dynamic obstacle at the same time, and the reverse dynamic obstacle is a dynamic obstacle with a driving direction opposite to that of the automatic driving vehicle;

a selection module for selecting a target obstacle based on the target meeting area;

a parameter determination module for determining a plurality of sets of feasible control parameters based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle;

And the control module is used for selecting a target control parameter from the plurality of groups of feasible control parameters and controlling the automatic driving vehicle to run through the target meeting area based on the target control parameter.

In one possible implementation manner, the parameter determining module includes:

a track determining unit configured to determine a plurality of first tracks of the autonomous vehicle, based on first state information of the autonomous vehicle, the first tracks being tracks of the autonomous vehicle traveling through the target meeting area;

The track determining unit is further configured to determine a second track of the target obstacle based on the second state information of the target obstacle and the prediction information of the target obstacle, where the second track is a track of the target obstacle that runs through the target meeting area;

And the parameter determining unit is used for determining a plurality of feasible tracks from the plurality of first tracks based on the second track, determining control parameters corresponding to the plurality of feasible tracks as the plurality of groups of feasible control parameters, wherein the feasible tracks are tracks without a coincidence point with the second track.

In one possible implementation manner, the parameter determining module is configured to take performance information of the autonomous vehicle and a plurality of selectable traffic decisions of the autonomous vehicle as sampling constraints, sample a trajectory of the autonomous vehicle based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle, and determine control parameters corresponding to the sampled trajectories as viable control parameters.

In one possible implementation, the trajectory includes a path and a speed; the performance information comprises at least one of a speed range, an acceleration range or a curvature range, wherein the speed range is used for restraining the speed corresponding to the track obtained by sampling to belong to the speed range, the acceleration range is used for restraining the acceleration corresponding to the track obtained by sampling to belong to the acceleration range, and the curvature range is used for restraining the curvature of the path corresponding to the track obtained by sampling to belong to the curvature range.

In one possible implementation, the plurality of selectable traffic decisions for the autonomous vehicle includes at least one of:

Preemptively passing through the target meeting area before the reverse dynamic obstacle passes through the target meeting area;

the avoidable area is stopped at the right side, and after the reverse dynamic obstacle passes through the target meeting area, the reverse dynamic obstacle passes through the target meeting area again;

the dodgeable area is stopped at the left side, and after the reverse dynamic obstacle passes through the target meeting area, the reverse dynamic obstacle passes through the target meeting area;

Reversing and stopping at the avoidable area on the right side, and passing through the target meeting area after the reverse dynamic obstacle passes through the target meeting area;

reversing and stopping at the left avoidable area, and passing through the target meeting area after the reverse dynamic obstacle passes through the target meeting area.

In one possible implementation manner, the parameter determining module is configured to determine a plurality of target areas based on a plurality of selectable traffic decisions, where the target areas are areas that the traffic decisions indicate the arrival of the autonomous vehicle; taking the performance information of the automatic driving vehicle and the plurality of target areas as sampling constraints, and sampling the track of the automatic driving vehicle based on the first state information of the automatic driving vehicle, the second state information of the target obstacle and the prediction information of the target obstacle so that the sampled track takes any one of the plurality of target areas as an end point.

In one possible implementation manner, the control module is configured to determine an optimal passing decision among the multiple passing decisions based on the multiple sets of feasible control parameters, and if the optimal passing decision corresponds to the multiple sets of feasible control parameters, determine the target control parameter from the multiple sets of feasible control parameters corresponding to the optimal passing decision, where a control effect of the target control parameter is higher than a control effect of other sets of control parameters in the multiple sets of feasible control parameters; or alternatively

The control module is used for directly selecting the target control parameter from the plurality of groups of feasible control parameters, and the control effect of the target control parameter is higher than that of other groups of control parameters in the plurality of groups of feasible control parameters.

In a possible implementation manner, the control module is configured to select, from the multiple sets of possible control parameters, an optimal control parameter as the target control parameter at the cost of any one or more of traffic efficiency, safe distance, kinematic stability, and path stability.

In a possible implementation manner, the selecting module is configured to perform at least one of the following:

Based on the target meeting area, taking a reverse dynamic barrier which is positioned at the other side of the target meeting area and is not more than a first distance threshold from the target meeting area as the target barrier;

Taking a same-direction dynamic obstacle which is positioned behind the automatic driving vehicle and is not more than a second distance threshold value from the automatic driving vehicle as the target obstacle based on the target meeting area, wherein the same-direction dynamic obstacle is a dynamic obstacle with the same driving direction as the driving direction of the automatic driving vehicle;

and taking a static obstacle which is not more than a third distance threshold from the target meeting area as the target obstacle based on the target meeting area.

In one possible implementation manner, the area determining module is configured to determine, when a reverse dynamic obstacle is detected, an area in a front passable area with a width smaller than a sum of the first width, the second width, and a meeting safety distance as the target meeting area based on a first width of the reverse dynamic obstacle and a second width of the autonomous vehicle.

In one aspect, an autonomous vehicle is provided that includes one or more processors and one or more memories having stored therein at least one program code loaded and executed by the one or more processors to implement operations performed by an autonomous vehicle driving method as in any of the possible implementations described above.

In one aspect, a computer readable storage medium having stored therein at least one program code loaded and executed by a processor to perform operations performed by an autonomous vehicle driving method as any of the possible implementations described above is provided.

In one aspect, there is provided a computer program or computer program product comprising: computer program code which, when executed by a computer, causes the computer to carry out the operations performed by the autonomous vehicle driving method as described in any of the possible implementations.

According to the automatic driving vehicle driving method and the automatic driving vehicle, after the target meeting area is determined, the target obstacle can be selected, a plurality of groups of feasible control parameters avoiding collision with the target obstacle are determined, one group of feasible control parameters is selected from the plurality of groups of feasible control parameters to control the automatic driving vehicle to drive through the target meeting area, collision between the automatic driving vehicle and the target obstacle can be avoided, and safety of the automatic driving vehicle is guaranteed.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic illustration of an implementation environment provided by an embodiment of the present application;

FIG. 2 is a flow chart of a method of driving an autonomous vehicle according to an embodiment of the present application;

FIG. 3 is a flow chart of a method of autonomous vehicle travel provided by an embodiment of the present application;

FIG. 4 is a schematic illustration of a static obstacle provided by an embodiment of the application;

FIG. 5 is a schematic view of a traffic zone provided by an embodiment of the present application;

FIG. 6 is a schematic diagram of sampling trajectories of an autonomous vehicle according to an embodiment of the present application;

FIG. 7 is a flowchart illustrating a method for determining a target control parameter according to an embodiment of the present application;

fig. 8 is a schematic structural view of a driving apparatus for an automatic driving vehicle according to an embodiment of the present application;

fig. 9 is a schematic structural view of an autonomous vehicle according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a server according to an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.

It is to be understood that the terms "first," "second," and the like, as used herein, may be used to describe various concepts, but are not limited by these terms unless otherwise specified. These terms are only used to distinguish one concept from another. For example, a first obstacle may be referred to as a second obstacle and a second obstacle may be referred to as a first obstacle without departing from the scope of the application.

The terms "at least one", "a plurality", "each", "any" as used herein, at least one includes one, two or more, a plurality includes two or more, and each refers to each of a corresponding plurality, any one refers to any one of a plurality, for example, a plurality of obstacles includes 3 obstacles, and each refers to each of the 3 obstacles, any one refers to any one of the 3 obstacles, either the first, the second, or the third.

It should be noted that, the information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals related to the present application are all authorized by the user or are fully authorized by the parties, and the collection, use, and processing of the related data is required to comply with the relevant laws and regulations and standards of the relevant countries and regions. For example, the status information and the like referred to in the present application are acquired with sufficient authorization. And the information and the data are processed and then used in big data application scenes, and can not be identified to any natural person or generate specific association with the natural person.

In some embodiments, the method for driving an autonomous vehicle according to the embodiments of the present application is performed by an autonomous vehicle. In some embodiments, the autonomous vehicle includes a vehicle that travels on the ground (e.g., an automobile, truck, bus, etc.), may include a vehicle that travels in the air (e.g., an unmanned plane, an airplane, a helicopter, etc.), and may include a vehicle that travels on or in water (e.g., a boat, a submarine, etc.). The autonomous vehicle may or may not accommodate one or more passengers. In addition, the autonomous vehicle can be applied to the unmanned distribution field, such as the express logistics field, the take-away meal delivery field, and the like.

In other embodiments, the method for driving an autonomous vehicle according to the embodiments of the present application is performed by an autonomous vehicle and a server. The server may be a server, a server cluster comprising a plurality of servers, or a cloud computing service center.

It should be noted that, in the embodiment of the present application, the execution subject of the driving method of the autonomous vehicle is not limited.

Fig. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application, and as shown in fig. 1, the implementation environment includes an autonomous vehicle 101 and a server 102, where the autonomous vehicle 101 and the server 102 are connected through a wireless or wired network.

The server 102 is a server for providing services to the autonomous vehicle 101. Optionally, the server 102 may provide an electronic map, a traffic decision, control parameters, etc. of the autonomous vehicle, and the service provided by the server 102 is not limited in the embodiments of the present application.

In some embodiments, when the autonomous vehicle 101 detects a reverse dynamic obstacle, determining a target meeting area of the autonomous vehicle 101 and the reverse dynamic obstacle, selecting a target obstacle based on the target meeting area, and transmitting first state information of the autonomous vehicle and second state information of the target obstacle to the server 102; the server 102 determines prediction information of the target obstacle, determines a plurality of sets of feasible control parameters based on the first dynamic information of the autonomous vehicle 101, the second state information of the target obstacle and the prediction information of the target obstacle, selects the target control parameter from the plurality of sets of feasible control parameters, and transmits the target control parameter to the autonomous vehicle 101; the autonomous vehicle 101 travels through the target meeting area based on the target control parameter.

In some embodiments, the autonomous vehicle 101 obtains an electronic map from the server 102, plans a driving route based on the electronic map, determines a target meeting area of the autonomous vehicle and the reverse dynamic obstacle in the case that the reverse dynamic obstacle is detected in the driving process according to the driving route, selects a target obstacle based on the target meeting area, determines a plurality of sets of feasible control parameters based on the first state information of the autonomous vehicle, the second state information of the target obstacle and the prediction information of the target obstacle, selects a target control parameter from the plurality of sets of feasible control parameters, and controls the autonomous vehicle to drive through the target meeting area based on the target control parameter. Of course, the autonomous vehicle 101 and the server 102 may together complete the above-described process, and the embodiment of the present application does not limit what processes the autonomous vehicle 101 and the server 102 do specifically.

Fig. 2 is a flowchart of a driving method of an automatic driving vehicle according to an embodiment of the present application. The embodiment of the application is exemplified by taking an automatic driving vehicle as an execution main body, and comprises the following steps:

201. when the automatic driving vehicle detects the reverse dynamic obstacle, a target meeting area of the automatic driving vehicle and the reverse dynamic obstacle is determined, wherein the target meeting area is an area where the automatic driving vehicle and the reverse dynamic obstacle cannot pass through at the same time, and the reverse dynamic obstacle is a dynamic obstacle with a driving direction opposite to that of the automatic driving vehicle.

A reverse dynamic obstacle is any dynamic obstacle whose travel direction is opposite to the travel direction of an autonomous vehicle. For example, the reverse dynamic obstacle is an oncoming vehicle of an automatic driving vehicle, and the embodiment of the application does not limit the reverse dynamic obstacle. It should be noted that, in the embodiment of the present application, the reverse dynamic obstacle is located in the same lane as the driving vehicle, so that the driving vehicle may be affected by the reverse dynamic obstacle, and the driving vehicle may adjust the control parameter based on the reverse dynamic obstacle.

The target meeting area is an area between the autonomous vehicle and the reverse dynamic obstacle and through which the autonomous vehicle and the reverse dynamic obstacle cannot pass at the same time. In some embodiments, the width of the target meeting area is less than the sum of the width of the autonomous vehicle and the width of the reverse dynamic obstacle, so that the autonomous vehicle and the reverse dynamic obstacle cannot pass through the target meeting area at the same time. In other embodiments, when the autonomous vehicle and the reverse dynamic obstacle meet, the autonomous vehicle and the reverse dynamic obstacle maintain a safe distance, and if the safe distance cannot be maintained, the autonomous vehicle and the reverse dynamic obstacle sequentially pass through the target meeting area, so that the width of the target meeting area is smaller than the sum of the width of the autonomous vehicle, the width of the reverse dynamic obstacle and the safe distance.

202. The autonomous vehicle selects a target obstacle based on the target meeting area.

Wherein, the target obstacle is an obstacle which can influence the running of the automatic driving vehicle when the automatic driving vehicle passes through the target meeting area. The target obstacle can be a reverse dynamic obstacle of the automatic driving vehicle, a same-direction dynamic obstacle of the automatic driving vehicle, or a static obstacle of a lane where the automatic driving vehicle is located. Therefore, the target obstacle includes at least one of a reverse dynamic obstacle, a homodromous dynamic obstacle and a static obstacle, and the embodiment of the application does not limit the target obstacle.

203. The autonomous vehicle determines a plurality of sets of viable control parameters based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle.

The first state information is used to indicate a running state of the autonomous vehicle, for example, the first state information is used to indicate at what speed the autonomous vehicle is running; as another example, the first state information is used to indicate in which direction the autonomous vehicle is traveling. In some embodiments, the first status information of the autonomous vehicle includes at least one of a speed, a front wheel rotation angle, and an orientation of the autonomous vehicle. The embodiment of the application does not limit the first state information.

When the target obstacle is a dynamic obstacle, the second state information is used to represent a traveling state of the target obstacle, for example, the second state information is used to represent at what speed the target obstacle is traveling; as another example, the second state information is used to indicate in which direction the target obstacle is traveling. In some embodiments, the second status information of the target obstacle includes at least one of a speed, a front wheel rotation angle, and an orientation of the target obstacle. The embodiment of the application does not limit the second state information. Optionally, the second status information is further used to indicate a presentation status of the target obstacle, for example, the second status information is used to indicate where the target obstacle is located; as another example, the second state information is used to indicate what shape the target obstacle is, and so on. In some embodiments, the second status information includes at least one of a location, a shape, etc. of the target obstacle.

When the target obstacle is a static obstacle, the second state information is used to represent the present state of the target obstacle. For example, the second status information is used to indicate where the target obstacle is located; as another example, the second state information is used to indicate what shape the target obstacle is, and so on. In some embodiments, the second status information includes at least one of a location, a shape, etc. of the target obstacle.

It should be noted that, in the embodiment of the present application, the target obstacle includes a reverse dynamic obstacle, and of course, the target obstacle may also include a co-dynamic obstacle and/or a static obstacle. Because the target obstacle comprises a dynamic obstacle, the embodiment of the application can acquire the prediction information of the target obstacle, and determine the feasible control parameters based on the prediction information of the target obstacle so as to avoid collision between the automatic driving vehicle and the target obstacle.

Wherein the predicted information of the target obstacle is used to represent the next driving state of the target obstacle. For example, the predicted information of the target obstacle is used to indicate that the target obstacle will stop, and the automated driving vehicle passes through the target meeting area after passing through the target meeting area. For another example, the predicted information of the target obstacle is used to indicate that the target obstacle will preemptively pass through the target meeting area, and the embodiment of the application does not limit the predicted information.

The feasible control parameters are a set of control parameters for controlling the safe passing of the automatic driving vehicle through the target meeting area, wherein the safe passing of the automatic driving vehicle through the target meeting area refers to: an autonomous vehicle passes through the target meeting area without colliding with a target obstacle.

In the embodiment of the application, the automatic driving vehicle can determine a plurality of groups of feasible control parameters based on the first state information of the automatic driving vehicle, the second state information of the target obstacle and the prediction information of the target obstacle. In one possible implementation, an autonomous vehicle determines a plurality of sets of viable control parameters based on first state information of the autonomous vehicle, second state information of a target obstacle, and predicted information of the target obstacle, including: the automatic driving vehicle firstly determines a plurality of groups of control parameters, and determines a plurality of groups of feasible control parameters from the plurality of groups of control parameters based on the first state information of the automatic driving vehicle, the second state of the target obstacle and the prediction information.

In another possible implementation, the autonomous vehicle determines a plurality of sets of viable control parameters based on first state information of the autonomous vehicle, second state information of a target obstacle, and predicted information of the target obstacle, including: determining a plurality of first trajectories of the autonomous vehicle based on the first state information of the autonomous vehicle, the first trajectories being trajectories of the autonomous vehicle traveling through the target meeting area; determining a second track of the target obstacle based on the second state information of the target obstacle and the prediction information of the target obstacle, wherein the second track is a track of the target obstacle running through the target meeting area; and determining a plurality of feasible tracks from the plurality of first tracks based on the second track, and determining control parameters corresponding to the feasible tracks as a plurality of groups of feasible control parameters, wherein the feasible tracks are tracks without overlapping points with the second track.

In the embodiment of the application, the track of the automatic driving vehicle represents the positions of the automatic driving vehicle at different moments, and the track of the target obstacle represents the positions of the target obstacle at different moments. The absence of a coincidence point between the feasible track and the second track means that the positions of the feasible track and the second track corresponding to each same moment are different.

204. The autonomous vehicle selects a target control parameter from a plurality of sets of viable control parameters, and controls the autonomous vehicle to travel through the target meeting area based on the target control parameter.

The target control parameter is any one of a plurality of groups of possible control parameters, and the target control parameter is not limited in the embodiment of the application. In some embodiments, the target control parameter is an optimal one of the plurality of sets of viable control parameters. It should be noted that, the optimal set of feasible control parameters herein refers to optimal feasible control parameters determined according to a certain screening condition, and the optimal feasible control parameters corresponding to different screening conditions may be different.

Because the target control parameter is any one of a plurality of groups of feasible control parameters, the automatic driving vehicle is controlled to run through the target meeting area based on the target control parameter, so that the automatic driving vehicle can be prevented from colliding with a target obstacle, and the safety of the automatic driving vehicle is ensured.

According to the method for driving the automatic driving vehicle, after the target meeting area is determined, the target obstacle can be selected, a plurality of groups of feasible control parameters avoiding collision with the target obstacle are determined, one group of feasible control parameters is selected from the plurality of groups of feasible control parameters to control the automatic driving vehicle to drive through the target meeting area, collision between the automatic driving vehicle and the target obstacle can be avoided, and safety of the automatic driving vehicle is guaranteed.

Fig. 3 is a flowchart of a driving method of an automatic driving vehicle according to an embodiment of the present application. The embodiment of the application is exemplified by taking an automatic driving vehicle as an execution main body, and comprises the following steps:

301. when the automatic driving vehicle detects the reverse dynamic obstacle, a target meeting area of the automatic driving vehicle and the reverse dynamic obstacle is determined, wherein the target meeting area is an area where the automatic driving vehicle and the reverse dynamic obstacle cannot pass through at the same time, and the reverse dynamic obstacle is a dynamic obstacle with a driving direction opposite to that of the automatic driving vehicle.

In some embodiments, the autonomous vehicle may detect an obstacle in a fourth distance ahead and an obstacle in a fourth five distance behind during travel, and plan a travel path based on the detected obstacles. If the autonomous vehicle detects a reverse dynamic obstacle, a determination is made as to whether the autonomous vehicle is likely to be in a narrow road meeting with the reverse dynamic obstacle. In some embodiments, the autonomous vehicle needs to maintain a safe distance from the obstacle, and thus, in the event that a reverse dynamic obstacle is detected, the autonomous vehicle determines a target meeting area for the autonomous vehicle and the reverse dynamic obstacle, comprising: in the case where the reverse dynamic obstacle is detected, an area of the front passable area having a width smaller than the sum of the first width, the second width, and the meeting safety distance is determined as the target meeting area based on the first width of the reverse dynamic obstacle and the second width of the autonomous vehicle. The meeting safety distance can be any distance, and the meeting safety distance is not limited in the embodiment of the application.

In some embodiments, when the autonomous vehicle is traveling on a roadway, there may be static obstacles such as plants, street lamps, signal lamps, etc. on both sides of the roadway, and each square represents a static obstacle as shown in fig. 4. To avoid collision of the autonomous vehicle with the static obstacle, a passable area of the autonomous vehicle may be determined based on the static obstacle. In one possible implementation, the autonomous vehicle determines the passable area of the autonomous vehicle based on appearance data of the static obstacle located in the current lane in case the static obstacle is detected.

The appearance data of the static obstacle is data for describing the appearance of the static obstacle, and may include the shape of the static obstacle, and the appearance data of the static obstacle is not limited in the embodiment of the present application. The autonomous vehicle may determine the passable area shown in fig. 5 based on the appearance data of the static obstacle, and then determine the target meeting area from the passable area based on the reverse dynamic obstacle coming from the front.

When the autonomous vehicle determines the passable area based on the appearance data of the static obstacle, djkistra (dijkstra) algorithm, RRT (Rapidly-exporing Random Tree, fast-expanding random number) algorithm, a (a direct search method for solving the shortest route in the static road network) algorithm, DP (Dynamic Programming, dynamic planning) algorithm, and the like may be used.

302. The autonomous vehicle selects a target obstacle based on the target meeting area.

Wherein the target obstacle is an obstacle that may affect the passage of an autonomous vehicle through the target meeting area.

In one possible implementation, the autonomous vehicle selects a target obstacle based on a target meeting area, including at least one of:

(1) And taking the reverse dynamic obstacle which is positioned at the other side of the target meeting area and is not more than a first distance threshold from the target meeting area as a target obstacle based on the target meeting area.

The automatic driving vehicle and the reverse dynamic obstacle are respectively positioned at two sides of the target meeting area, so that the automatic driving vehicle and the reverse dynamic obstacle can meet vehicles in the target meeting area. And if the distance between the reverse dynamic obstacle and the target meeting area is not greater than the first distance threshold, indicating that the distance between the reverse dynamic obstacle and the target meeting area is relatively short. Since the autonomous vehicle is a target meeting area determined based on a range of obstacles, the autonomous vehicle is also closer to the target meeting area. Thus, an autonomous vehicle is likely to meet with a reverse dynamic obstacle in a target meeting area.

It should be noted that, in the embodiment of the present application, only an example in which the reverse dynamic obstacle is not greater than the first distance threshold from the target meeting area is illustrated, and in another embodiment, an automatic driving vehicle may also be used as a reference object. And taking the reverse dynamic obstacle which is positioned at the other side of the target meeting area and is not more than a fourth distance threshold from the automatic driving vehicle as a target obstacle based on the target meeting area.

The first distance threshold and the fourth distance threshold may be any value, and the first distance threshold and the fourth distance threshold may be a tested value or may be set by a technician.

(2) And taking the same-direction dynamic obstacle which is positioned behind the automatic driving vehicle and is not more than a second distance threshold value from the automatic driving vehicle as a target obstacle based on the target meeting area, wherein the same-direction dynamic obstacle is a dynamic obstacle with the same driving direction as that of the automatic driving vehicle.

The co-directional dynamic obstacle located behind the autonomous vehicle may overtake the autonomous vehicle, thereby affecting the travel of the autonomous vehicle; even if the vehicle does not pass, the reverse of the autonomous vehicle may be affected, and therefore, it is also necessary to consider the same-direction dynamic obstacle which is closer to the rear of the autonomous vehicle.

The second distance threshold may be any value, and the second distance threshold may be a tested value or may be set by a technician.

(3) And taking the static obstacle which is not more than a third distance threshold from the target meeting area as a target obstacle based on the target meeting area.

The static obstacle may be used to determine a passable area, an evasive area, etc. of the autonomous vehicle, and thus track planning is performed with reference to the static obstacle that is closer to the target meeting area.

303. The automatic driving vehicle takes performance information of the automatic driving vehicle and a plurality of selectable traffic decisions of the automatic driving vehicle as sampling constraints, samples the track of the automatic driving vehicle based on the first state information of the automatic driving vehicle, the second state information of the target obstacle and the prediction information of the target obstacle, and determines control parameters corresponding to the sampled tracks as feasible control parameters.

Wherein the performance information of the autonomous vehicle is used to represent the performance of the autonomous vehicle. Optionally, the performance parameter comprises at least one of a speed range, an acceleration range, or a curvature range. The speed range indicates a minimum speed and a maximum speed of the autonomous vehicle.

Wherein the autonomous vehicle can travel forward or reverse, so that the speed of the autonomous vehicle is a vector speed with a direction, and when the autonomous vehicle travels forward, the speed of the autonomous vehicle is a positive value; when the autonomous vehicle is reversed, the speed of the autonomous vehicle is negative. Thus, the maximum speed of the autonomous vehicle is the maximum speed that can be used when the autonomous vehicle is traveling forward, and the minimum speed of the autonomous vehicle is the maximum speed that can be used when the autonomous vehicle is reversing.

Similarly, the acceleration range indicates a minimum acceleration and a minimum acceleration of the autonomous vehicle, the maximum acceleration of the autonomous vehicle being a maximum acceleration that can be employed when the autonomous vehicle is traveling forward, and the minimum acceleration of the autonomous vehicle being a maximum acceleration that can be employed when the autonomous vehicle is traveling rearward.

Similarly, the curvature range indicates a maximum curvature of the travel path of the autonomous vehicle, which is a maximum curvature of the path when the autonomous vehicle travels forward, and a minimum curvature of the path when the autonomous vehicle travels backward.

In some embodiments, the track includes a path and a speed, the speed range is used to restrict the speed corresponding to the sampled track from belonging to the speed range, the acceleration range is used to restrict the acceleration corresponding to the sampled track from belonging to the acceleration range, and the curvature range is used to restrict the curvature of the path corresponding to the sampled track from belonging to the curvature range.

The traffic decision in the embodiment of the application is a decision for indicating that the automatic driving vehicle completes the narrow-road meeting. In some embodiments, the selectable plurality of traffic decisions for the autonomous vehicle includes at least one of: (1) Preemptively passing through the target meeting area before the reverse dynamic obstacle passes through the target meeting area; (2) The vehicle-crossing system comprises an avoidance area which is stopped at the right side, and a target vehicle-crossing area which is passed by the reverse dynamic obstacle; (3) The vehicle-crossing system comprises an avoidance area which is stopped at the left side, and a target vehicle-crossing area which is passed by a reverse dynamic obstacle; (4) Reversing and stopping at the avoidable area on the right side, and passing through the target meeting area after the reverse dynamic obstacle passes through the target meeting area; (5) Reversing and stopping at the left avoidable area, and passing through the target meeting area after the reverse dynamic obstacle passes through the target meeting area.

Wherein different traffic decisions indicate that the autonomous vehicle arrives in different areas, and thus the area in which the end point of the autonomous vehicle is located can be determined based on the traffic decisions, from which area the end point of the autonomous vehicle is sampled. In one possible implementation, as shown in fig. 6, the method for sampling the track of the autonomous vehicle based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle, with the performance information of the autonomous vehicle and the selectable multiple traffic decisions as sampling constraints includes: determining a plurality of target areas of the automatic driving vehicle based on a plurality of selectable traffic decisions, wherein the target areas are areas which are reached by the automatic driving vehicle through the traffic decisions; taking performance information of the automatic driving vehicle and a plurality of target areas as sampling constraints, and sampling the track of the automatic driving vehicle based on the first state information of the automatic driving vehicle, the second state information of the target obstacle and the prediction information of the target obstacle so that the sampled track takes any one of the plurality of target areas as an end point.

For example, as shown in FIG. 6, the traffic decision is that "when the reverse dynamic obstacle passes the target meeting area before it is preempted by the target meeting area," the target area is the other side of the target meeting area, that is, the opposite side of the target meeting area relative to the autonomous vehicle.

As another example, as shown in fig. 6, the traffic decision is "the evasive region parked on the right side", and when the reverse dynamic obstacle passes through the target meeting region and then passes through the target meeting region ", there are two target regions, the first target region is the evasive region on the right side, and the second target region is the other side of the target meeting region; the method comprises the steps of sampling from a first target area to obtain a first end point, sampling from a second target area to obtain a second end point, and enabling an automatic driving vehicle to reach the first end point and then reach the second end point.

As another example, as shown in fig. 6, the traffic decision is "the evasive region parked at the left side", and when the reverse dynamic obstacle passes through the target meeting region and then passes through the target meeting region ", there are two target regions, the first target region is the evasive region at the left side, and the second target region is the other side of the target meeting region; the method comprises the steps of sampling from a first target area to obtain a first end point, sampling from a second target area to obtain a second end point, and enabling an automatic driving vehicle to reach the first end point and then reach the second end point.

As another example, as shown in fig. 6, the traffic decision is "back and park in the evasive region on the right side", and when the reverse dynamic obstacle passes through the target meeting region and then passes through the target meeting region ", there are two target regions, the first target region is the evasive region on the right rear side, and the second target region is the other side of the target meeting region; the method comprises the steps of sampling from a first target area to obtain a first end point, sampling from a second target area to obtain a second end point, and enabling an automatic driving vehicle to reach the first end point and then reach the second end point.

As another example, as shown in fig. 6, the traffic decision is "back and park in the left avoidable area", and when the reverse dynamic obstacle passes through the target meeting area and then passes through the target meeting area ", there are two target areas, the first target area is the left rear avoidable area, and the second target area is the other side of the target meeting area; the method comprises the steps of sampling from a first target area to obtain a first end point, sampling from a second target area to obtain a second end point, and enabling an automatic driving vehicle to reach the first end point and then reach the second end point.

In the embodiment of the application, the performance information of the automatic driving vehicle and a plurality of selectable passing decisions of the automatic driving vehicle are taken as sampling constraints, the track of the automatic driving vehicle is sampled based on the first state information of the automatic driving vehicle, the second state information of the target obstacle and the prediction information of the target obstacle, the track which accords with any one of the performance information of the automatic driving vehicle and the selectable passing decisions of the automatic driving vehicle can be directly sampled, the track can also be sampled in an omnibearing way, and the track which meets the constraints is screened out from the sampled track based on the performance information of the automatic driving vehicle and the selectable passing decisions of the automatic driving vehicle. The embodiment of the present application is not limited thereto.

Wherein determining a plurality of sets of feasible control parameters based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle comprises: determining a plurality of first trajectories of the autonomous vehicle based on the first state information of the autonomous vehicle, the first trajectories being trajectories of the autonomous vehicle traveling through the target meeting area; determining a second track of the target obstacle based on the second state information of the target obstacle and the prediction information of the target obstacle, wherein the second track is a track of the target obstacle running through the target meeting area; and determining a plurality of feasible tracks from the plurality of first tracks based on the second track, and determining control parameters corresponding to the feasible tracks as a plurality of groups of feasible control parameters, wherein the feasible tracks are tracks without overlapping points with the second track.

It should be noted that, the autonomous vehicle may sample the track by any algorithm, for example, RS (Reeds-Shepp) curve, lattice (laidi) curve, etc., and the embodiment of the present application does not limit the sampling algorithm.

304. The autonomous vehicle selects a target control parameter from a plurality of sets of possible control parameters.

The target control parameter may be any one of a plurality of sets of possible control parameters, which is not limited in the embodiment of the present application.

In one possible implementation, the target control parameter is the optimal control parameter of the plurality of possible control parameter sets, as shown in fig. 7. Optionally, the autonomous vehicle selects the target control parameter from a plurality of sets of possible control parameters, including: and selecting the optimal control parameter from the plurality of groups of feasible control parameters as a target control parameter at the cost of any one or more of traffic efficiency, safety distance, kinematic stability and path stability.

The traffic efficiency cost is determined by the time of the automatic driving vehicle passing through the target meeting area, and the shorter the time of the automatic driving vehicle passing through the target meeting area is, the lower the traffic efficiency cost is. Optionally, the traffic efficiency penalty is:

relative_distance＝math::Clamp(adc_distance/adc_max_distance,0.0,1.0)；

forward_cost＝ego_forward_coe*std::cos(relative_longtitudinal_distance*M_PI*0.5)。

The safe distance cost is determined by the distance between the automatic driving vehicle and the target obstacle in the driving process, and the greater the distance between the automatic driving vehicle and the target obstacle is, the smaller the safe distance cost is. Optionally, the safe distance cost is:

obstacle_dynamic_cost＝dynamic_obs_safe_distance_coe*std::cos(relative_lateral_distance*M_PI/2.0)*std::cos(relative_lateral_distance*M_PI/2.0);

obstacle_static_cost＝static_obs_safe_distance_coe*std::cos(relative_lateral_distance*M_PI/2.0)*std::cos(relative_lateral_distance*M_PI/2.0);

safety_cost＝obstacle_dynamic_cost+obstacle_static_cost。

the kinematic stability penalty is determined by the acceleration of the autonomous vehicle, the smaller the kinematic stability penalty of the autonomous vehicle. Optionally, the kinematic stability penalty is:

kinematic_cost＝acc_cost(trajectory)+jerk_cost(trajectory)+centripetal_cost(trajectory)。

The path stability cost is determined by the path of the autonomous vehicle, the straighter the path, the lower the path stability cost of the autonomous vehicle. Optionally, the path stability penalty is:

stableness_cost＝FDE_cost(trajectory,pre_trajectory)+ADE_cost(trajectory,pre_trajectory)。

It should be noted that, in the embodiment of the present application, the automatic driving vehicle may select the target control parameter from multiple sets of possible control parameters, which may be directly selected, or may first determine an optimal traffic decision, and then select the target control parameter from multiple sets of possible control parameters corresponding to the traffic decision.

In one possible implementation, the autonomous vehicle selects a target control parameter from a plurality of possible control parameters, including: and determining an optimal passing decision in a plurality of passing decisions based on a plurality of sets of feasible control parameters by the automatic driving vehicle, and determining a target control parameter from the plurality of sets of feasible control parameters corresponding to the optimal passing decision if the optimal passing decision corresponds to the plurality of sets of feasible control parameters, wherein the control effect of the target control parameter is higher than that of other sets of control parameters in the plurality of sets of feasible control parameters.

In another possible implementation, the autonomous vehicle directly selects a target control parameter from among a plurality of sets of possible control parameters, the target control parameter having a control effect that is higher than the control effect of the other sets of control parameters in the plurality of sets of possible control parameters.

305. The autonomous vehicle controls the autonomous vehicle to travel through the target meeting area based on the target control parameter.

The automatic driving vehicle may be controlled to travel through the target meeting area based on the target control parameter, or the automatic driving vehicle may be controlled to travel through the target meeting area based on the target control parameter, where steps 302 to 305 are repeatedly performed continuously during the traveling process to obtain an updated target control parameter, and the automatic driving vehicle is controlled to travel through the target meeting area based on the updated target control parameter.

In addition, in the embodiment of the application, when the feasible control parameters are determined, the static obstacle, the same-direction dynamic obstacle and the reverse dynamic obstacle are considered at the same time, so that the safety of the automatic driving vehicle passing through the target meeting area is improved.

According to the embodiment of the application, the forced, yielding and reversing yielding of the automatic driving vehicle are supported, more abundant passing decisions are provided, and more complex meeting scenes can be dealt with.

In addition, in the embodiment of the application, when the target control parameter is determined, unnecessary spot brake and sudden brake conditions can be reduced at the cost of kinematic stability, and the safety of the automatic driving vehicle is improved.

Fig. 8 is a schematic structural diagram of an automatic driving vehicle driving device according to an embodiment of the present application, referring to fig. 8, the device includes:

The area determining module 801 is configured to determine, when a reverse dynamic obstacle is detected, a target meeting area of an autonomous vehicle and the reverse dynamic obstacle, where the target meeting area is an area where the autonomous vehicle and the reverse dynamic obstacle cannot pass through at the same time, and the reverse dynamic obstacle is a dynamic obstacle having a driving direction opposite to a driving direction of the autonomous vehicle;

A selection module 802 for selecting a target obstacle based on the target meeting area;

a parameter determining module 803 for determining a plurality of sets of feasible control parameters based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle;

The control module 804 is configured to select a target control parameter from the multiple sets of possible control parameters, and control the autonomous vehicle to travel through the target meeting area based on the target control parameter.

In one possible implementation, the parameter determining module 803 includes:

In a possible implementation manner, the parameter determining module 803 is configured to sample a trajectory of the autonomous vehicle based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle, and determine control parameters corresponding to the sampled trajectories as viable control parameters, with performance information of the autonomous vehicle and selectable multiple traffic decisions of the autonomous vehicle as sampling constraints.

In a possible implementation manner, the parameter determining module 803 is configured to determine a plurality of target areas based on a plurality of selectable traffic decisions, where the target areas are areas that the traffic decisions indicate the arrival of the autonomous vehicle; taking the performance information of the automatic driving vehicle and the plurality of target areas as sampling constraints, and sampling the track of the automatic driving vehicle based on the first state information of the automatic driving vehicle, the second state information of the target obstacle and the prediction information of the target obstacle so that the sampled track takes any one of the plurality of target areas as an end point.

In a possible implementation manner, the control module 804 is configured to determine, based on the multiple sets of feasible control parameters, an optimal passing decision among the multiple passing decisions, and if the optimal passing decision corresponds to the multiple sets of feasible control parameters, determine, from among the multiple sets of feasible control parameters corresponding to the optimal passing decision, the target control parameter, where a control effect of the target control parameter is higher than a control effect of other sets of control parameters in the multiple sets of feasible control parameters; or alternatively

The control module 804 is configured to directly select the target control parameter from the multiple sets of feasible control parameters, where a control effect of the target control parameter is higher than a control effect of other sets of control parameters in the multiple sets of feasible control parameters.

In a possible implementation manner, the control module 804 is configured to select, from the multiple sets of possible control parameters, an optimal control parameter as the target control parameter at the cost of any one or more of traffic efficiency, safe distance, kinematic stability, and path stability.

In one possible implementation, the selecting module 802 is configured to perform at least one of:

In one possible implementation manner, the area determining module 801 is configured to determine, when a reverse dynamic obstacle is detected, an area in a front passable area having a width smaller than a sum of the first width, the second width, and a meeting safety distance as the target meeting area based on the first width of the reverse dynamic obstacle and the second width of the autonomous vehicle.

It should be noted that: in the calibration of the automatic driving vehicle driving device provided in the above embodiment, only the division of the above functional modules is used for illustration, and in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the automatic driving vehicle is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the driving device of the automatic driving vehicle provided in the above embodiment and the driving method embodiment of the automatic driving vehicle belong to the same concept, and the specific implementation process is detailed in the method embodiment, and will not be described herein again.

Fig. 9 is a schematic structural view of an autonomous vehicle according to an embodiment of the present application. The autonomous vehicle 900 includes: a processor 901 and a memory 902.

Processor 901 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 901 may be implemented in at least one hardware form of DSP (DIGITAL SIGNAL Processing), FPGA (Field-Programmable gate array), PLA (Programmable Logic Array ). Processor 901 may also include a main processor, which is a processor for processing data in an awake state, also referred to as a CPU (Central Processing Unit ), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 901 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen. In some embodiments, the processor 901 may also include an AI (ARTIFICIAL INTELLIGENCE ) processor for processing computing operations related to machine learning.

The memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 902 is used to store at least one program code for execution by processor 901 to implement the autonomous vehicle driving method provided by the method embodiments of the present application.

In some embodiments, autonomous vehicle 900 may optionally further include: a peripheral interface 903, and at least one peripheral. The processor 901, memory 902, and peripheral interface 903 may be connected by a bus or signal line. The individual peripheral devices may be connected to the peripheral device interface 903 via buses, signal lines, or circuit boards. Specifically, the peripheral device includes: at least one of radio frequency circuitry 904, a display 905, a camera 906, audio circuitry 907, positioning components 908, and a power source 909.

The peripheral interface 903 may be used to connect at least one peripheral device associated with an I/O (Input/Output) to the processor 901 and the memory 902. In some embodiments, the processor 901, memory 902, and peripheral interface 903 are integrated on the same chip or circuit board; in some other embodiments, either or both of the processor 901, the memory 902, and the peripheral interface 903 may be implemented on separate chips or circuit boards, which is not limited in this embodiment.

The Radio Frequency circuit 904 is configured to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 904 communicates with a communication network and other communication devices via electromagnetic signals. The radio frequency circuit 904 converts an electrical signal into an electromagnetic signal for transmission, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 904 includes: antenna systems, RF transceivers, one or more amplifiers, tuners, oscillators, digital signal processors, codec chipsets, subscriber identity module cards, and so forth. The radio frequency circuit 904 may communicate with other autonomous vehicles via at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: metropolitan area networks, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks, and/or WiFi (WIRELESS FIDELITY ) networks. In some embodiments, the radio frequency circuit 904 may further include NFC (NEAR FIELD Communication) related circuits, which is not limited by the present application.

The display 905 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display 905 is a touch display, the display 905 also has the ability to capture touch signals at or above the surface of the display 905. The touch signal may be input as a control signal to the processor 901 for processing. At this time, the display 905 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 905 may be one, providing a front panel of the autonomous vehicle 900; in other embodiments, the display 905 may be at least two, each disposed on a different surface of the autonomous vehicle 900 or in a folded configuration; in still other embodiments, the display 905 may be a flexible display disposed on a curved surface or a folded surface of the autonomous vehicle 900. Even more, the display 905 may be arranged in an irregular pattern other than rectangular, i.e., a shaped screen. The display 905 may be made of LCD (Liquid CRYSTAL DISPLAY), OLED (Organic Light-Emitting Diode) or other materials.

The camera assembly 906 is used to capture images or video. Optionally, the camera assembly 906 includes a front camera and a rear camera. The front camera is arranged on the front panel of the automatic driving vehicle, and the rear camera is arranged on the back of the automatic driving vehicle. In some embodiments, the at least two rear cameras are any one of a main camera, a depth camera, a wide-angle camera and a tele camera, so as to realize that the main camera and the depth camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize a panoramic shooting and Virtual Reality (VR) shooting function or other fusion shooting functions. In some embodiments, camera assembly 906 may also include a flash. The flash lamp can be a single-color temperature flash lamp or a double-color temperature flash lamp. The dual-color temperature flash lamp refers to a combination of a warm light flash lamp and a cold light flash lamp, and can be used for light compensation under different color temperatures.

The audio circuit 907 may include a microphone and a speaker. The microphone is used for collecting sound waves of users and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 901 for processing, or inputting the electric signals to the radio frequency circuit 904 for voice communication. For purposes of stereo acquisition or noise reduction, a plurality of microphones may be provided at different portions of the autonomous vehicle 900, respectively. The microphone may also be an array microphone or an omni-directional pickup microphone. The speaker is used to convert electrical signals from the processor 901 or the radio frequency circuit 904 into sound waves. The speaker may be a conventional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, not only the electric signal can be converted into a sound wave audible to humans, but also the electric signal can be converted into a sound wave inaudible to humans for ranging and other purposes. In some embodiments, the audio circuit 907 may also include a headphone jack.

The location component 908 is used to locate the current geographic location of the autonomous vehicle 900 to enable navigation or LBS (Location Based Service, location-based services). The positioning component 908 may be a positioning component based on the United states GPS (Global Positioning System ), the Beidou system of China, the Granati system of Russia, or the Galileo system of the European Union.

The power supply 909 is used to power the various components in the autonomous vehicle 900. The power supply 909 may be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 909 includes a rechargeable battery, the rechargeable battery can support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, autonomous vehicle 900 also includes one or more sensors 910. The one or more sensors 910 include, but are not limited to: acceleration sensor 911, gyroscope sensor 912, pressure sensor 913, fingerprint sensor 914, optical sensor 915, and proximity sensor 916.

The acceleration sensor 911 may detect the magnitudes of accelerations on three coordinate axes of a coordinate system established with the autonomous vehicle 900. For example, the acceleration sensor 911 may be used to detect components of gravitational acceleration in three coordinate axes. The processor 901 may control the display 905 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal acquired by the acceleration sensor 911. The acceleration sensor 911 may also be used for the acquisition of motion data of a game or a user.

The gyro sensor 912 may detect the body direction and the rotation angle of the autonomous vehicle 900, and the gyro sensor 912 may collect the 3D motion of the user on the autonomous vehicle 900 in cooperation with the acceleration sensor 911. The processor 901 may implement the following functions according to the data collected by the gyro sensor 912: motion sensing (e.g., changing UI according to a tilting operation by a user), image stabilization at shooting, game control, and inertial navigation.

The pressure sensor 913 may be provided at a side frame of the autonomous vehicle 900 and/or at an underside of the display 905. When the pressure sensor 913 is provided at the side frame of the autonomous vehicle 900, a grip signal of the user on the autonomous vehicle 900 may be detected, and the processor 901 performs a left-right hand recognition or a quick operation according to the grip signal collected by the pressure sensor 913. When the pressure sensor 913 is provided at the lower layer of the display 905, the processor 901 performs control of the operability control on the UI interface according to the pressure operation of the user on the display 905. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

The fingerprint sensor 914 is used for collecting the fingerprint of the user, and the processor 901 identifies the identity of the user according to the fingerprint collected by the fingerprint sensor 914 or the fingerprint sensor 914 identifies the identity of the user according to the collected fingerprint. Upon recognizing that the user's identity is a trusted identity, the processor 901 authorizes the user to perform relevant sensitive operations including unlocking the screen, viewing encrypted information, downloading software, paying for and changing settings, etc. The fingerprint sensor 914 may be provided on the front, back, or side of the autonomous vehicle 900. When a physical key or vendor Logo is provided on the autonomous vehicle 900, the fingerprint sensor 914 may be integrated with the physical key or vendor Logo.

The optical sensor 915 is used to collect the intensity of ambient light. In one embodiment, the processor 901 may control the display brightness of the display panel 905 based on the intensity of ambient light collected by the optical sensor 915. Specifically, when the ambient light intensity is high, the display luminance of the display screen 905 is turned up; when the ambient light intensity is low, the display luminance of the display panel 905 is turned down. In another embodiment, the processor 901 may also dynamically adjust the shooting parameters of the camera assembly 906 based on the ambient light intensity collected by the optical sensor 915.

A proximity sensor 916, also referred to as a distance sensor, is provided on the front panel of the autonomous vehicle 900. The proximity sensor 916 is used to capture the distance between the user and the front of the autonomous vehicle 900. In one embodiment, when the proximity sensor 916 detects a gradual decrease in the distance between the user and the front of the autonomous vehicle 900, the processor 901 controls the display 905 to switch from the bright screen state to the off screen state; when the proximity sensor 916 detects that the distance between the user and the front of the autonomous vehicle 900 gradually increases, the processor 901 controls the display panel 905 to switch from the off-screen state to the on-screen state.

Those skilled in the art will appreciate that the configuration shown in fig. 9 is not limiting of the autonomous vehicle 900 and may include more or fewer components than shown, or may combine certain components, or may employ a different arrangement of components.

Fig. 10 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 1000 may have a relatively large difference due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 1001 and one or more memories 1002, where at least one program code is stored in the memories 1002, and the at least one program code is loaded and executed by the processors 1001 to implement the methods provided in the foregoing method embodiments. Of course, the server may also have a wired or wireless network interface, a keyboard, an input/output interface, and other components for implementing the functions of the device, which are not described herein.

The server 1000 is configured to perform the steps performed by the server in the method embodiments described above.

In an exemplary embodiment, a computer readable storage medium, such as a memory, comprising program code executable by a processor in a computer device to perform the autonomous vehicle driving method of the above embodiment is also provided. For example, the computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

In an exemplary embodiment, a computer program or a computer program product is also provided, which comprises computer program code which, when executed by a computer, causes the computer to implement the method of autonomous vehicle driving in the above-described embodiments.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the above storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The foregoing description of the preferred embodiments of the present application is not intended to limit the application, but rather, the application is to be construed as limited to the appended claims.

Claims

1. A method of driving an autonomous vehicle, the method comprising:

selecting a target obstacle based on the target meeting area;

2. The method of claim 1, wherein the determining a plurality of sets of viable control parameters based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle comprises:

Taking performance information of the automatic driving vehicle and selectable multiple passing decisions of the automatic driving vehicle as sampling constraints, sampling the track of the automatic driving vehicle based on the first state information of the automatic driving vehicle, the second state information of the target obstacle and the prediction information of the target obstacle, and determining control parameters corresponding to the sampled tracks as feasible control parameters.

3. The method of claim 2, wherein the trajectory comprises a path and a speed; the performance information comprises at least one of a speed range, an acceleration range or a curvature range, wherein the speed range is used for restraining the speed corresponding to the track obtained by sampling to belong to the speed range, the acceleration range is used for restraining the acceleration corresponding to the track obtained by sampling to belong to the acceleration range, and the curvature range is used for restraining the curvature of the path corresponding to the track obtained by sampling to belong to the curvature range.

4. The method of claim 2, wherein the selectable plurality of traffic decisions for the autonomous vehicle includes at least one of:

5. The method of claim 2, wherein sampling the trajectory of the autonomous vehicle based on the first state information of the autonomous vehicle, the second state information of the target obstacle, and the predicted information of the target obstacle with the performance information of the autonomous vehicle and the selectable plurality of traffic decisions of the autonomous vehicle as sampling constraints comprises:

Determining a plurality of target areas based on a plurality of selectable traffic decisions, wherein the target areas are areas which the traffic decisions indicate the arrival of the automatic driving vehicle;

Taking the performance information of the automatic driving vehicle and the plurality of target areas as sampling constraints, and sampling the track of the automatic driving vehicle based on the first state information of the automatic driving vehicle, the second state information of the target obstacle and the prediction information of the target obstacle so that the sampled track takes any one of the plurality of target areas as an end point.

6. The method of claim 2, wherein the selecting the target control parameter from the plurality of sets of possible control parameters comprises:

Determining an optimal passing decision among the plurality of passing decisions based on the plurality of sets of feasible control parameters, and determining the target control parameter from the plurality of sets of feasible control parameters corresponding to the optimal passing decision if the optimal passing decision corresponds to the plurality of sets of feasible control parameters, wherein the control effect of the target control parameter is higher than the control effect of other sets of control parameters in the plurality of sets of feasible control parameters; or alternatively

And directly selecting the target control parameters from the plurality of groups of feasible control parameters, wherein the control effect of the target control parameters is higher than that of other groups of control parameters in the plurality of groups of feasible control parameters.

7. The method of claim 1, wherein said selecting a target control parameter from said plurality of sets of possible control parameters comprises:

And selecting the optimal control parameter from the plurality of groups of feasible control parameters as the target control parameter at the cost of any one or more of traffic efficiency, safe distance, kinematic stability and path stability.

8. The method of claim 1, wherein the selecting a target obstacle based on the target meeting area comprises at least one of:

9. The method according to any one of claims 1 to 8, wherein in the event that a reverse dynamic obstacle is detected, determining a target meeting area for an autonomous vehicle with the reverse dynamic obstacle comprises:

In the case of detecting a reverse dynamic obstacle, a region of a front passable region having a width smaller than a sum of the first width, the second width, and a meeting safety distance is determined as the target meeting region based on a first width of the reverse dynamic obstacle and a second width of the autonomous vehicle.

10. An autonomous vehicle comprising one or more processors and one or more memories having stored therein at least one program code loaded and executed by the one or more processors to perform the operations performed by the autonomous vehicle driving method of any of claims 1-9.