CN115562280A - Path planning method, device and storage medium for automatically driving vehicle to get rid of trouble - Google Patents

Abstract

The application provides a path planning method, a device and a storage medium for automatically driving a vehicle to get rid of difficulties, wherein the method comprises the following steps: acquiring the vehicle direction and the surrounding perception information of the automatic driving vehicle in a blocking bypassing mode; determining a target point and a terminal point in the vehicle periphery perception information according to the vehicle periphery perception information; calculating a detour path according to the vehicle position, the target point and the terminal point; and checking the detour path, and outputting the detour path when the automatic driving vehicle does not collide with surrounding obstacles when the automatic driving vehicle runs along the detour path. According to the method and the device, the detour path is calculated according to the vehicle position, the target point and the terminal point under the blocking detour mode, and when the automatic driving vehicle drives according to the detour path, the detour path is output when the automatic driving vehicle does not collide with surrounding obstacles, so that when the automatic driving vehicle blocks under a complex road environment, path planning can be actively carried out, and the purpose of getting rid of difficulties is achieved.

Description

Path planning method, device and storage medium for automatic driving vehicle escape

technical field

The present application relates to the technical field of automatic driving, and more specifically relates to a route planning method, device and storage medium for automatic driving vehicles to get out of trouble.

Background technique

In the field of autonomous driving technology, for how to solve the problem of getting out of trouble in the case of congestion, R & D personnel are more focused on the solution of getting out of trouble for motor vehicles on structured roads. For example, a common treatment method is: 1. Keep a sufficient distance from the vehicle in front (generally enough distance can ensure that the vehicle will turn out in place); Inner bypass implementation). This is a passive and conservative approach, which has very high requirements for passing space.

But on the open road, because the road conditions are complicated, and the distance of the front vehicle is too large, when encountering jamming, overtaking and other behaviors, it is difficult to apply the above-mentioned technical solution. Therefore cause the escape strategy of motor vehicle not flexible enough, easily fall into blockage again when escape, can't really escape the problem of difficulty.

Contents of the invention

This application was made in order to solve the above-mentioned problems. According to one aspect of the present application, there is provided a path planning method for an autonomous vehicle to get out of trouble, the method comprising:

In the blocking bypass mode, obtain the vehicle orientation and surrounding perception information of the self-driving vehicle;

determining a target point and an end point in the vehicle circumference perception information according to the vehicle circumference perception information;

calculating a detour route according to the vehicle orientation, the target point and the end point;

The detour route is checked, and when the self-driving vehicle does not collide with surrounding obstacles while driving according to the detour route, the detour route is output.

In an embodiment of the present application, in the blocking bypass mode, before acquiring the vehicle orientation and vehicle circumference perception information of the autonomous vehicle, the method further includes:

When the speed of the self-driving vehicle is zero, determine whether the self-driving vehicle is in a blocked environment;

When the self-driving vehicle is in a blocked environment, the blocked bypass mode is triggered.

In one embodiment of the present application, determining the target point and the end point in the vehicle circumference perception information according to the vehicle circumference perception information includes:

Taking the position where there is no obstacle in the perception information around the vehicle as the end point;

Determining the complex driving path from the self-driving vehicle to the terminal point, splitting the complex driving path into at least two simple driving paths, and using the connection of each two simple driving paths as the target point .

In one embodiment of the present application, calculating a detour route according to the vehicle orientation, the target point and the end point includes:

The detour path is obtained by performing calculation based on an obstacle avoidance path planning algorithm of an open road.

In one embodiment of the present application, calculation is performed based on an obstacle avoidance path planning algorithm for open roads, and the detour path is obtained, including:

planning a collision-free path through a hybrid A* algorithm according to the vehicle orientation, the target point, and the end point;

The collision-free path is optimized by using a quadratic convex optimization algorithm to obtain the detour path.

In one embodiment of the present application, checking the detour route includes:

checking for static obstacles in the detour path to determine whether the self-driving vehicle will collide with the static obstacles;

calculating a speed profile of the self-driving vehicle to determine whether the self-driving vehicle will collide with a dynamic obstacle;

When the automatic driving vehicle will not collide with the static obstacle and the dynamic obstacle, it is determined that the automatic driving vehicle will not collide with the surrounding obstacles.

In an embodiment of the present application, after outputting the detour path, the method further includes:

The vehicle is guided to travel to the end point according to the detour route.

In an embodiment of the present application, after guiding the vehicle to the destination according to the detour route, the method further includes:

judging whether the driving vehicle meets the conditions for exiting the blocking bypass mode;

When the condition for exiting the blocking bypass mode is met, the blocking bypass mode is exited.

In one embodiment of the present application, judging whether the self-driving vehicle meets the conditions for exiting the congestion bypass mode includes:

Reacquiring the current orientation and current perception information of the self-driving vehicle to determine whether there is an obstacle in front of the self-driving vehicle;

Planning the driving path of the self-driving vehicle in a non-blocking mode to determine whether the self-driving vehicle will collide with an obstacle;

When there is no obstacle in front of the self-driving vehicle, and the self-driving vehicle will not collide with the obstacle, it is determined that the self-driving vehicle meets the conditions for exiting the blocking bypass mode.

According to another aspect of the present application, there is provided a path planning device for an autonomous vehicle to get out of trouble, the device comprising:

A memory and a processor, the memory stores a computer program run by the processor, and when the computer program is run by the processor, the processor executes the aforementioned path planning method for self-driving vehicles to get out of trouble .

According to still another aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the computer program is run by a processor, the processor executes the above-mentioned path planning method for getting out of trouble for an automatic driving vehicle.

According to the path planning method, device and storage medium for autonomous driving vehicles to get out of trouble in the present application, in the blocked bypass mode, the bypass path is calculated according to the vehicle orientation, target point and destination, and when the automatic driving vehicle follows the bypass path When driving, if there is no collision with surrounding obstacles, the detour path is output, so that when the self-driving vehicle is blocked in a complex road environment, it can actively plan the path to achieve escape.

Description of drawings

The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used together with the embodiments of the present application to explain the present application, and do not constitute limitations to the present application. In the drawings, the same reference numerals generally represent the same components or steps.

FIG. 1 shows a schematic flowchart of a path planning method for an autonomous vehicle to get out of trouble according to an embodiment of the present application;

Fig. 2 shows a schematic block diagram of a path planning device for an autonomous vehicle to get out of trouble according to an embodiment of the present application.

detailed description

In order to make the objects, technical solutions, and advantages of the present application more apparent, exemplary embodiments according to the present application will be described in detail below with reference to the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described here. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

At present, automatic driving control technology has become a hot spot in the field of driving due to its high technical requirements, high difficulty and complex problems. The characteristics of my country's urban roads are that there are fewer conventional roads (6 lanes, 8 lanes) and expressways, more roads in urban areas, and more narrow roads with complex road conditions between urban and rural areas (no more than 3 lanes). ) and roads where non-motor vehicles and motor vehicles are mixed. Especially for unstructured roads, unconventional scenarios such as temporary parking, illegal parking, roadside stalls occupying roads, and construction roads are often encountered. Compared with conventional road sections, unstructured roads are narrower, the road structure is more complex, pedestrians and non-motor vehicles interact more, and they often encounter the problem of being blocked and impassable. Therefore, how to achieve congestion relief in this environment is particularly important for autonomous driving capabilities, and is an important technical guarantee for whether autonomous driving can land on urban roads.

Based on the aforementioned technical problems, the present application provides a path planning method for an autonomous vehicle to get out of trouble. The method includes: acquiring the vehicle orientation and vehicle circumference perception information of the autonomous vehicle in the blocking bypass mode; determining the target point and the end point in the vehicle circumference perception information according to the vehicle circumference perception information; Orientation, the target point and the end point to calculate the detour path; check the detour path, when the self-driving vehicle will not collide with surrounding obstacles when driving according to the detour path, then output the detour path. By calculating the detour path according to the vehicle orientation, target point and end point in the blocking detour mode, and when the self-driving vehicle drives according to the detour path without colliding with surrounding obstacles, the detour is output Path, so that when the self-driving vehicle is blocked in a complex road environment, it can actively plan the path to get out of trouble.

The scheme of the route planning method for an autonomous vehicle to get out of trouble according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings. On the premise of no conflict, the features of the various embodiments of the present application can be combined with each other.

Fig. 1 shows a schematic flow chart of a path planning method for an automatic driving vehicle to get out of trouble according to an embodiment of the present application; as shown in Fig. 1 , the method for planning a path 100 for an automatic driving vehicle to get out of trouble according to an embodiment of the present application may include the following steps S101 , Step S102, Step S103 and Step S104:

In step S101, the vehicle orientation and vehicle circumference perception information of the autonomous vehicle is acquired in the congestion bypass mode.

In an embodiment of the present application, in the blocking bypass mode, before acquiring the vehicle orientation and vehicle circumference perception information of the autonomous vehicle, the method further includes:

A1, when the speed of the self-driving vehicle is zero, judging whether the self-driving vehicle is in a congested environment; A2, when the self-driving vehicle is in a congested environment, triggering the congested detour mode.

In this application, when judging whether to trigger the blocking bypass mode, the state of the autonomous vehicle needs to be considered. For example, the prerequisite for triggering the blocking bypass mode is that the autonomous vehicle must be in a stationary state. At the same time, it is also necessary to combine the status of static obstacles around the self-driving vehicle to determine whether the self-driving vehicle is actually blocked or temporarily parked. For example, if there are no obstacles or fewer obstacles around, it may be a temporary stop. At the same time, it is also necessary to combine the relative positional relationship between the obstacle and the self-driving vehicle to determine whether the front block or the side block is blocked. Through the above judgments, some special scenarios can be filtered out, for example, when vehicles are waiting in line for a red light and other temporary parking situations, so as to avoid erroneous operations.

In step S102, a target point and an end point in the vehicle circumference perception information are determined according to the vehicle circumference perception information.

In one embodiment of the present application, determining the target point (goalpoint) and the end point in the vehicle circumference perception information according to the vehicle circumference perception information includes:

B1, taking the position where there is no obstacle in the perception information around the vehicle as the end point;

B2. Determine the complex driving channel from the self-driving vehicle to the terminal point, split the complex driving channel into at least two simple driving channels, and use the connection of each two simple driving channels as the Target.

In the embodiment of the present application, the selection of the target point is crucial to the calculation of the detour path, and a reasonable target point can greatly speed up the calculation and improve the success rate of the detour. The basic principle of target point selection is: split the complex driving channel into several simple driving channels, avoid using a point that is directly circled as the target point, but choose a simple way point, and the target point A little bit closer to the finish line. In the embodiment of the present application, the self-driving vehicle can actively and flexibly find the target point, and can get out of trouble more effectively.

The endpoint in this application refers to the position where the self-driving vehicle exits the obstructed environment.

In step S103, a detour route is calculated according to the vehicle orientation, the target point and the end point.

In one embodiment of the present application, calculating the detour route according to the vehicle orientation, the target point and the end point includes: calculating based on an open space obstacle avoidance route planning algorithm to obtain the detour route line path.

In the embodiment of the present application, the basic algorithm for calculating the detour path is an openspace-based obstacle avoidance path planning, and many methods in traditional technologies can be used to implement the openspace-based obstacle avoidance path planning. For example, one of the more reliable methods that has been verified in practice is: first, set a reasonable heuristic function, search for a rough collision-free path through the hybrid A* (hybridA*) algorithm, and then use the quadratic convex optimization (QP) method to get a smooth collision-free final path.

In a specific example, calculation is performed based on an obstacle avoidance path planning algorithm for open roads, and the detour path is obtained, including:

C1, planning a collision-free path through a hybrid A* (hybridA*) algorithm according to the vehicle orientation, the target point, and the end point;

C2. Optimizing the collision-free path by using a quadratic convex optimization (QP) algorithm to obtain the detour path.

In step S104, the detour route is checked, and when the self-driving vehicle does not collide with surrounding obstacles while driving along the detour route, the detour route is output.

In one embodiment of the present application, checking the detour route includes:

D1, checking a static obstacle in the detour path, and determining whether the self-driving vehicle will collide with the static obstacle;

D2, calculating the speed curve of the self-driving vehicle, and determining whether the self-driving vehicle will collide with a dynamic obstacle;

D3. When the automatic driving vehicle will not collide with the static obstacle and the dynamic obstacle, determine that the automatic driving vehicle will not collide with the surrounding obstacles.

In the embodiment of the present application, after the detour route is planned, the detour route may also be checked to determine the feasibility of the detour route and ensure the success rate of getting out of trouble.

In an embodiment of the present application, after the detour route is output, the method further includes: guiding the vehicle to travel to the end point according to the detour route.

In an example, after guiding the vehicle to travel to the end point according to the detour route, the method further includes:

E1, judging whether the driving vehicle meets the conditions for exiting the blocking bypass mode;

E2. Exit the blocking bypass mode when the conditions for exiting the blocking bypass mode are met.

In an example, judging whether the self-driving vehicle meets the conditions for exiting the congestion bypass mode includes:

F1, reacquiring the current orientation of the self-driving vehicle and the current perception information around the vehicle to determine whether there is an obstacle in front of the self-driving vehicle;

F2, planning the driving path of the self-driving vehicle in a non-blocking mode, to determine whether the self-driving vehicle will collide with an obstacle;

F3. When there is no obstacle in front of the self-driving vehicle, and the self-driving vehicle will not collide with the obstacle, determine that the self-driving vehicle meets the conditions for exiting the blocking bypass mode.

In this application, when the escape is successful, the self-driving vehicle will return to the normal driving mode for driving. Therefore, when the self-driving vehicle reaches the destination, it will make a judgment to confirm whether to exit the blocking bypass mode. If the conditions for exiting the blocking bypass mode are met, it will exit the blocking bypass mode and return to the normal driving mode. If the condition of the blocking bypass mode is blocked, the bypass path is re-planned in the blocking bypass mode. Confirm that the blocking bypass mode must meet the following conditions: 1. There is no blocking obstacle in front; 2. It is feasible to switch back to the normal mode state. Therefore, it is necessary to plan a planned route in normal mode to ensure that the self-driving vehicle will not collide with obstacles when driving in normal mode.

The embodiment of the present application calculates the detour route according to the vehicle orientation, target point and end point in the blocking detour mode, and when the self-driving vehicle will not collide with the surrounding obstacles when driving according to the detour route, then output The detour path enables the self-driving vehicle to actively plan the path when it is blocked in a complex road environment, so as to get out of trouble.

The following describes the path planning device for an automatic driving vehicle getting out of trouble in the present application with reference to FIG. 2 , wherein FIG. 2 shows a schematic block diagram of a path planning device for getting out of trouble for an automatic driving vehicle according to an embodiment of the present application.

As shown in FIG. 2 , the path planning device 200 for an autonomous vehicle to get out of trouble includes: one or more memories 201 and one or more processors 202, the memory 201 is stored with a computer program run by the processor 202, When the computer program is run by the processor 202 , the processor 202 executes the above-mentioned path planning method for the automatic driving vehicle to get out of trouble.

The apparatus 200 may be a part or all of computer equipment that can realize the path planning method for autonomous driving vehicles to get out of trouble by means of software, hardware or a combination of software and hardware.

As shown in FIG. 2 , the path planning device 200 for an autonomous vehicle to get out of trouble includes one or more memories 201, one or more processors 202, a display (not shown) and a communication interface, etc., and these components are connected via a bus system and/or Other forms of connection mechanisms (not shown) are interconnected. It should be noted that the components and structure of the path planning device 200 for autonomous driving vehicle escape shown in FIG. structure.

The memory 201 is used for storing various data and executable program instructions generated during the operation of the method of the present application, for example, for storing various application programs or algorithms for realizing various specific functions. One or more computer program products may be included, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and/or cache memory (cache). The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, and the like.

The processor 202 may be a central processing unit (CPU), a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other forms of processing with data processing capabilities and/or instruction execution capabilities. unit, and other components in device 200 may be used to perform desired functions.

In one example, the path planning device 200 for autonomous vehicle escape also includes an output device that can output various information (such as images or sounds) to the outside (such as a user), and may include one or more of a display device, a speaker, etc. .

The communication interface can be an interface of any currently known communication protocol, such as a wired interface or a wireless interface, wherein the communication interface can include one or more serial ports, USB interfaces, Ethernet ports, WiFi, wired networks, DVI interfaces, equipment Integrate interconnection modules or other suitable various ports, interfaces, or connections.

In addition, according to an embodiment of the present application, a storage medium is also provided, on which program instructions are stored, and when the program instructions are executed by a computer or a processor, they are used to execute the self-driving vehicle of the embodiment of the present application. The corresponding steps of the path planning method for getting out of trouble. The storage medium may include, for example, a memory card of a smart phone, a storage unit of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk ROM, etc. (CD-ROM), USB memory, or any combination of the above storage media.

The path planning device and storage medium for autonomous vehicles in the embodiments of the present application have the same advantages as the aforementioned path planning methods for autonomous vehicles because they can implement the aforementioned path planning methods for autonomous vehicles.

Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above-described example embodiments are exemplary only, and are not intended to limit the scope of the application thereto. Various changes and modifications can be made therein by those of ordinary skill in the art without departing from the scope and spirit of the application. All such changes and modifications are intended to be included within the scope of this application as claimed in the appended claims.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

In the description provided herein, numerous specific details are set forth. However, it is understood that the embodiments of the application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be understood that in the description of the exemplary embodiments of the application, in order to streamline the application and to facilitate understanding of one or more of the various inventive aspects, various features of the application are sometimes grouped together into a single embodiment, figure , or in its description. This method of application, however, is not to be interpreted as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as the corresponding claims reflect, the inventive point lies in that the corresponding technical problem may be solved by using less than all features of a single disclosed embodiment. Thus, the claims following this Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this application.

It will be appreciated by those skilled in the art that all features disclosed in this specification (including accompanying claims, abstract and drawings) and all features of any method or apparatus so disclosed may be used in any combination, except where the features are mutually exclusive. Processes or units are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

In addition, those skilled in the art will appreciate that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the present application. and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

The various component embodiments of the present application may be realized in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some modules according to the embodiments of the present application. The present application can also be implemented as an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program implementing the present application may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

The above is only the specific implementation of the application or the description of the specific implementation. The scope of protection of the application is not limited thereto. Any person familiar with the technical field can easily Any changes or substitutions that come to mind should be covered within the protection scope of the present application. The protection scope of the present application should be based on the protection scope of the claims.

Claims (11)

1. A path planning method for self-driving vehicles to get out of trouble, characterized in that the method comprises: In the blocking bypass mode, obtain the vehicle orientation and surrounding perception information of the self-driving vehicle; determining a target point and an end point in the vehicle circumference perception information according to the vehicle circumference perception information; calculating a detour route according to the vehicle orientation, the target point and the end point; The detour route is checked, and when the self-driving vehicle does not collide with surrounding obstacles while driving according to the detour route, the detour route is output. 2. The method according to claim 1, wherein, in the blocking bypass mode, before acquiring the vehicle orientation and vehicle circumference perception information of the autonomous vehicle, the method further comprises: When the speed of the self-driving vehicle is zero, determine whether the self-driving vehicle is in a blocked environment; When the self-driving vehicle is in a blocked environment, the blocked bypass mode is triggered. 3. The method according to claim 1, wherein determining the target point and the end point in the vehicle circumference perception information according to the vehicle circumference perception information comprises: Taking the position where there is no obstacle in the perception information around the vehicle as the end point; Determining the complex driving path from the self-driving vehicle to the terminal point, splitting the complex driving path into at least two simple driving paths, and using the connection of each two simple driving paths as the target point . 4. The method according to claim 1, wherein calculating a detour path according to the vehicle orientation, the target point and the end point comprises: The detour path is obtained by performing calculation based on an obstacle avoidance path planning algorithm of an open road. 5. The method according to claim 4, characterized in that, calculating based on the obstacle avoidance path planning algorithm of the open road, obtaining the detour path, comprises: planning a collision-free path through a hybrid A* algorithm according to the vehicle orientation, the target point, and the end point; The collision-free path is optimized by using a quadratic convex optimization algorithm to obtain the detour path. 6. The method according to claim 1, wherein checking the detour path comprises: checking for static obstacles in the detour path to determine whether the self-driving vehicle will collide with the static obstacles; calculating a speed profile of the self-driving vehicle to determine whether the self-driving vehicle will collide with a dynamic obstacle; When the automatic driving vehicle will not collide with the static obstacle and the dynamic obstacle, it is determined that the automatic driving vehicle will not collide with the surrounding obstacles. 7. The method according to claim 1, wherein after outputting the detour route, the method further comprises: The vehicle is guided to travel to the end point according to the detour route. 8. The method according to claim 7, wherein after guiding the vehicle to travel to the destination according to the detour route, the method further comprises: judging whether the driving vehicle meets the conditions for exiting the blocking bypass mode; When the condition for exiting the blocking bypass mode is met, the blocking bypass mode is exited. 9. The method according to claim 8, wherein judging whether the self-driving vehicle meets the conditions for exiting the blocking bypass mode comprises: Reacquiring the current orientation and current perception information of the self-driving vehicle to determine whether there is an obstacle in front of the self-driving vehicle; Planning the driving path of the self-driving vehicle in a non-blocking mode to determine whether the self-driving vehicle will collide with an obstacle; When there is no obstacle in front of the self-driving vehicle, and the self-driving vehicle will not collide with the obstacle, it is determined that the self-driving vehicle meets the conditions for exiting the blocking bypass mode. 10. A path planning device for self-driving vehicles to get out of trouble, characterized in that the device comprises: A memory and a processor, the memory stores a computer program run by the processor, and when the computer program is run by the processor, the processor executes the process described in any one of claims 1 to 9. The above-mentioned path planning method for self-driving vehicles to get out of trouble. 11. A storage medium, characterized in that a computer program is stored on the storage medium, and when the computer program is executed by a processor, the processor executes the automatic processing method according to any one of claims 1 to 9. A path planning method for driving a vehicle out of trouble.

Images