CN118012030A

CN118012030A - Path planning method, path planning device, vehicle, storage medium and computer program product

Info

Publication number: CN118012030A
Application number: CN202211335100.0A
Authority: CN
Inventors: 余开江
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Ruilian Xingchen Beijing Technology Co ltd
Priority date: 2022-10-28
Filing date: 2022-10-28
Publication date: 2024-05-10

Abstract

The present application relates to a path planning method, apparatus, vehicle, storage medium and computer program product. The method comprises the following steps: the method includes the steps of acquiring driving characteristic information of a first vehicle, driving characteristic information of a second vehicle related to driving intention of the first vehicle and driving environment characteristic information of the first vehicle, determining predicted driving corridor information of the second vehicle for indicating a predicted driving area of the second vehicle according to the driving characteristic information of the first vehicle and the driving characteristic information of the second vehicle, inputting the driving characteristic information of the first vehicle, the driving characteristic information of the second vehicle, the driving environment characteristic information and the predicted driving corridor information of the second vehicle into a generated countermeasure network, and determining predicted driving corridor information of the first vehicle for indicating the predicted driving area of the first vehicle according to output of the generated countermeasure network. By adopting the method, the accuracy of the planned lane corridor for the vehicle to run can be improved.

Description

Path planning method, path planning device, vehicle, storage medium and computer program product

Technical Field

The embodiment of the disclosure relates to the technical field of intelligent driving, in particular to a path planning method, a path planning device, a vehicle, a storage medium and a computer program product.

Background

With the development of intelligent driving technology, the intelligent driving automobile reduces the occurrence of traffic accidents to a certain extent and reduces the driving fatigue of drivers. The intelligent driving automobile acquires driving environment information by using sensing equipment such as a camera, a radar and the like, and plans a lane corridor for the vehicle to run according to the driving environment information.

However, the conventional technique has a problem in that the accuracy of the lane corridor in which the planned vehicle travels is low.

Disclosure of Invention

The disclosed embodiments provide a path planning method, apparatus, vehicle, storage medium and computer program product, which can be used to improve the accuracy of a planned lane corridor in which the vehicle is traveling.

In a first aspect, an embodiment of the present disclosure provides a path planning method, including:

acquiring driving characteristic information of a first vehicle, driving characteristic information of a second vehicle and driving environment characteristic information of the first vehicle, wherein the second vehicle is a vehicle related to the driving intention of the first vehicle;

Determining predicted travel corridor information of the second vehicle according to the travel characteristic information of the first vehicle and the travel characteristic information of the second vehicle, wherein the predicted travel corridor information of the second vehicle is used for indicating a predicted travel area of the second vehicle;

The driving characteristic information of the first vehicle, the driving characteristic information of the second vehicle, the driving environment characteristic information and the predicted driving corridor information of the second vehicle are input into a generated countermeasure network, and the predicted driving corridor information of the first vehicle is determined according to the output of the generated countermeasure network, wherein the predicted driving corridor information of the first vehicle is used for indicating the predicted driving area of the first vehicle.

In a second aspect, an embodiment of the present disclosure provides a path planning apparatus, the apparatus including:

The system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring running characteristic information of a first vehicle, running characteristic information of a second vehicle and running environment characteristic information of the first vehicle, and the second vehicle is a vehicle related to the running intention of the first vehicle;

A first determining module, configured to determine predicted driving corridor information of the second vehicle according to driving characteristic information of the first vehicle and driving characteristic information of the second vehicle, where the predicted driving corridor information of the second vehicle is used to indicate a predicted driving area of the second vehicle;

The planning module is used for inputting the running characteristic information of the first vehicle, the running characteristic information of the second vehicle, the running environment characteristic information and the predicted running corridor information of the second vehicle into a generated countermeasure network, and determining the predicted running corridor information of the first vehicle according to the output of the generated countermeasure network, wherein the predicted running corridor information of the first vehicle is used for indicating a predicted running area of the first vehicle.

In a third aspect, an embodiment of the present disclosure provides a vehicle, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the method of the first aspect when executing the computer program.

In a fourth aspect, an embodiment of the present disclosure provides a storage medium having stored thereon a computer program which, when executed by a processor, implements the method of the first aspect described above.

In a fifth aspect, embodiments of the present disclosure provide a computer program product comprising a computer program which, when executed by a processor, implements the method of the first aspect described above.

The path planning method, the path planning device, the computer equipment, the storage medium and the computer program product provided by the embodiment of the disclosure acquire the running characteristic information of the first vehicle, the running characteristic information of the second vehicle related to the running intention of the first vehicle and the running environment characteristic information of the first vehicle, further determine the predicted running corridor information of the second vehicle for indicating the predicted running area of the second vehicle according to the running characteristic information of the first vehicle and the running characteristic information of the second vehicle, so as to input the running characteristic information of the first vehicle, the running characteristic information of the second vehicle, the running environment characteristic information and the predicted running corridor information of the second vehicle into a generating countermeasure network, and determine the predicted running corridor information of the first vehicle for indicating the predicted running area of the first vehicle according to the output of the generating countermeasure network. The predicted driving corridor information of the second vehicle is determined according to the driving characteristic information of the first vehicle and the driving characteristic information of the second vehicle, so that the predicted driving corridor information of the second vehicle considers the driving conditions of the first vehicle and the second vehicle, is more accurate driving corridor information, and further, on the basis of the driving characteristic information of the first vehicle, the driving characteristic information of the second vehicle, the driving environment characteristic information and the predicted driving corridor information of the second vehicle, the predicted driving corridor information of the first vehicle determined by using the generated countermeasure network is more accurate, so that the problem that in the prior art, only driving environment information is acquired, and the lane accuracy of the vehicle driving caused by planning the lane corridor of the vehicle driving according to the driving environment information is lower is solved, and the lane accuracy of the planned vehicle driving is improved.

Drawings

Fig. 1 is an application environment diagram of a path planning method in an embodiment of the present application;

FIG. 2 is a flow chart of a path planning method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of predicted driving corridor information of a second vehicle according to an embodiment of the present application;

FIG. 4 is a schematic diagram of predicted driving corridor information of a first vehicle according to an embodiment of the present application;

FIG. 5 is a flow chart of a path planning method according to another embodiment of the present application;

FIG. 6 is a flow chart of a path planning method according to another embodiment of the application;

FIG. 7 is a schematic overall view of a first vehicle according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a scene understanding module according to an embodiment of the present application;

FIG. 9 is an overall schematic diagram of a path planning method according to an embodiment of the present application;

FIG. 10 is a block diagram of a path planning apparatus according to an embodiment of the present application;

Fig. 11 is an internal structural view of a vehicle in an embodiment of the application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the disclosed embodiments and are not intended to limit the disclosed embodiments.

First, before the technical solution of the embodiments of the present disclosure is specifically described, a description is given of a technical background or a technical evolution context on which the embodiments of the present disclosure are based. In general, in the field of intelligent driving, the current technical background is: with the popularization of intelligent driving vehicles, when using the intelligent driving vehicle, it is necessary to input a destination, the intelligent driving vehicle generates a travel route based on a current position and the destination, and travels according to the generated travel route. Therefore, the intelligent driving vehicle needs to be able to handle not only the running situation in the normal ideal state but also the running situation in some abnormal situations, such as an obstacle on a running road, a traffic accident, and the like. Therefore, the intelligent driving automobile needs to utilize the sensing equipment such as a camera, a radar and the like to predict the information of the driving corridor of the intelligent driving automobile, so as to carry out path planning on the intelligent driving automobile, thereby avoiding danger caused by abnormal conditions. Based on the background, the applicant discovers that the traditional technology has the problem of low accuracy of a planned lane corridor for running a vehicle through long-term model simulation research and development and collection, demonstration and verification of experimental data. Therefore, how to improve the accuracy of the lane corridor where the planned vehicle runs becomes a current challenge to be solved. In addition, it should be noted that, from the conventional technology, there is a low accuracy of the planned lane corridor in which the vehicle runs and the technical solutions described in the following embodiments, the applicant has made a lot of creative work.

The following describes a technical scheme related to an embodiment of the present disclosure in conjunction with a scenario in which the embodiment of the present disclosure is applied.

Fig. 1 is an application environment diagram of a path planning method according to an embodiment of the present application, and the path planning method provided by the embodiment of the present disclosure may be applied to the application environment shown in fig. 1. The first vehicle 102 is a currently used intelligent driving vehicle, the second vehicle 104 is a vehicle related to the driving intention of the first vehicle 102, and the first vehicle 102 communicates with the second vehicle 104, it may be understood that the second vehicle 104 may be a vehicle driven intelligently or a vehicle driven manually. The first and second vehicles may be, but are not limited to, various cars, commercial vehicles, buses, trucks, motorcycles, and the like.

Fig. 2 is a flow chart of a path planning method according to an embodiment of the present application, in an embodiment, as shown in fig. 2, a path planning method is provided, and the method is applied to the first vehicle in fig. 1 for illustration, and includes the following steps:

s201, traveling characteristic information of a first vehicle, traveling characteristic information of a second vehicle, which is a vehicle related to a traveling intention of the first vehicle, and traveling environment characteristic information of the first vehicle are acquired.

In this embodiment, the first vehicle is an intelligent driving car currently in use, i.e., a host vehicle; the second vehicle is a vehicle that is related to the traveling intention of the first vehicle, i.e., the other vehicle. A vehicle that is related to the traveling intention of the first vehicle may be understood as a vehicle that the first vehicle needs to pay attention to during traveling. For example, when the first vehicle travels in lane 1 and vehicle a is traveling in the vicinity of lane 2 on the left side of the first vehicle, the first vehicle needs to consider vehicle a if it wants to change lanes, and thus vehicle a is a second vehicle related to the traveling intention of the first vehicle.

Further, the first vehicle acquires the travel characteristic information of the first vehicle, the travel characteristic information of the second vehicle, and the travel environment characteristic information of the first vehicle related to the travel intention of the first vehicle. Wherein the driving characteristic information is a kinematically related parameter of the vehicle during driving, for example, the driving characteristic information may include speed information, angular speed information, and the like; the running environment characteristic information is a relevant parameter of the environment in which the vehicle is located during running, and for example, the running environment characteristic information may include lane line information, road boundary information, and the like. The driving characteristic information and the driving environment characteristic information are both information related to time, for example, the first vehicle acquires the driving characteristic information and the driving environment characteristic information of each time frame in a preset time period.

The first vehicle may acquire the travel characteristic information of the first vehicle, the travel characteristic information of the second vehicle, and the travel environment characteristic information of the first vehicle through its own sensor, such as a visual sensor, an inertial sensor, and the like. The first vehicle may also acquire the driving characteristic information of the first vehicle and the driving environment characteristic information of the first vehicle via its own sensors, and acquire the driving characteristic information of the second vehicle via a communication link, for example, via vehicle-to-vehicle (vehicle-to-vehicle) communication. The first vehicle may also obtain, through the server, driving characteristic information of the first vehicle, driving characteristic information of the second vehicle, and driving environment characteristic information of the first vehicle, which is not limited to this embodiment.

S202, determining predicted driving corridor information of the second vehicle according to driving characteristic information of the first vehicle and driving characteristic information of the second vehicle, wherein the predicted driving corridor information of the second vehicle is used for indicating a predicted driving area of the second vehicle.

In the present embodiment, the first vehicle can determine the predicted travel corridor information of the second vehicle based on the travel characteristic information of the first vehicle and the travel characteristic information of the second vehicle. Wherein the predicted driving corridor information can represent a possible driving area of the vehicle in a future period of time. That is, the predicted travel corridor information of the second vehicle is used to indicate the predicted travel area of the second vehicle.

For example, fig. 3 is a schematic diagram of predicted driving corridor information of the second vehicle. Referring to fig. 3, the predicted driving corridor information of the second vehicle 302 is shown as a dotted line area in fig. 3, and it can be seen from the predicted driving corridor information of the second vehicle 302 that the second vehicle 302 is about to change lane 1 to lane 2 within a future period of time, for example, 3 minutes.

Referring to fig. 3, lane 1 and lane 2 are intersecting road conditions, and a second vehicle 302 is about to travel from lane 1 to lane 2 in conjunction with the road conditions. During the period when the second vehicle 302 is going from lane 1 to lane 2, the second vehicle 302 may perform a series of preliminary actions such as decelerating and turning on the steering lamp. Further, the first vehicle 301 traveling on the lane 2 can determine the predicted travel corridor information of the second vehicle 302 based on the own travel characteristic information and the travel characteristic information of the second vehicle 302. For example, the first vehicle 301 may input its own driving characteristic information and driving characteristic information of the second vehicle 302 into the trained first prediction network to obtain predicted driving corridor information of the second vehicle. The first prediction network may be a convolutional neural network (Convolutional Neural Networks, CNN), a cyclic neural network (Recurrent Neural Network, RNN), or may be another deep learning network, a machine learning network, or the like.

In a specific embodiment, during the running process of the first vehicle, a plurality of vehicles are on the running road, the first vehicle does not need to determine the predicted running corridor information of all the vehicles, only needs to determine the second vehicle related to the running intention of the first vehicle, further determines the predicted running corridor information of the second vehicle, and the number of the second vehicles may be a plurality. Therefore, the first vehicle may determine the second vehicle from the plurality of vehicles on the driving road according to the driving characteristic information of the first vehicle, for example, the first vehicle determines the second vehicle located within a preset distance of the driving position according to the driving position of the first vehicle, and further determines the predicted driving corridor information of the second vehicle according to the driving characteristic information of the second vehicle, for example, the turn signal information, the speed information and the like of the second vehicle.

S203, inputting the driving characteristic information of the first vehicle, the driving characteristic information of the second vehicle, the driving environment characteristic information, and the predicted driving corridor information of the second vehicle into the generation countermeasure network, and determining the predicted driving corridor information of the first vehicle according to the output of the generation countermeasure network, wherein the predicted driving corridor information of the first vehicle is used for indicating the predicted driving area of the first vehicle.

In the present embodiment, after the predicted travel corridor information of the second vehicle is determined, the first vehicle may input its own travel characteristic information, the travel characteristic information of the second vehicle, the travel environment characteristic information, and the predicted travel corridor information of the second vehicle into the generated countermeasure network, and determine the predicted travel corridor information of the first vehicle for instructing the predicted travel area of the first vehicle based on the output of the generated countermeasure network.

Fig. 4 is a schematic diagram of predicted driving corridor information of the first vehicle, and after determining predicted driving corridor information of the second vehicle on the basis of fig. 3, please continue to refer to fig. 4, the predicted driving corridor information of the second vehicle indicates that the second vehicle 402 is about to go from lane 1 to lane 2 in a future period of time. The predicted driving corridor information of the first vehicle, which is determined by the first vehicle 401 according to the output of the generated countermeasure network, is shown in a black area of fig. 4, that is, the first vehicle 401 may change lanes from lane 2 to lane 3 in a future period of time, so that the path planning of the first vehicle 401 is completed, so as to avoid the second vehicle 402 from colliding and interfering with the first vehicle 401 during the lane change.

Wherein generating the countermeasure network includes a generator and a arbiter. The generator sequentially comprises an input layer, a first hidden layer, a second hidden layer, a first full-connection layer, a second full-connection layer and an output layer; the discriminator also comprises an input layer, a first hidden layer, a second hidden layer, a first full-connection layer, a second full-connection layer and an output layer in sequence.

The training process for generating the countermeasure network may be performed on a server or other computer device, for example, the server trains the generation of the countermeasure network, and in the process for generating the countermeasure network training, the server obtains a plurality of travel characteristic information samples of the historical first vehicle, travel characteristic information samples of the historical second vehicle, travel environment characteristic information samples of the historical second vehicle, and predicted travel corridor information samples of the historical second vehicle. The server inputs the travel characteristic information sample of the first vehicle, the travel characteristic information sample of the second vehicle, the travel environment characteristic information sample of the second vehicle, and the predicted travel corridor information sample of the second vehicle to the generation countermeasure network to be trained, predicts the generated countermeasure network, and outputs the predicted travel corridor information of the first vehicle.

Further, the generator inputs the predicted travel corridor information of the first vehicle to the discriminator, the discriminator discriminates the predicted travel corridor information of the first vehicle and the corresponding actual corridor information of the first vehicle, and when the discriminator confirms that the corresponding actual corridor information of the first vehicle is true from the predicted travel corridor information of the first vehicle and the corresponding actual corridor information of the first vehicle, the server continues to optimize the optimization parameters of the generator. And stopping training until the discriminator cannot discriminate true or false from the predicted running corridor information of the first vehicle and the corresponding actual corridor information of the first vehicle, and obtaining the final-use generated countermeasure network.

Further, the first vehicle may input the driving characteristic information of the first vehicle, the driving characteristic information of the second vehicle, the driving environment characteristic information, and the predicted driving corridor information of the second vehicle into the trained generated countermeasure network, and then the generator in the generated countermeasure network may output the predicted driving corridor information of the first vehicle.

The first vehicle may directly use the output of the generated countermeasure network as the predicted travel path information of the first vehicle, or may use the output of the generated countermeasure network as the predicted travel path information of the first vehicle after post-processing such as smoothing and denoising.

In the path planning method, the travel characteristic information of the first vehicle, the travel characteristic information of the second vehicle related to the travel intention of the first vehicle, and the travel environment characteristic information of the first vehicle are acquired, and further, the predicted travel corridor information of the second vehicle for indicating the predicted travel area of the second vehicle is determined based on the travel characteristic information of the first vehicle and the travel characteristic information of the second vehicle, so that the travel characteristic information of the first vehicle, the travel characteristic information of the second vehicle, the travel environment characteristic information, and the predicted travel corridor information of the second vehicle are input into the generation countermeasure network, and the predicted travel corridor information of the first vehicle for indicating the predicted travel area of the first vehicle is determined based on the output of the generation countermeasure network. Since the predicted travel path information of the second vehicle is determined based on the travel characteristic information of the first vehicle and the travel characteristic information of the second vehicle, the predicted travel path information of the second vehicle is more accurate travel path information in consideration of the travel conditions of the first vehicle and the second vehicle. Further, on the basis of the driving characteristic information of the first vehicle, the driving characteristic information of the second vehicle, the driving environment characteristic information and the predicted driving corridor information of the second vehicle, the predicted driving corridor information of the first vehicle determined by the countermeasure network is generated more accurately, the problem that in the conventional technology, only the driving environment information is acquired, and the accuracy of a lane corridor of the vehicle driving caused by planning the lane corridor of the vehicle driving according to the driving environment information is lower is solved, and the accuracy of the planned lane corridor of the vehicle driving is improved.

Fig. 5 is a schematic flow chart of determining the driving intention information of the first vehicle according to an embodiment of the present application, and referring to fig. 5, this embodiment relates to an alternative implementation of how to determine the driving intention information of the first vehicle. On the basis of the above embodiment, the path planning method further includes the following steps:

s501, determining travel intention information of the first vehicle.

In this embodiment, in order to better perform path planning, the first vehicle needs to determine own travel intention information during traveling. The travel intention information is used to indicate a travel intention of the first vehicle, the travel intention including at least one of lane change, acceleration, deceleration, jam, and emergency braking. The first vehicle may determine its own travel intention information through its own sensor, for example, a visual sensor or an inertial sensor, and may also receive the travel intention information of the first vehicle transmitted from the server.

S502, determining a region of interest from the road according to the driving intention information of the first vehicle, and taking the vehicle in the region of interest as a second vehicle.

In the present embodiment, the first vehicle determines a region of interest from the road based on own travel intention information, and the vehicle in the region of interest is taken as the second vehicle. For example, when the first vehicle accelerates in the lane 1, the vehicle in front of the first vehicle on the lane 1 may affect the path planning of the first vehicle, and the first vehicle may take the area within 500m before the first vehicle on the lane 1 is located at the moment as the area of interest, and take the vehicles a to D in the interest as the second vehicle.

According to the method and the device for determining the driving intention information of the first vehicle, the region of interest is determined from the road according to the driving intention information of the first vehicle, and the vehicle in the region of interest is used as the second vehicle, so that the calculation range of the second vehicle is accurate, and the efficiency and the accuracy of determining the predicted driving corridor information of the first vehicle are improved.

Optionally, in S501, determining the driving intention information of the first vehicle may be implemented as follows: and determining the driving intention information of the first vehicle according to the driving characteristic information and the driving environment characteristic information of the first vehicle.

In this embodiment, the first vehicle needs to determine its own travel intention information according to its own travel characteristic information and travel environment characteristic information, for example, the first vehicle determines its own travel intention information according to its own position information, speed information, lane line information, road boundary information, and the like during travel.

Optionally, the means for determining the driving intention information of the first vehicle is: the first vehicle inputs the driving characteristic information and the driving environment characteristic information of the first vehicle to the trained second prediction network so as to obtain the driving intention information of the first vehicle. The second prediction network may be a convolutional neural network (Convolutional Neural Networks, CNN) or a cyclic neural network (Recurrent Neural Network, RNN), or may be another deep learning network, a machine learning network, or the like.

According to the method and the device for determining the driving corridor information of the first vehicle, the driving intention information of the first vehicle is determined according to the driving characteristic information and the driving environment characteristic information of the first vehicle, and the driving intention information of the first vehicle can be determined according to the driving intention information of the first vehicle, so that the second vehicle can be determined according to the driving intention information of the first vehicle, the calculation range of the second vehicle is accurate, and the efficiency and the accuracy of determining the predicted driving corridor information of the first vehicle are improved.

Optionally, in some scenarios, the second vehicle may include a plurality of second vehicles, and the determining the predicted driving corridor information of the second vehicle according to the driving characteristic information of the first vehicle and the driving characteristic information of the second vehicle in S202 may be implemented as follows: for each second vehicle, determining a target vehicle related to the second vehicle according to the driving intention information of the second vehicle, and determining predicted driving corridor information of the second vehicle according to the driving characteristic information of the second vehicle, the driving intention information of the second vehicle and the driving characteristic information of the target vehicle, wherein the target vehicle is the first vehicle or other second vehicles.

In this embodiment, the number of vehicles traveling on the road may be large, and thus the number of second vehicles may be plural. For example, in the case where the number of the second vehicles is plural, assuming that the second vehicles include a vehicle a, a vehicle B, and a vehicle C, the first vehicle may determine a target vehicle related to the vehicle a based on the traveling intention information of the vehicle a, determine a target vehicle related to the vehicle B based on the traveling intention information of the vehicle B, and determine a target vehicle related to the vehicle C based on the traveling intention information of the vehicle C, the target vehicle being the first vehicle or another second vehicle. The driving intention information of the vehicles a, B and C may be obtained by the first vehicle from the server, or may be determined by the first vehicle after obtaining the driving characteristic information of the second vehicle and the driving environment characteristic information according to the sensors of the first vehicle, which is not limited in this embodiment.

Taking a driving scene of a vehicle A, a vehicle B, a vehicle C and a first vehicle in a lane 1 as an example, the vehicle A, the vehicle B and the vehicle C sequentially drive in front of the first vehicle, and when the first vehicle determines that the self-driving intention is to accelerate, the second vehicle comprises the vehicle A, the vehicle B and the vehicle C. When the first vehicle determines that the traveling intention of the vehicle a is lane 2, the vehicle related to the traveling intention of the vehicle a is a vehicle D of lane 2; when the first vehicle determines that the traveling intention of the vehicle B is the deceleration forward, the vehicle related to the traveling intention of the vehicle B is the vehicle C and the first vehicle behind; when the first vehicle determines that the traveling intention of the vehicle C is the acceleration forward traveling, the vehicles related to the traveling intention of the vehicle C are the vehicles a and B in front, that is, the target vehicle may include the vehicle D in addition to the first vehicle and the second vehicle.

Further, the first vehicle can determine predicted travel corridor information of the second vehicle based on the travel intention information of the second vehicle and the travel characteristic information of the target vehicle. That is, the predicted travel corridor information of the vehicles a to C is determined based on the travel characteristic information of the first vehicle, the travel characteristic information of the vehicles a to D, and the travel intention information of the vehicles a to C, respectively.

In a specific embodiment, the first vehicle may input the driving intention information of the second vehicle and the driving characteristic information of the target vehicle into the trained third prediction network to obtain the predicted driving corridor information of the second vehicle.

In this embodiment, for each second vehicle, a target vehicle related to the second vehicle is determined according to the driving intention information of the second vehicle, and predicted driving corridor information of the second vehicle is determined according to the driving characteristic information of the second vehicle, the driving intention information of the second vehicle, and the driving characteristic information of the target vehicle, where the target vehicle is the first vehicle or another second vehicle. Since it is also necessary to determine the target vehicle related to the traveling intention of the second vehicle, the predicted travel corridor information of the second vehicle is further determined based on the traveling characteristic information of the second vehicle, the traveling intention information of the second vehicle, and the traveling characteristic information of the target vehicle. Accordingly, the accuracy of the predicted travel corridor information of the second vehicle is further improved, thereby improving the accuracy of the predicted travel corridor information of the first vehicle, which is obtained based on the predicted travel corridor information of the second vehicle.

Fig. 6 is a schematic flow chart of determining predicted driving corridor information of a second vehicle according to an embodiment of the present application, and referring to fig. 6, this embodiment relates to an alternative implementation of how to determine predicted driving corridor information of a second vehicle. On the basis of the above embodiment, the above method for determining the predicted driving corridor information of the second vehicle according to the driving characteristic information of the second vehicle, the driving intention information of the second vehicle, and the driving characteristic information of the target vehicle includes the steps of:

S601, predicting the interaction position of the second vehicle and the target vehicle according to the driving characteristic information of the second vehicle, the driving characteristic information of the target vehicle and the driving intention information of the second vehicle.

In this embodiment, when the first vehicle determines the travel characteristic information of the second vehicle, the travel characteristic information of the target vehicle, and the travel intention information of the second vehicle, the interaction position of the second vehicle and the target vehicle can be predicted based on the travel characteristic information of the second vehicle, the travel characteristic information of the target vehicle, and the travel intention information of the second vehicle.

Continuing with the above example, with the second vehicle including the vehicle a and the target vehicle including the vehicle D, the traveling of the vehicle a is intended to change to the lane 2, and in the case where the vehicle a changes from the lane 1 to the lane 2, the first vehicle can determine the interaction position of the vehicle a and the vehicle D, for example, the area 1 where the vehicle a and the vehicle D are on the lane 2 may collide, in combination with the traveling characteristic information of the vehicle a and the traveling characteristic information of the vehicle D, for example, the speed information and the position information of the vehicle a and the vehicle D.

S602, determining predicted driving corridor information of the second vehicle according to the prediction result of the interaction position.

In this embodiment, after the interaction position of the second vehicle and the target vehicle is obtained, the first vehicle can determine predicted travel corridor information of the second vehicle according to the prediction result of the interaction position. Continuing the above illustration, if it is predicted that the vehicle a and the vehicle D collide in the area 1 on the lane 2, the driving corridor information of the vehicle a includes the driving area where the vehicle changes from the current position to the lane 2 to the area 1 on the lane 2.

The embodiment predicts the interaction position of the second vehicle and the target vehicle by using the driving characteristic information of the second vehicle, the driving characteristic information of the target vehicle and the driving intention information of the second vehicle, so as to determine the predicted driving corridor information of the second vehicle according to the prediction result of the interaction position. Because the interactive position of the second vehicle and the target vehicle can be predicted, the area needing to be avoided in the running process of the second vehicle can be known in advance, so that the accuracy of the predicted running corridor information of the second vehicle is improved, and the accuracy of the predicted running corridor information of the first vehicle is further improved.

Optionally, in an embodiment, the path planning method further includes: and determining the driving intention information of the second vehicle according to the driving characteristic information and the driving environment characteristic information of the second vehicle.

In the present embodiment, the first vehicle also needs to determine the travel intention information of the second vehicle based on the travel characteristic information of the second vehicle and the travel environment characteristic information of the second vehicle, basically the same principle as described above for determining the travel intention information of the first vehicle. For example, the first vehicle determines the traveling intention information of the second vehicle based on the position information, the speed information, the lane line information, the road boundary information, and the like of the second vehicle during traveling. For example, the first vehicle may also input the driving characteristic information and the driving environment characteristic information of the second vehicle to the trained second prediction network to obtain the driving intention information of the second vehicle.

The present embodiment determines the travel intention information of the second vehicle based on the travel characteristic information of the second vehicle and the travel environment characteristic information. Since the travel intention information of the second vehicle can be determined from the travel characteristic information of the second vehicle and the travel environment characteristic information, the target vehicle related to the travel intention of the second vehicle is determined in conjunction with the travel intention of the second vehicle, thereby improving the accuracy of the predicted travel corridor information of the second vehicle.

Optionally, the driving characteristic information includes at least one of position information, speed information, angular speed information, and acceleration information, and the driving environment characteristic information includes at least one of lane line information, road boundary information, boundary information of a drivable region, road gradient information, and road curvature information.

In the present embodiment, the acquisition of the running characteristic information and the running environment characteristic information depends on the sensor of the first vehicle. For example, the speed information, the angular speed information, the acceleration information, the road gradient information, and the road curvature information may be obtained by a sensor of the first vehicle, such as an inertial sensor. The position information can be obtained by matching the travel characteristic information with a high-precision map. The high-precision map may be a map obtained by the first vehicle from the server, or may be a map stored by the first vehicle itself. The lane line information, the road boundary information, and the boundary information of the drivable area can be obtained by their own sensors, such as visual sensors.

In a specific embodiment, the sensors of the first vehicle include 11 cameras, 5 millimeter wave radars, and 12 ultrasonic radars. The camera is used for detecting continuous images of each time frame in a preset time period, so that a target object is identified from the continuous images, and the distance between the camera and the target object, the speed of the target object and attribute information are determined by combining the millimeter wave radar and the ultrasonic radar, wherein the attribute information is used for identifying specific attributes of the target object. The object may be a second vehicle or may be a marker distinguishing the environment, such as traffic lights, road-side traffic, lane lines, etc. For example, taking the target object as the second vehicle as an example, the attribute information may include a color, a vehicle type, and the like of the second vehicle.

It is understood that when the object is a marker for distinguishing an environment, the first vehicle may determine lane line information, road boundary information, boundary information of a drivable area based on image data collected by the camera and point cloud data collected by the millimeter wave radar.

Further, since the angles and positions of the cameras, the millimeter wave radar and the ultrasonic radar on the first vehicle are different, the first vehicle can respectively perform fusion correlation on detection data obtained by the same camera, the same millimeter wave radar and the same ultrasonic radar, so that accuracy of the obtained driving characteristic information and the obtained driving environment characteristic information is improved. Of course, the first vehicle may also mutually fuse the obtained detection data of the camera, the millimeter wave radar and the ultrasonic radar for the same target object, for example, fuse the data of the second vehicle obtained by the camera with the detection data of the second vehicle obtained by the millimeter wave radar, so as to further improve the accuracy of the obtained driving characteristic information and the driving environment characteristic information.

The implementation routine driving characteristic information comprises at least one of position information, speed information, angular speed information and acceleration information, and the driving environment characteristic information comprises at least one of lane line information, road boundary information, boundary information of a driving area, road gradient information and road curvature information, so that the types of the driving characteristic information and the driving environment characteristic information are enriched, and the accuracy of predicting driving corridor information of the first vehicle is further improved.

Fig. 7 is a schematic overall view of the structure of the first vehicle, and in one specific embodiment, the first vehicle includes a sensor, a domain controller, and a System On Chip (SOC) as shown in fig. 7.

The sensors of the first vehicle may include a vision sensor, a distance sensor, an inertial sensor, and a positioning sensor. For example, the sensor of the first vehicle includes a camera, millimeter wave radar, ultrasonic radar, high-precision positioning sensor. The domain controller of the first vehicle comprises a perception module, a fusion module, an environment understanding module, a scene understanding module, a motion estimation module and a decision module. The SOC includes a prediction module and a planning module.

Specifically, the sensing module acquires detection data of each time frame of the sensor in a preset time period, and obtains speed information, attribute information, distance between the sensor and the target object, and the like. And the fusion module is used for carrying out fusion association on detection data obtained by the sensors of the same class and/or carrying out mutual fusion on data obtained by the detection data obtained by the different classes on the same target object. The prediction module determines predicted driving corridor information of the second vehicle using an output of the fusion module. The environment understanding module determines lane line information, road boundary information and boundary information of a drivable area according to detection data of the sensor, such as image data collected by a camera and point cloud data collected by a millimeter wave radar. The map positioning module is used for determining the running track of the first vehicle by acquiring positioning data of the high-precision positioning sensor and the high-precision map, matching the positioning data with the high-precision map, performing fitting smoothing on boundary lines and a reference line lattice to obtain a smooth reference line for running of the vehicle, and further determining the position information of the first vehicle. The motion estimation module estimates a motion state of the first vehicle through a sensor of the first vehicle and determines position information, speed information, acceleration information, vehicle body angle information, vehicle body angular velocity information, road gradient information, road curvature information, and the like. The scene understanding module is combined with the outputs of the sensing module, the fusion module, the prediction module, the environment understanding module, the map positioning module and the motion estimation module to determine the predicted driving corridor information of the first vehicle. The planning module is used for planning and smoothing the reference line of the lane, outputting a speed lattice and a path lattice meeting the dynamic characteristics of the first vehicle, and finally obtaining fine-grained track information in the corridor of the first vehicle reference drivable space.

Fig. 8 is a schematic diagram of the architecture of the scene understanding module based on fig. 7. As shown in fig. 8, the scene understanding module of the first vehicle includes a generate countermeasure network sub-module and a state machine sub-module. The generation countermeasure network submodule comprises a track feature acquisition unit, a track feature processing unit, a generator unit, a discriminator unit, a scene understanding fusion unit and a scene understanding output unit. The state machine sub-module may control a travel path of the first vehicle over a future time period based on the predicted travel corridor information of the first vehicle that generates the countermeasure network output.

Specifically, the track characteristic acquisition unit acquires track data and lane line data of first vehicles and second vehicles in mass at the cloud end and the vehicle end. The track feature processing unit performs fusion processing on track data and lane line data of the first vehicle and the second vehicle and outputs track features meeting the requirements of vehicle dynamics characteristics and matching requirements of a road model and a vehicle dynamics model. The generator unit and the arbiter unit are used for training the generation of the countermeasure network submodule. And the scene understanding fusion unit fuses the trained generator unit and the trained discriminator unit and is used for real-time scene understanding inference so as to output the predicted driving corridor information of the first vehicle with higher accuracy by the scene understanding output unit.

For a clearer description of the path planning in the present application, referring specifically to fig. 9, fig. 9 is an overall schematic diagram of a path planning method, which is specifically used in the scene understanding module in fig. 7 and 8, and includes the following steps:

s901: and acquiring the driving characteristic information of the first vehicle and the driving environment characteristic information of the first vehicle.

S902: and determining the driving intention information of the first vehicle according to the driving characteristic information and the driving environment characteristic information of the first vehicle.

S903: and determining a region of interest from the road according to the driving intention information of the first vehicle, and taking the vehicle in the region of interest as a second vehicle.

S904: and acquiring the driving characteristic information of the second vehicle and the driving environment characteristic information of the second vehicle.

S905: and determining the driving intention information of the second vehicle according to the driving characteristic information and the driving environment characteristic information of the second vehicle.

S906: for each second vehicle, a target vehicle associated with the second vehicle is determined based on the travel intention information of the second vehicle.

S907: and predicting the interaction position of the second vehicle and the target vehicle according to the driving characteristic information of the second vehicle, the driving characteristic information of the target vehicle and the driving intention information of the second vehicle.

S908: and determining predicted driving corridor information of the second vehicle according to the predicted result of the interaction position.

S909: the driving characteristic information of the first vehicle, the driving characteristic information of the second vehicle, the driving environment characteristic information, and the predicted driving corridor information of the second vehicle are input into the generation countermeasure network.

S9010: the predicted corridor information for the first vehicle is determined based on the output of the generated countermeasure network.

Wherein the driving characteristic information includes at least one of position information, speed information, angular speed information, and acceleration information, and the driving environment characteristic information includes at least one of lane line information, road boundary information, boundary information of a drivable region, road gradient information, and road curvature information.

The working principle of the path planning method provided in this embodiment is please refer to the detailed description in the above embodiment, which is not repeated here.

It should be understood that, although the steps in the flowcharts of fig. 2-9 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2-9 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.

Fig. 10 is a block diagram of a path planning apparatus according to an embodiment of the present application, in one embodiment, as shown in fig. 10, there is provided a path planning apparatus 1000, including: an acquisition module 1001, a first determination module 1002, and a planning module 1003, wherein:

an obtaining module 1001, configured to obtain driving feature information of a first vehicle, driving feature information of a second vehicle, and driving environment feature information of the first vehicle, where the second vehicle is a vehicle related to a driving intention of the first vehicle;

a first determining module 1002, configured to determine predicted driving corridor information of a second vehicle according to driving characteristic information of the first vehicle and driving characteristic information of the second vehicle, where the predicted driving corridor information of the second vehicle is used to indicate a predicted driving area of the second vehicle;

A planning module 1003, configured to input driving characteristic information of the first vehicle, driving characteristic information of the second vehicle, driving environment characteristic information, and predicted driving corridor information of the second vehicle into the generated countermeasure network, and determine predicted driving corridor information of the first vehicle according to an output of the generated countermeasure network, where the predicted driving corridor information of the first vehicle is used to indicate a predicted driving area of the first vehicle.

The path planning device provided by the embodiment of the disclosure acquires the running characteristic information of the first vehicle, the running characteristic information of the second vehicle related to the running intention of the first vehicle and the running environment characteristic information of the first vehicle, further determines the predicted running corridor information of the second vehicle for indicating the predicted running area of the second vehicle according to the running characteristic information of the first vehicle and the running characteristic information of the second vehicle, inputs the running characteristic information of the first vehicle, the running characteristic information of the second vehicle, the running environment characteristic information and the predicted running corridor information of the second vehicle into a generated countermeasure network, and determines the predicted running corridor information of the first vehicle for indicating the predicted running area of the first vehicle according to the output of the generated countermeasure network. Since the predicted travel path information of the second vehicle is determined based on the travel characteristic information of the first vehicle and the travel characteristic information of the second vehicle, the predicted travel path information of the second vehicle is more accurate travel path information in consideration of the travel conditions of the first vehicle and the second vehicle. Further, on the basis of the driving characteristic information of the first vehicle, the driving characteristic information of the second vehicle, the driving environment characteristic information and the predicted driving corridor information of the second vehicle, the predicted driving corridor information of the first vehicle determined by the countermeasure network is generated more accurately, the problem that in the conventional technology, only the driving environment information is acquired, and the accuracy of a lane corridor of the vehicle driving caused by planning the lane corridor of the vehicle driving according to the driving environment information is lower is solved, and the accuracy of the planned lane corridor of the vehicle driving is improved.

Optionally, the path planning apparatus 1000 further includes:

And the second determining module is used for determining the driving intention information of the first vehicle.

And the third determining module is used for determining a region of interest from the road according to the driving intention information of the first vehicle, and taking the vehicle in the region of interest as a second vehicle.

Optionally, the second determining module is specifically configured to determine the driving intention information of the first vehicle according to the driving characteristic information and the driving environment characteristic information of the first vehicle.

Optionally, the second vehicle includes a plurality of vehicles, and the first determining module 1002 includes:

And the determining unit is used for determining a target vehicle related to the second vehicle according to the running intention information of the second vehicle for each second vehicle, and determining the predicted running corridor information of the second vehicle according to the running characteristic information of the second vehicle, the running intention information of the second vehicle and the running characteristic information of the target vehicle, wherein the target vehicle is the first vehicle or other second vehicles.

Optionally, the determining unit includes:

And the prediction subunit is used for predicting the interaction position of the second vehicle and the target vehicle by using the driving characteristic information of the second vehicle, the driving characteristic information of the target vehicle and the driving intention information of the second vehicle.

And the determining subunit is used for determining the predicted driving corridor information of the second vehicle according to the prediction result of the interaction position.

Optionally, the path planning apparatus 1000 further includes:

and the fourth determining module is used for determining the driving intention information of the second vehicle according to the driving characteristic information and the driving environment characteristic information of the second vehicle.

For specific limitations of the path planning apparatus, reference may be made to the above limitations of the path planning method, and no further description is given here. The various modules in the path planning apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the vehicle, or may be stored in software in a memory in the vehicle, so that the processor may invoke and execute operations corresponding to the above modules.

Fig. 11 is an internal structural view of a vehicle in an embodiment of the application. The vehicle 1100 may be a first vehicle or a second vehicle, which may be a car, commercial vehicle, passenger car, bus, truck, motorcycle, or the like.

Referring to fig. 11, a vehicle 1100 may include one or more of the following components: a processing component 1102, a memory 1104, a power component 1106, a multimedia component 1108, an audio component 1110, an input/output (I/O) interface 1112, a sensor component 1114, and a communication component 1116. Wherein the memory has stored thereon a computer program or instructions that run on the processor.

The processing component 1102 generally controls overall operation of the vehicle 1100, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 1102 may include one or more processors 1120 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 1102 can include one or more modules that facilitate interactions between the processing component 1102 and other components. For example, the processing component 1102 may include a multimedia module to facilitate interaction between the multimedia component 1108 and the processing component 1102.

The memory 1104 is configured to store various types of data to support operation at the vehicle 1100. Examples of such data include instructions for any application or method operating on the vehicle 1100, contact data, phonebook data, messages, pictures, videos, and the like. The memory 1104 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply assembly 1106 provides power to the various components of the vehicle 1100. The power components 1106 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the vehicle 1100.

The multimedia component 1108 includes a touch-sensitive display screen between the vehicle 1100 and the user that provides an output interface. In some embodiments, the touch display screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, multimedia component 1108 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the vehicle 1100 is in an operational mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 1110 is configured to output and/or input an audio signal. For example, the audio component 1110 includes a Microphone (MIC) configured to receive external audio signals when the vehicle 1100 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 1104 or transmitted via the communication component 1116. In some embodiments, the audio component 1110 further comprises a speaker for outputting audio signals.

The I/O interface 1112 provides an interface between the processing component 1102 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 1114 includes one or more sensors for providing status assessment of various aspects of the vehicle 1100. For example, the sensor assembly 1114 may detect an on/off state of the vehicle 1100, a relative positioning of the components, such as a display and keypad of the vehicle 1100, a change in position of the vehicle 1100 or a component of the vehicle 1100, the presence or absence of a user's contact with the vehicle 1100, an orientation or acceleration/deceleration of the vehicle 1100, and a change in temperature of the vehicle 1100. The sensor assembly 1114 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 1114 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1114 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 1116 is configured to facilitate communication between the vehicle 1100 and other devices, either wired or wireless. The vehicle 1100 may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication component 1116 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 1116 further includes a Near Field Communication (NFC) module to facilitate short range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the vehicle 1100 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for performing the path planning methods described above.

In an exemplary embodiment, a non-transitory storage medium is also provided, such as a memory 1104 including instructions executable by the processor 1120 of the vehicle 1100 to perform the above-described method. For example, the non-transitory 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 storage medium is also provided that includes instructions, such as memory 1122 including instructions, that are executable by a processor of server 1200 to perform the above-described method. The storage medium may be a non-transitory storage medium, which may be, for example, ROM, random-access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

In an exemplary embodiment, a computer program product is also provided, which, when being executed by a processor, may implement the above-mentioned method. The computer program product includes one or more computer instructions. When loaded and executed on a computer, these computer instructions may implement some or all of the methods described above, in whole or in part, in accordance with the processes or functions described in embodiments of the present disclosure.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided by the present disclosure may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples merely represent a few implementations of the disclosed examples, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made to the disclosed embodiments without departing from the spirit of the disclosed embodiments. Accordingly, the protection scope of the disclosed embodiment patent should be subject to the appended claims.

Claims

1. A method of path planning, the method comprising:

2. The method according to claim 1, wherein the method further comprises:

determining travel intention information of the first vehicle;

And determining a region of interest from a road according to the driving intention information of the first vehicle, and taking the vehicle in the region of interest as the second vehicle.

3. The method according to claim 2, wherein the determining the travel intention information of the first vehicle includes:

And determining the driving intention information of the first vehicle according to the driving characteristic information of the first vehicle and the driving environment characteristic information.

4. The method of claim 1, wherein the second vehicle includes a plurality of vehicles, and wherein determining predicted corridor information for the second vehicle based on the travel characteristic information for the first vehicle and the travel characteristic information for the second vehicle includes:

For each second vehicle, determining a target vehicle related to the second vehicle according to the driving intention information of the second vehicle, and determining predicted driving corridor information of the second vehicle according to the driving characteristic information of the second vehicle, the driving intention information of the second vehicle and the driving characteristic information of the target vehicle, wherein the target vehicle is the first vehicle or other second vehicles.

5. The method according to claim 4, wherein the determining the predicted travel corridor information of the second vehicle based on the travel characteristic information of the second vehicle and the travel characteristic information of the target vehicle includes:

Predicting the interaction position of the second vehicle and the target vehicle according to the driving characteristic information of the second vehicle, the driving characteristic information of the target vehicle and the driving intention information of the second vehicle;

and determining the predicted driving corridor information of the second vehicle according to the predicted result of the interaction position.

6. The method according to claim 4, wherein the method further comprises:

and determining the driving intention information of the second vehicle according to the driving characteristic information of the second vehicle and the driving environment characteristic information.

7. The method according to any one of claims 1 to 6, wherein the travel characteristic information includes at least one of position information, speed information, angular speed information, and acceleration information, and the travel environment characteristic information includes at least one of lane line information, road boundary information, boundary information of a drivable area, road gradient information, and road curvature information.

8. A path planning apparatus, the apparatus comprising:

9. A vehicle comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when the computer program is executed.

10. A storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method of any of claims 1 to 7.

11. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1-7.