Path determination method, system and equipment and storage medium

Abstract

The invention provides a path determination method, and belongs to the technical field of path planning, and the path determination method comprises the steps: obtaining at least two candidate paths; path evaluation information of each candidate path is determined, the path evaluation information comprises at least one of collision probability, smoothness and dynamics feasibility, the collision probability represents the feasibility of collision between the candidate path and an obstacle, the smoothness represents the smoothness of the candidate path, and the dynamics feasibility represents the feasibility of collision between the candidate path and the obstacle. The dynamics feasibility represents the degree that the candidate path meets the dynamics of the target object; and determining the candidate path of which the path evaluation information meets a preset condition from the at least two candidate paths as a target path. According to the embodiment of the invention, the path most suitable for the movement of the target object can be effectively determined, so that the accurate control of the movement of the target object is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of path determination, in particular to a path determination method, system, device and storage medium. BACKGROUND

[0002] With the acceleration of global technological revolution, the importance of automatic driving technology for vehicle driving is increasingly prominent. In the process of vehicle driving, the automatic driving system can be guided by the driving target, and the precise control of vehicle driving can be realized through a safe, compliant and efficient driving path. However, there are many methods for generating driving paths in the prior art, each with advantages and disadvantages. How to select the optimal driving path and then realize the precise control of vehicle driving is a technical problem to be solved. SUMMARY

[0003] The present application aims to solve at least one of the technical problems existing in the prior art, and proposes a path determination method, system, device and storage medium.

[0004] In a first aspect, an embodiment of the present application provides a path determination method, which comprises:

[0005] obtaining at least two candidate paths;

[0006] determining path evaluation information of each candidate path, the path evaluation information comprising at least one of collision probability, smoothness and dynamics feasibility, wherein the collision probability represents the feasibility of collision between the candidate path and an obstacle, the smoothness represents the smoothness of the candidate path, and the dynamics feasibility represents the degree to which the candidate path meets the dynamics of a target object;

[0007] determining a candidate path whose path evaluation information meets a preset condition from the at least two candidate paths as a target path.

[0008] In a second aspect, an embodiment of the present application provides a path determination system, which comprises:

[0009] an obtaining module configured to obtain at least two candidate paths;

[0010] a determining module configured to determine path evaluation information of each candidate path, the path evaluation information comprising at least one of collision probability, smoothness and dynamics feasibility, wherein the collision probability represents the feasibility of collision between the candidate path and an obstacle, the smoothness represents the smoothness of the candidate path, and the dynamics feasibility represents the degree to which the candidate path meets the dynamics of a target object;

[0011] The determining module is further configured to determine, from the at least two candidate paths, a candidate path whose path evaluation information meets a preset condition as a target path

[0012] In a third aspect, an electronic device is provided, and the electronic device includes one or more processors; a memory configured to store one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the path determination method according to the first aspect.

[0013] In a fourth aspect, a computer storage medium is provided, and the computer storage medium stores a computer program, and when the computer program is executed by a processor, the path determination method according to the first aspect is implemented.

[0014] The path determination method provided by the present application can obtain at least two candidate paths, determine path evaluation information of each candidate path, and then determine, from the at least two candidate paths, a candidate path whose path evaluation information meets a preset condition as a target path for moving a target object. Since the path evaluation information can include at least one of a collision probability, a smoothness, and a dynamic feasibility, the optimal candidate path can be selected from the at least two candidate paths for moving the target object from the aspects of the collision probability, the smoothness, and the dynamic feasibility, so that the accurate control of the movement of the target object can be achieved. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is one of flow diagrams of a path determination method provided by an embodiment of the present application;

[0016] Figure 2 is another one of flow diagrams of a path determination method provided by an embodiment of the present application;

[0017] Figure 3 is still another one of flow diagrams of a path determination method provided by an embodiment of the present application;

[0018] Figure 4 is a structural block diagram of a path determination system provided by an embodiment of the present application;

[0019] Figure 5 is a structural block diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0020] For a better understanding of the technical solutions of the present application, the exemplary embodiments of the present application are described below in conjunction with the drawings, which include various details of the embodiments of the present application to help understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Also, for the sake of clarity and conciseness, the description below omits the description of well-known functions and structures.

[0021] In the case of no conflict, each embodiment of the present application and each feature in the embodiments can be combined with each other.

[0022] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0023] The terms used herein are only used to describe specific embodiments, and are not intended to limit the present application. As used herein, the singular forms "a" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the terms "comprise" and / or "consist of", when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. The terms "connected" or "coupled" and / or similar terms are not limited to a physical or mechanical connection, but can include an electrical connection, whether direct or indirect.

[0024] Unless otherwise defined, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in a generally used dictionary should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present application, and should not be interpreted in an idealized or overly formal sense, unless expressly so defined herein.

[0025] In the technical solutions of the present application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solutions comply with relevant laws and regulations, and do not violate public order and good customs. The use of user data in the technical solutions complies with relevant national laws and regulations (for example, "Information Security Technology Personal Information Security Specification" and the like). For example: appropriate measures are taken for personal information access control; restrictions are given to the display of personal information; the use purpose of personal information does not exceed the direct or reasonably related range; the identity of the personal information is eliminated when it is used, avoiding precise positioning to a specific individual.

[0026] To solve at least one of the problems in the background art, the present application provides a path determination method. The path determination method provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0027] Figure 1 A flowchart of one of the path determination methods provided by the embodiments of the present application.

[0028] As Figure 1 shown, the execution subject of the method can be a path determination system, based on which the method can specifically include the following steps:

[0029] Step 110, obtaining at least two candidate paths.

[0030] The candidate paths can be trajectories for the movement of a target object, which can be a vehicle, a robot or any object capable of automatic driving or movement, without specific limitation.

[0031] Step 120, determining path evaluation information of each candidate path.

[0032] In some embodiments, the path evaluation information can include at least one of a collision probability, a smoothness and a dynamics feasibility. The collision probability can represent the possibility of collision between the candidate path and an obstacle, the smoothness can represent the smoothness of the candidate path, and the dynamics feasibility can represent the degree to which the candidate path meets the dynamics of the target object.

[0033] Step 130, determining a candidate path whose path evaluation information meets a preset condition from the at least two candidate paths as a target path.

[0034] The preset condition can be set in advance based on actual experience or situation, for example, if the path evaluation information includes a collision probability, the corresponding preset condition can be set as the collision probability being less than a preset probability threshold, without specific limitation.

[0035] Specifically, the path determination system can obtain at least two candidate paths and determine the path evaluation information of each candidate path, and then can screen a candidate path whose path evaluation information meets a preset condition from the at least two candidate paths as a target path for the movement of the candidate target object.

[0036] In the path determination method provided by the present application, at least two candidate paths are obtained, and path evaluation information of each candidate path is determined, and then a candidate path whose path evaluation information meets a preset condition is determined as a target path for the target object to move. Since the path evaluation information can include at least one of collision probability, smoothness and dynamic feasibility, the optimal candidate path can be selected from the at least two candidate paths for the target object to move in terms of collision probability, smoothness and dynamic feasibility, so that accurate control of the movement of the target object can be achieved.

[0037] In order to accurately obtain at least two candidate paths for selecting the optimal candidate path as the target path for the target object to move, in an embodiment of the present application, the step 110 can specifically include:

[0038] obtaining path planning information;

[0039] processing the path planning information according to at least two preset path planning manners to obtain a candidate path corresponding to each of the preset path planning manners.

[0040] The path planning information can be information used to determine the candidate path, and the preset path planning manner can be a manner for path planning which is set in advance based on actual experience or situation, and is not limited herein. It should be noted that the path planning information required by different preset path planning manners can be different or the same, and is not limited herein.

[0041] Specifically, the path determination system can obtain path planning information, and process the obtained path planning information according to at least two preset path planning manners to obtain a candidate path corresponding to each of the preset path planning manners.

[0042] In this embodiment, the path planning information can be processed by different path planning manners to obtain different candidate paths, so that the optimal candidate path can be selected as the target path for the target object to move based on the information such as collision probability, smoothness and dynamic feasibility, so that accurate control of the movement of the target object can be achieved, and the safety of the movement of the target object is ensured.

[0043] Based on this, in order to be able to describe the path determination method provided by the embodiments of the present application in detail, in an embodiment of the present application, the at least two candidate paths can include a first candidate path and a second candidate path, so that the at least two preset path planning manners can include two preset path planning manners, and the path planning information required by different path planning manners can be different or the same, and the path planning information can include first planning information and second planning information, which can be the same or different. Based on this, the step of processing the path planning information according to the at least two preset path planning manners to obtain the candidate path corresponding to each preset path planning manner can specifically include the following steps:

[0044] processing the first planning information by using a path planning model to obtain the first candidate path;

[0045] processing the second planning information based on a preset path planning rule to obtain the second candidate path.

[0046] In some embodiments, the first planning information can include sensor data, which can be related data collected by a sensor deployed on a target object, where the sensor can be a camera, a laser radar, etc., and correspondingly, the sensor data can be image data, point cloud data, etc., which are not limited here. In addition, the first planning information can also include the location information of the destination, which is not limited here.

[0047] In addition, the preset path planning rule can be set in advance based on actual experience or situation, which is not limited here. The second planning information can include environment perception information, map information, and positioning information. It should be noted that the environment perception information can be determined based on the sensor data by using the path planning model, which is not limited here.

[0048] Specifically, in the case where the obtained at least two candidate paths include a first candidate path and a second candidate path, the path determination system can process the first planning information by using a path planning model to obtain the first candidate path, and can process the second planning information based on a preset path planning rule to obtain the second candidate path.

[0049] In this embodiment, the first candidate path can be obtained by a model, and the second candidate path can be obtained by a rule, so that the first candidate path and the second candidate path can be comprehensively considered from the aspects of collision probability, smoothness, and dynamic feasibility, etc. in the subsequent stage. In this way, when the model generated path does not meet the vehicle kinematics and dynamics or even causes safety problems, the rule based candidate path can be used for safety protection. Compared with the single modular path planning method (i.e. the second candidate path is obtained by a rule), the path planning ability to deal with complex scenes can be improved. Different candidate paths can be obtained by different path planning methods, so that a better path can be selected in the subsequent stage, and the accuracy of path determination is effectively improved.

[0050] Based on this, in order to describe the path determination method provided by the embodiments of the present application in detail, in an embodiment of the present application, based on this, the step of processing the first planning information by using the path planning model to obtain the first candidate path can specifically include the following steps:

[0051] extracting path planning features from the first planning information by using a first sub-model in the path planning model;

[0052] determining environment perception information based on the path planning features by using a second sub-model in the path planning model;

[0053] determining the first candidate path based on the environment perception information by using a third sub-model in the path planning model.

[0054] The path planning features can be related features used for path planning, which are not limited here. In addition, the environment perception information can be related information of the environment around the candidate path. The environment perception information can include dynamic element information and static element information. The dynamic element information can be a moving pedestrian, vehicle, etc. The static element information can be a lane line, a road edge, and a sidewalk, etc. which are not described in detail here.

[0055] Specifically, the path determination system can extract path planning features from the first planning information by using a first sub-model in the path planning model, determine environment perception information based on the path planning features by using a second sub-model in the path planning model, and then determine the first candidate path based on the environment perception information by using a third sub-model in the path planning model.

[0056] In one example, the first sub-model can include a feature extractor and an encoder. In this way, the path planning features can be extracted from the first planning information by using the feature extractor, and the path planning features can be encoded by using the encoder to obtain the path planning features after encoding.

[0057] The second sub-model can include a vectorized motion transformer and a vectorized Map transformer. In this way, dynamic element information in the scene can be extracted using the vectorized motion transformer to achieve dynamic target detection and vectorized trajectory prediction, and static element information in the scene can be extracted using the vectorized Map transformer.

[0058] The third sub-model can include a Planning transformer. In this way, the dynamic element information and the static element information can be processed using the Planning transformer to extract information related to planning to obtain the first candidate path.

[0059] In this embodiment, the path planning feature can be extracted from the first planning information using the first sub-model in the path planning model, the environment perception information can be determined based on the path planning feature using the second sub-model in the path planning model, and the first candidate path can be determined based on the environment perception information using the third sub-model in the path planning model. In this way, the first candidate path can be accurately obtained by generating a path using a model.

[0060] To be able to describe the path determination method provided by the embodiments of the present application in detail, in an embodiment of the present application, as shown in Figure 2 If the path evaluation information includes dynamic feasibility, the step 120 can specifically include the following steps:

[0061] Step 210, determining the path curvature of each target path point in the plurality of target path points.

[0062] Step 220, determining a first value corresponding to each target path point based on the relative relationship between the path curvature of each target path point and a preset curvature threshold.

[0063] Step 230, determining the sum of the first values corresponding to the plurality of target path points as the dynamic feasibility of the candidate path.

[0064] The candidate path can include a plurality of target path points. It should be noted that the candidate path can include a plurality of path points, and the plurality of path points can include the plurality of target path points. In other words, the plurality of target path points can be determined from the plurality of path points in a preset manner. The preset manner can be set based on actual experience or conditions, for example, the preset manner can be to obtain at a preset interval or continuously, which is not limited herein.

[0065] In addition, the preset curvature threshold can be set in advance based on actual experience or conditions, which is not limited here.

[0066] Specifically, since each candidate path can include a plurality of target path points, the path determination system can first determine the path curvature of each target path point in the plurality of target path points, and then determine the first value corresponding to each target path point based on the relative relationship between the path curvature of each target path point and the preset curvature threshold. In this way, a plurality of first values can be obtained, and the sum of the plurality of first values can be determined as the dynamic feasibility of the candidate path.

[0067] In one example, the step of determining the first value corresponding to each target path point based on the relative relationship between the path curvature of each target path point and the preset curvature threshold satisfies the following formula (1):

[0068] (1)

[0069] wherein, is a preset threshold, is the path curvature corresponding to the i-th target path point.

[0070] In this embodiment, the path curvature of each target path point can be determined, and then the first value corresponding to each target path point can be determined based on the relative relationship between the path curvature of the target path point and the preset curvature threshold, and the dynamic feasibility can be determined based on the first value. In this way, the dynamic feasibility corresponding to the candidate path can be accurately and effectively determined.

[0071] In addition, in the above embodiment, the path evaluation information in the embodiment of the present application can also include collision probability and smoothness. Based on this, the collision probability can be determined based on the distance between the candidate path and the obstacle, and the smoothness can be determined based on the continuous curvature of the candidate path. The specific determination method of the collision probability and the smoothness in the embodiment of the present application is not limited.

[0072] In order to comprehensively and in detail describe the path determination method provided by the embodiment of the present application, in one embodiment of the present application, as shown in Figure 3 Before the step 220, the path determination method provided by the embodiment of the present application can include the following steps:

[0073] Step 310, determining the object turning information required when the target object moves according to the candidate path and the target road surface adhesion information corresponding to the candidate path.

[0074] The object turning information can be information related to the direction of the target object during movement. If the target object is a vehicle, the object turning information can be a vehicle turning angle. The target road adhesion information can be information related to the adhesion of the path on which the candidate path is located, which is not specifically limited herein.

[0075] At step 320, the object turning information is matched based on a preset correspondence between turning information and path curvature, to determine a first curvature corresponding to the object turning information.

[0076] The preset correspondence between turning information and path curvature can be set in advance based on actual experience or conditions, which is not specifically limited herein.

[0077] At step 330, the target road adhesion information is matched based on a preset correspondence between road adhesion information and path curvature, to determine a second curvature corresponding to the target road adhesion information.

[0078] The preset correspondence between road adhesion information and path curvature can be set in advance based on actual experience or conditions, which is not specifically limited herein.

[0079] At step 340, the preset curvature threshold is determined based on the first curvature and the second curvature.

[0080] Specifically, the road determination system can first determine the object turning information required when the target object moves along the candidate path and the target road adhesion information corresponding to the candidate path, match the object turning information based on a preset correspondence between turning information and path curvature, to determine a first curvature corresponding to the object turning information, match the target road adhesion information based on a preset correspondence between road adhesion information and path curvature, to determine a second curvature corresponding to the target road adhesion information, and finally determine a preset curvature threshold based on the first curvature and the second curvature.

[0081] It should be noted that in the process of determining the preset curvature threshold based on the first curvature and the second curvature, the minimum curvature can be selected from the first curvature and the second curvature as the preset curvature threshold, or the preset curvature threshold can be determined based on the average of the first curvature and the second curvature, which is not specifically limited herein.

[0082] In one example, taking a vehicle as the target object, considering that the maximum turning angle of the turning system of the vehicle is limited due to the mechanical structure, the maximum turning angle of the vehicle is considered as the preset curvature threshold. However, for a given driving path, it is not possible to directly determine whether the path is feasible by the steering angle, therefore, the embodiment of the application converts the constraint of the vehicle steering angle into the limit of the path curvature by the vehicle kinematics formula, and the conversion formula (corresponding to the above-mentioned preset correspondence between the steering information and the path curvature) is as follows:

[0083] (2).

[0084] wherein, represents the curvature, R is the vehicle turning radius, and L is the vehicle wheelbase.

[0085] On the other hand, considering the influence of the road adhesion coefficient , the absolute value of the lateral acceleration of the vehicle driving is usually in , and exceeding this lateral acceleration range is not dynamically feasible, so the limit of the curvature can be shown in the following formula (3):

[0086] (3)

[0087] wherein, is the lateral acceleration limit, is the vehicle longitudinal speed.

[0088] Based on this, it should be noted that the preset correspondence between the road adhesion information and the path curvature can include the correspondence between the road adhesion information and the object lateral acceleration, and the correspondence between the object lateral acceleration and the path curvature.

[0089] In this way, the preset curvature threshold .

[0090] In this embodiment, the preset curvature threshold can be accurately determined by considering the influence of the object steering information required when the target object moves along the candidate path and the target road adhesion information corresponding to the candidate path on the path curvature, so that the dynamic feasibility can be accurately determined subsequently.

[0091] In an embodiment of the application, the above-mentioned path evaluation information includes at least one evaluation element, which can include at least one of the collision probability smoothness and the dynamic feasibility; based on this, the above-mentioned step 130 can specifically include the following steps:

[0092] For each of the at least two candidate paths, the at least one evaluation element corresponding to the candidate path is weighted and summed based on a preset weight to obtain a path evaluation value of the candidate path;

[0093] The candidate path with the maximum path evaluation value is determined from the at least two candidate paths as the target path.

[0094] The preset weight can be set based on actual experience or situation, and is not specifically limited here.

[0095] Specifically, the path determination system can perform weighted summation processing on the at least one evaluation element corresponding to each candidate path in the at least two candidate paths based on a preset weight, to obtain a path evaluation value of the candidate path, and then determine the candidate path with the maximum path evaluation value from the at least two candidate paths as the target path.

[0096] In this embodiment, by performing weighted summation processing on the at least one evaluation element corresponding to each candidate path based on a preset weight, to obtain a path evaluation value of the candidate path, and then determining the candidate path with the maximum path evaluation value from the at least two candidate paths as the target path. In this way, the optimal candidate path can be accurately and effectively determined from the at least two candidate paths, the accuracy of path determination is improved, and the precise control of the movement of the target object is realized.

[0097] Based on the same inventive concept, the embodiments of the present application provide a path determination system, which can be specifically combined with Figure 4 The path determination system provided by the embodiments of the present application is described in detail.

[0098] As Figure 4 The path determination system 400 can include:

[0099] The acquisition module 410 is configured to acquire at least two candidate paths.

[0100] The determination module 420 is configured to determine path evaluation information of each candidate path, the path evaluation information including at least one of a collision probability, a smoothness, and a dynamics feasibility, wherein the collision probability represents the feasibility of collision between the candidate path and an obstacle, the smoothness represents the smoothness of the candidate path, and the dynamics feasibility represents the degree to which the candidate path meets the dynamics of a target object.

[0101] The determination module 420 is further configured to determine, from the at least two candidate paths, a candidate path with path evaluation information satisfying a preset condition as the target path.

[0102] In one embodiment of the present application, the path determination system provided by the embodiments of the present application can include:

[0103] The acquisition module is specifically configured to acquire path planning information.

[0104] The processing module is configured to process the path planning information according to at least two preset path planning manners, to obtain a candidate path corresponding to each of the preset path planning manners.

[0105] In an embodiment of the present application, the at least two candidate paths include a first candidate path and a second candidate path, and the path planning information includes first planning information and second planning information. Based on this, the processing module is specifically configured to:

[0106] process the first planning information by using a path planning model to obtain the first candidate path, wherein the first planning information includes sensor data;

[0107] process the second planning information by using a preset path planning rule to obtain the second candidate path, wherein the second planning information includes environmental perception information, map information, and positioning information.

[0108] In an embodiment of the present application, the path determination system provided by the embodiment of the present application can include:

[0109] The feature extraction module is configured to extract path planning features from the first planning information by using a first sub-model in the path planning model.

[0110] The determination module is further configured to determine environmental perception information based on the path planning features by using a second sub-model in the path planning model.

[0111] The determination module is further configured to determine the first candidate path based on the environmental perception information by using a third sub-model in the path planning model.

[0112] In an embodiment of the present application, the path evaluation information includes kinetic feasibility, and the candidate path includes a plurality of target path points. Based on this, the determination module is specifically configured to:

[0113] determine a path curvature of each target path point in the plurality of target path points;

[0114] determine a first value corresponding to each target path point based on a relative relationship between the path curvature of each target path point and a preset curvature threshold;

[0115] determine a sum of the first values corresponding to the plurality of target path points as the kinetic feasibility of the candidate path.

[0116] In an embodiment of the present application, the path determination system provided by the embodiment of the present application can include:

[0117] The determining module is further configured to determine object turning information required when the target object moves along the candidate path and target road adhesion information corresponding to the candidate path.

[0118] The matching module is configured to match the object turning information based on a preset correspondence between turning information and path curvature, and determine a first curvature corresponding to the object turning information.

[0119] The matching module is further configured to match the target road adhesion information based on a preset correspondence between road adhesion information and path curvature, and determine a second curvature corresponding to the target road adhesion information.

[0120] The determining module is further configured to determine the preset curvature threshold based on the first curvature and the second curvature.

[0121] In an embodiment of the present application, the path evaluation information includes at least one evaluation element, and the at least one evaluation element includes at least one of the collision probability, the smoothness and the dynamic feasibility. Based on this, the path determination system provided by the embodiment of the present application can include:

[0122] The weighted sum module is configured to, for each of the at least two candidate paths, perform weighted sum processing on the at least one evaluation element corresponding to the candidate path based on a preset weight, to obtain a path evaluation value of the candidate path.

[0123] The determining module is specifically configured to determine, from the at least two candidate paths, a candidate path with the maximum path evaluation value as the target path.

[0124] In the path determination method provided by the present application, at least two candidate paths are obtained, and path evaluation information of each candidate path is determined, and then a candidate path with path evaluation information meeting a preset condition is determined from the at least two candidate paths as a target path for the target object to move. Since the path evaluation information can include at least one of the collision probability, the smoothness and the dynamic feasibility, the optimal candidate path can be selected from the at least two candidate paths for the target object to move from the aspects of the collision probability, the smoothness and the dynamic feasibility, so that the precise control of the movement of the target object can be realized.

[0125] The various modules in the path determination system provided by the embodiment of the present application can implement the method steps of the embodiments of any one of Figures 1 to 3 described above, and can achieve the corresponding technical effects, and for brevity, will not be described here.

[0126] Based on the same inventive concept, the embodiment of the present application further provides an electronic device. Figure 5A structural block diagram of an electronic device is provided in an embodiment of the present application. As shown in Figure 5 The electronic device provided in the embodiment of the present application includes one or more processors 501, a memory 502, and one or more I / O interfaces 503. The memory 502 stores one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the path determination method in any of the above embodiments. The one or more I / O interfaces 503 are connected between the processor and the memory, and are configured to implement information interaction between the processor and the memory.

[0127] The processor 501 is a device with data processing capability, including but not limited to a central processing unit (CPU) and the like. The memory 502 is a device with data storage capability, including but not limited to a random access memory (RAM, more specifically, SDRAM, DDR, etc.), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), and a flash memory (FLASH). The I / O interface (read-write interface) 503 is connected between the processor 501 and the memory 502, and can implement information interaction between the processor 501 and the memory 502, including but not limited to a data bus (Bus) and the like.

[0128] In some embodiments, the processor 501, the memory 502, and the I / O interface 503 are connected to each other and to other components of the computing device through a bus 504.

[0129] In some embodiments, the one or more processors 501 include a field programmable gate array.

[0130] The embodiment of the present application also provides a computer readable medium. The computer readable medium stores a computer program, and when the program is executed by a processor, the steps in the path determination method in any of the above embodiments are implemented. The computer readable storage medium can be a volatile or non-volatile computer readable storage medium.

[0131] The embodiment of the present application also provides a computer program product, including computer readable code or a non-volatile computer readable storage medium carrying computer readable code. When the computer readable code is run in a processor of an electronic device, the processor in the electronic device executes the path determination method.

[0132] Those skilled in the art can understand that all or some of the steps in the methods disclosed above and the functional modules / units in the systems and devices can be implemented by software, firmware, hardware, or a combination thereof. In hardware implementation, the division between the functional modules / units referred to in the above description does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be performed by several physical components in cooperation. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on computer-readable storage media, which can include computer storage media (or non-transitory media) and communication media (or transitory media).

[0133] As is well known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable program instructions, data structures, program modules or other data. Computer storage media include, but are not limited to, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM), static random access memory (SRAM), flash memory or other memory technology, portable compact disc read only memory (CD-ROM), digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer. Further, it is well known to those skilled in the art that communication media typically embodies computer readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. As a result, the desired information can be downloaded to a computer or external storage device via computer readable storage media or communication media from a network, such as the Internet, a local area network, a wide area network, and / or a wireless network.

[0134] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device from a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0135] Computer readable program instructions for carrying out operations of the present application can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate array (FPGA), or programmable logic array (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present application.

[0136] The computer program product described herein can be embodied in a specific manner by hardware, software, or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), and the like.

[0137] The computer program product described herein can be embodied in a specific manner by hardware, software, or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium. In another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK), and the like.

[0138] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium that can be a computer- readable storage medium having no data storage cycles that change state. The instructions can be executed by one or more processors of a computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process such that the instructions which execute via the one or more processors of the computer or other programmable data processing devices create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0139] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0140] The flow and block diagrams in the drawings show the architectural, functional, and operational views of possible implementations of systems, methods, and computer program products according to the present application. In this regard, each block in the flow and block diagrams can represent a module, a segment, or a portion of instructions which contain one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0141] Example embodiments have been disclosed and, although a specific terminology is employed, it is merely for the convenience of the reader and is not intended to be limiting. In some instances, specific details have been included for the purpose of providing a thorough understanding of the embodiments presented, but it will be apparent to those skilled in the art that embodiments of the application can be practiced without these specific details. In some instances, features, characteristics and / or elements described in connection with a particular embodiment can be used in conjunction with, or switched to, features, characteristics and / or elements described in connection with other embodiments, unless otherwise explicitly stated. Accordingly, it will be understood that various changes in form and details can be made without departing from the scope of the present application as set forth in the appended claims.

Claims

1. A path determination method characterized by, The method comprises: obtaining at least two candidate paths; determining path evaluation information of each of the candidate paths, the path evaluation information comprising at least one of a collision probability, a smoothness and a dynamic feasibility, wherein the collision probability represents a feasibility of collision between the candidate path and an obstacle, the smoothness represents a smoothness degree of the candidate path, and the dynamic feasibility represents a degree of satisfaction of the candidate path to dynamics of a target object; determining, from the at least two candidate paths, a candidate path whose path evaluation information satisfies a preset condition as a target path.

2. The method of claim 1, wherein, The obtaining of the at least two candidate paths comprises: obtaining path planning information; processing the path planning information according to at least two preset path planning manners to obtain a candidate path corresponding to each of the preset path planning manners.

3. The method according to claim 1 or 2, characterized in that, The at least two candidate paths comprise a first candidate path and a second candidate path, and the path planning information comprises first planning information and second planning information. The processing of the path planning information according to at least two preset path planning manners to obtain a candidate path corresponding to each of the preset path planning manners comprises: processing the first planning information by using a path planning model to obtain the first candidate path, the first planning information comprising sensor data; processing the second planning information based on a preset path planning rule to obtain the second candidate path, the second planning information comprising environmental perception information, map information and positioning information.

4. The method of claim 3, wherein, The processing of the first planning information by using the path planning model to obtain the first candidate path comprises: extracting path planning features from the first planning information by using a first sub-model in the path planning model; determining environmental perception information based on the path planning features by using a second sub-model in the path planning model; determining the first candidate path based on the environmental perception information by using a third sub-model in the path planning model.

5. The method of claim 1, wherein, The path evaluation information comprises dynamic feasibility, and the candidate path comprises a plurality of target path points. The determination of the path evaluation information of each of the candidate paths comprises: determining a path curvature of each target path point in the plurality of target path points; determining a first value corresponding to each target path point based on a relative relationship between the path curvature of each target path point and a preset curvature threshold; determining a sum of the first values corresponding to the plurality of target path points as the dynamic feasibility of the candidate path.

6. The method of claim 5, wherein, Before the determination of the first value corresponding to each target path point based on the relative relationship between the path curvature of each target path point and the preset curvature threshold, the method further comprises: determining object turning information required when a target object moves along the candidate path and target road adhesion information corresponding to the candidate path; matching the object turning information based on a preset correspondence between turning information and path curvature to determine a first curvature corresponding to the object turning information. match the target road adhesion information based on a preset correspondence relationship between road adhesion information and path curvature, to determine a second curvature corresponding to the target road adhesion information; determine the preset curvature threshold based on the first curvature and the second curvature.

7. The method of claim 1, wherein, The path evaluation information includes at least one evaluation element, and the at least one evaluation element includes at least one of the collision probability, the smoothness, and the dynamics feasibility; The method further includes: For each of the at least two candidate paths, performing weighted summation processing on at least one evaluation element corresponding to the candidate path based on a preset weight, to obtain a path evaluation value of the candidate path. The candidate path with the maximum path evaluation value is determined as the target path.

8. A route determination system characterized by, The method further includes: an acquisition module configured to acquire at least two candidate paths; a determination module configured to determine path evaluation information of each of the candidate paths, the path evaluation information including at least one of a collision probability, a smoothness, and a dynamics feasibility, wherein the collision probability represents the feasibility of collision between the candidate path and an obstacle, the smoothness represents the smoothness of the candidate path, and the dynamics feasibility represents the degree to which the candidate path meets the dynamics of a target object; The determination module is further configured to determine, from the at least two candidate paths, a candidate path whose path evaluation information meets a preset condition as the target path.

9. An electronic device, comprising: The method further includes: one or more processors; a memory configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having stored thereon a computer program, characterized in that The computer program, when executed by a processor, implements the steps in the method according to any one of claims 1 to 7.

Images