An unmanned path planning method and system

Abstract

The present disclosure is about a method, system, electronic device and storage medium for unmanned driving path planning. The method includes: generating a global path of the vehicle based on an offline planner according to the location information of the vehicle's starting point, end point and task point; generating a first path file based on a file generator after processing the global path of the vehicle for path smoothness; performing environmental detection based on a perception function module to generate environmental information, and generating a local path based on an online planner; generating a second path file after processing the local path of the vehicle for path smoothness; and a decision control module controlling the vehicle's driving based on the first path file or the second path file to complete the path planning of unmanned driving. The present disclosure improves the system operation efficiency by deploying common modules with small differences on the cloud and the vehicle at the same time, and performing more resource-consuming long-distance path planning operations on the cloud with stronger computing power.

Description

Background Art

[0002] The adoption of autonomous driving technology helps reduce the cost and improve the productivity of transportation systems. Under the management of a central control server, an unmanned transportation system can enable unmanned trucks used for transportation and loading / unloading to operate safely and continuously when equipped with a vehicle control system, a GNSS navigation and positioning system, and sensing sensors. A basic unmanned transportation system includes unmanned trucks for performing transportation tasks, a central control system for task management, and a wireless communication network for ensuring communication between the trucks and the central control system. In addition, auxiliary machines are also essential components of the system. Taking the intelligent mine, a typical unmanned transportation system, as an example, the loading operation requires the cooperation of an excavator.

[0003] In an unmanned transportation system, there have been many discussions on how to balance the system complexity at the vehicle end and the server end. The centralized deployment scheme simplifies the vehicle-end functions by performing as many necessary calculations as possible on the central control system, thereby improving the execution efficiency of the vehicle. Through the specific control instructions issued by the central control system, the vehicle end only needs to perform a small amount of instruction conversion and execute operations, reducing the requirements for in-vehicle equipment and making the actions of each vehicle controllable. However, such an operating mode highly depends on communication performance. In the case of weak communication signals, the operation of the system will be affected. The decentralized deployment scheme focuses on enhancing the single-vehicle intelligence of each vehicle, and the central control system only focuses on completing task allocation before the start of transportation work. Such an operating mode provides as much freedom as possible for each vehicle, but has extremely high requirements for the computing efficiency and functional perfection of the single-vehicle terminal. If the vehicle terminal functions are not perfect or the computing efficiency is low, it will lead to the system being unable to operate safely and efficiently.

[0004] Although an existing SysML-based unmanned vehicle simulation method proposes an unmanned vehicle modeling model based on systems engineering, this model only targets the vehicle-end system and is mainly used for experimental simulation, and is not applicable to decentralized system analysis; the multi-platform collaborative path planning system with task timeliness proposes a decentralized system for different platforms, but does not provide a clear architecture for specific application scenarios. At the same time, the computing complexities of the second platform and the first platform are different. The first platform only serves as task allocation and does not fully utilize the computing power of its centralized platform.

[0005] Therefore, one or more methods are needed to solve the above problems.

[0006] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] The purpose of the present disclosure is to provide an unmanned path planning method, system, electronic device, and computer-readable storage medium, thereby at least to some extent overcoming one or more problems caused by the limitations and defects of related technologies.

[0008] According to one aspect of the present disclosure, there is provided an unmanned path planning method, including:

[0009] Based on the position information of the vehicle's starting point, ending point, and mission points, an offline planner deployed on the cloud control scheduling system side of the path planning module generates a global path of the vehicle;

[0010] After the global path of the vehicle is processed for path smoothness based on a smoother deployed on the cloud control scheduling system side of the path planning module, a first path file is generated based on a file generator deployed on the cloud control scheduling system side of the path planning module, and the first path file is sent to the in-vehicle system side;

[0011] The in-vehicle system side receives the first path file, performs environmental detection based on a perception function module deployed on the in-vehicle system side to generate environmental information, and an online planner deployed on the in-vehicle system side of the path planning module generates a local path according to the first path file and the environmental information;

[0012] After the local path of the vehicle is processed for path smoothness based on a smoother deployed on the in-vehicle system side of the path planning module, a second path file is generated based on a file generator deployed on the in-vehicle system side of the path planning module;

[0013] A decision control module deployed on the in-vehicle system side controls the vehicle's driving based on the first path file or the second path file to complete the unmanned path planning.

[0014] In an exemplary embodiment of the present disclosure, the method further includes:

[0015] After generating the first path file based on a file generator deployed on the cloud control scheduling system side of the path planning module, the first path file is stored on the cloud control scheduling system side;

[0016] After generating the second path file based on a file generator deployed on the in-vehicle system side of the path planning module and completing the vehicle driving control based on the second path file, the second path file is deleted.

[0017] In an exemplary embodiment of the present disclosure, the method further includes:

[0018] The global path of the vehicle is processed for path smoothness based on a smoother deployed on the cloud control scheduling system side of the path planning module according to the curvature change rate and sampling resolution of the global path;

[0019] The local path of the vehicle is subjected to path smoothness processing based on the curvature change rate and sampling resolution of the local path by a smoother deployed on the vehicle-mounted system side of the path planning module.

[0020] In an exemplary embodiment of the present disclosure, the first path file / second path file in the method further includes:

[0021] A path description file, which contains vehicle segmented path information;

[0022] A task description file, which contains vehicle gear information.

[0023] In an exemplary embodiment of the present disclosure, the method further includes:

[0024] Based on the position information of the access point and exit point of the vehicle loading task area, environmental detection is performed based on a perception function module deployed on the vehicle-mounted system side to generate environmental information, and an online planner deployed on the vehicle-mounted system side of the path planning module generates a local path according to the first path file and the environmental information.

[0025] In an exemplary embodiment of the present disclosure, the method further includes:

[0026] Environmental detection is performed based on a perception function module deployed on the vehicle-mounted system side to generate environmental information, the terrain information and obstacle information in the environmental information are parsed, an online planner deployed on the vehicle-mounted system side of the path planning module generates an obstacle avoidance path according to the terrain information and obstacle information, and a local path is generated based on the obstacle avoidance path and the first path file.

[0027] In an exemplary embodiment of the present disclosure, the method further includes:

[0028] After the local path of the vehicle is subjected to path smoothness processing by a smoother deployed on the vehicle-mounted system side of the path planning module, a file generator deployed on the vehicle-mounted system side of the path planning module generates a second path file according to the locally path after smoothness processing and the first path file.

[0029] In an exemplary embodiment of the present disclosure, the method further includes:

[0030] The vehicle-mounted system side receives the first path file and performs environmental detection based on a perception function module deployed on the vehicle-mounted system side to generate environmental information;

[0031] If the environmental information includes obstacle information, after the local path of the vehicle is processed for path smoothness by the smoother deployed on the vehicle-mounted system side of the path planning module, a second path file is generated by the file generator deployed on the vehicle-mounted system side of the path planning module; the decision control module deployed on the vehicle-mounted system side controls the vehicle driving based on the second path file to complete the path planning for driverless driving;

[0032] If the environmental information does not include obstacle information, the decision control module deployed on the vehicle-mounted system side controls the vehicle driving based on the first path file to complete the path planning for driverless driving.

[0033] In one aspect of the present disclosure, a path planning system for driverless driving is provided, including a system layer, an analysis layer, a design layer, and an implementation layer, wherein:

[0034] The system layer includes a vehicle, a wireless communication network, an auxiliary machine, and a central control server, and the vehicle includes a vehicle-mounted control system, a positioning system, and a sensor;

[0035] The analysis layer includes server requirements, perception requirements, planning requirements, and control requirements. The perception requirements include a perception function module on the vehicle-mounted system side, the control system includes a decision control module on the vehicle-mounted system side, the planning requirements include a path planning module, and the path planning module includes an offline planner, a smoother, and a file generator deployed on the cloud control scheduling system side, and an online planner, a smoother, and a file generator deployed on the vehicle-mounted system side;

[0036] The design layer is used to generate a modular path planning;

[0037] The implementation layer is used to generate a path package block diagram and a path planning process flow chart based on the modular path planning.

[0038] In one aspect of the present disclosure, an electronic device is provided, including:

[0039] a processor; and

[0040] a memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the method according to any one of the above is implemented.

[0041] In one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of the above is implemented.

[0042] A path planning method for driverless in an exemplary embodiment of the present disclosure, wherein the method includes: generating a global path of the vehicle based on an offline planner according to the position information of the vehicle's starting point, ending point, and task points; after performing path smoothness processing on the global path of the vehicle, generating a first path file based on a file generator; performing environment detection based on a perception function module to generate environment information, and generating a local path based on an online planner; after performing path smoothness processing on the local path of the vehicle, generating a second path file; and a decision control module controlling the vehicle driving based on the second path file to complete the path planning for driverless. By deploying general modules with relatively small differences on both the cloud side and the vehicle side simultaneously, and performing long-distance path planning operations that consume more resources on the cloud side with stronger computing power, the operation efficiency of the system is improved.

[0043] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] By referring to the accompanying drawings to describe its exemplary embodiments in detail, the above and other features and advantages of the present disclosure will become more obvious.

[0045] Figure 1 FIG. shows a flowchart of a path planning method for driverless according to an exemplary embodiment of the present disclosure;

[0046] Figure 2 FIG. shows a schematic block diagram of a path planning system for driverless according to an exemplary embodiment of the present disclosure;

[0047] Figure 3 FIG. shows a logic diagram of a path planning method for driverless according to an exemplary embodiment of the present disclosure;

[0048] Figure 4 FIG. shows a model diagram of a path planning system for driverless according to an exemplary embodiment of the present disclosure;

[0049] Figure 5 FIG. schematically shows a block diagram of an electronic device according to an exemplary embodiment of the present disclosure; and

[0050] Figure 6 FIG. schematically shows a schematic diagram of a computer-readable storage medium according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. Like reference numerals in the figures denote like or similar parts, and thus their repetitive description will be omitted.

[0052] In addition, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present disclosure. However, those skilled in the art will realize that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, materials, systems, steps, etc. may be employed. In other cases, well-known structures, methods, systems, implementations, materials, or operations are not shown or described in detail to avoid obscuring aspects of the present disclosure.

[0053] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or in one or more software-hardened modules, or in different networks and / or processor systems and / or microcontroller systems.

[0054] In the present example embodiment, first, a path planning method for driverless is provided; as shown in Figure 1 , the path planning method for driverless may include the following steps:

[0055] Step S110, based on the position information of the vehicle starting point, ending point, and task point, generate the global path of the vehicle by an offline planner deployed on the cloud control scheduling system side of the path planning module;

[0056] Step S120, after performing path smoothness processing on the global path of the vehicle by a smoother deployed on the cloud control scheduling system side of the path planning module, generate a first path file by a file generator deployed on the cloud control scheduling system side of the path planning module, and send the first path file to the vehicle-mounted system side;

[0057] Step S130, the vehicle-mounted system side receives the first path file, performs environment detection based on a perception function module deployed on the vehicle-mounted system side to generate environment information, and generate a local path based on an online planner deployed on the vehicle-mounted system side of the path planning module according to the first path file and the environment information;

[0058] Step S140: After performing path smoothness processing on the local path of the vehicle based on the smoother deployed on the vehicle-mounted system side of the path planning module, generate a second path file based on the file generator deployed on the vehicle-mounted system side of the path planning module;

[0059] Step S150: The decision control module deployed on the vehicle-mounted system side controls the vehicle's driving based on the first path file or the second path file to complete the path planning for driverless driving.

[0060] A path planning method for driverless driving in an exemplary embodiment of the present disclosure, wherein the method includes: generating a global path of the vehicle based on an offline planner according to the position information of the vehicle's starting point, ending point, and task points; performing path smoothness processing on the global path of the vehicle and generating a first path file based on a file generator; performing environment detection based on a perception function module to generate environment information and generating a local path based on an online planner; performing path smoothness processing on the local path of the vehicle to generate a second path file; and the decision control module controlling the vehicle's driving based on the second path file to complete the path planning for driverless driving. The present disclosure improves the system operation efficiency by simultaneously deploying general modules with small differences on both the cloud side and the vehicle side, and performing long-distance path planning operations that consume more resources on the cloud side with stronger computing power.

[0061] Next, a path planning method for driverless driving in this exemplary embodiment will be further described.

[0062] In this exemplary embodiment, to implement the automated transportation and loading / unloading processes in a semi-structured scenario, the driverless truck needs to automatically drive on the transportation roads between loading / unloading areas and the internal roads of the loading / unloading areas. This driving process can be summarized as a path-tracking process. The trajectory used in the path-tracking process consists of a curved path (route) connecting the starting position and the ending position, and the time-series information (speed, acceleration) of each sampling point on the curved path. Therefore, to enable the driverless truck to automatically drive from the starting position to the target position to complete the loading / unloading task and detect and avoid various obstacles during driving to ensure safety, the path planning module needs to calculate, based on the regional map, a collision-free path that conforms to the vehicle kinematic performance (especially the minimum turning radius) for the vehicle to track. Since the transportation application scenario has a large load and the flatness of the terrain cannot be guaranteed, to reduce vehicle wear, the path needs to have better smoothness and a better density of path sampling points. For the path packet file generated from the path to describe the trajectory, when the path planning module performs speed allocation, it needs to consider the reasonable allocation of the speed on the curve to avoid cornering at too high a speed. At the same time, during the path packaging process, the forward driving part needs to be separated from the reverse driving part to facilitate the gear shifting of the vehicle. In particular, for the obstacle avoidance and detour working condition, when the vehicle identifies an obstacle not marked on the map, the path planning module needs to provide a corresponding detour path and modify the original path packet file to ensure the completion of the transportation and loading / unloading tasks.

[0063] In step S110, based on the position information of the vehicle's starting point, ending point, and task point, a global path of the vehicle can be generated by the offline planner deployed on the cloud control and scheduling system side of the path planning module.

[0064] In step S120, after the global path of the vehicle is processed for path smoothness by the smoother deployed on the cloud control and scheduling system side of the path planning module, a first path file can be generated by the file generator deployed on the cloud control and scheduling system side of the path planning module, and the first path file can be sent to the in-vehicle system side.

[0065] In the embodiment of this example, the cloud side and the vehicle side use exactly the same smoother to improve the smoothness and resolution of the path. The improvement of smoothness can reduce the curvature change rate of the path, make the change in the driving direction of the vehicle smoother and more uniform, and reduce tire wear; the improvement of resolution can make the path-tracking sampling points denser and make the actual path-tracking path closer to the planned path. Additionally, for the upsampling of the path, that is, the improvement of resolution, it also enables the planner to generate paths at larger path point intervals, reducing the number of calculations and improving the calculation speed.

[0066] In the embodiment of this example, the file generator is responsible for generating a path package file actually used for vehicle path tracking according to the planned path processed by the smoother, for the decision control module to read. The path package file contains several path files and a path interpretation file (specifically referring to forward driving or reverse driving in this case) for explaining the use of each path file, that is, the task description file. During the path package generation process, the file generator assigns driving speeds according to the curvatures of each path sampling point to improve the steering stability of the vehicle. At the same time, the file generator segments the planned path according to forward driving, reverse driving, and the set maximum segment length, which is convenient for vehicle gear shifting and avoids excessive occupation of the in-vehicle control terminal's operating memory by a single path file. There are slight differences between the file generators on the cloud side and the vehicle side. Compared with the file generator on the cloud side, due to the existence of obstacle avoidance conditions, the file generator on the vehicle side requires additional path package reading and modification functions. After the file generator on the vehicle side reads and locates the currently used path segment under obstacle avoidance conditions, it only modifies the necessary path segments to avoid unnecessary repeated calculations.

[0067] In step S130, the vehicle-mounted system can receive the first path file, perform environmental detection based on the perception function module deployed on the vehicle-mounted system to generate environmental information, and the online planner deployed on the vehicle-mounted system of the path planning module generates a local path according to the first path file and the environmental information.

[0068] In the embodiment of this example, different from the decision control module and the perception function module only deployed on the vehicle-mounted system, to ensure the efficient and stable operation of the unmanned transportation system, the path planning module will be divided into two parts and deployed on the cloud control scheduling system side (cloud side) and the vehicle-mounted system side (vehicle side) respectively. Each independent part of the path planning module can be further divided into three sub-modules, namely, the planner, the smoother, and the file generator.

[0069] The offline planner deployed on the cloud side can make full use of the high-performance server on the cloud to calculate the long-distance global path; the online planner deployed on the vehicle side processes the short-distance local path through direct linkage with the decision control module and the perception function module.

[0070] The global path responsible for by the offline planner specifically refers to the path from the starting point of the vehicle through the transportation roads in each loading and unloading section to the access point of the designated loading and unloading area for the task. This section of the journey has the characteristics of long transportation distance, relatively obvious structured features (still belonging to unstructured roads), and few redundant obstacles. Therefore, after the path package is calculated in the cloud, it is sent to the vehicle end together with the task file through the mobile network, which can reduce the computational workload and save computational time during the operation of the vehicle end system. When special scenarios occur during the vehicle's driving, the online planner is called through the decision control module for offline planning at the vehicle end. Additionally, due to the relatively fixed driving route of the transportation section and the absence of redundant obstacles during path generation, the calculated path package file can be stored in the cloud with relatively abundant disk space for repeated use.

[0071] In step S140, the local path of the vehicle can be subjected to path smoothness processing based on the smoother deployed on the vehicle-mounted system side of the path planning module, and then a second path file can be generated based on the file generator deployed on the vehicle-mounted system side of the path planning module.

[0072] In the embodiment of this example, the method further includes:

[0073] The global path of the vehicle is subjected to path smoothness processing based on the smoother deployed on the cloud control scheduling system side of the path planning module according to the curvature change rate and sampling resolution of the global path;

[0074] The local path of the vehicle is subjected to path smoothness processing based on the smoother deployed on the vehicle-mounted system side of the path planning module according to the curvature change rate and sampling resolution of the local path.

[0075] In the embodiment of this example, the method further includes:

[0076] After generating the first path file based on the file generator deployed on the cloud control scheduling system side of the path planning module, the first path file is stored on the cloud control scheduling system side;

[0077] After generating the second path file based on the file generator deployed on the vehicle-mounted system side of the path planning module and completing the vehicle driving control based on the second path file, the second path file is deleted.

[0078] In the embodiment of this example, the first path file / second path file in the method further includes:

[0079] A path description file, which contains the vehicle's segmented path information;

[0080] A task description file, which contains the vehicle gear information.

[0081] In the embodiment of this example, the method further includes:

[0082] Based on the position information of the access point and the exit point of the vehicle loading task area, environmental detection is performed based on the perception function module deployed on the vehicle-mounted system side to generate environmental information. Based on the online planner deployed on the vehicle-mounted system side of the path planning module, a local path is generated according to the first path file and the environmental information.

[0083] In the embodiment of this example, the method further includes:

[0084] Based on the perception function module deployed on the vehicle-mounted system side, environmental detection is performed to generate environmental information, the terrain information and obstacle information in the environmental information are parsed, and based on the online planner deployed on the vehicle-mounted system side of the path planning module, an obstacle avoidance path is generated according to the terrain information and the obstacle information, and a local path is generated based on the obstacle avoidance path and the first path file.

[0085] In the embodiment of this example, the method further includes:

[0086] After the local path of the vehicle is processed for path smoothness based on the smoother deployed on the vehicle-mounted system side of the path planning module, based on the file generator deployed on the vehicle-mounted system side of the path planning module, a second path file is generated according to the locally path after the smoothness processing and the first path file.

[0087] In the embodiment of this example, the local paths responsible for by the online planner include but are not limited to the following two situations here: First, the path planning in the loading and unloading area, specifically referring to the two sections of paths from the designated access point of the loading and unloading area to the designated loading and unloading task point, and then from the task point to the designated exit point of the loading and unloading area. The driving distance of this section of the journey is short, but there are many terrain variables and obstacles generated by the loading and unloading tasks. At the same time, the loading and unloading tasks are also involved in the linkage with the vehicle decision control module. Second, the obstacle avoidance path planning in any area, specifically referring to the path from the stopping point after encountering an obstacle to bypass the obstacle and then return to the reusable part of the original path or directly drive to the designated target point. The driving distance of this section of the journey is short in most cases, and it involves the obstacle detection of the perception function module and the linkage with the vehicle decision control module. It can be seen that both of the above two working conditions have the characteristics of short distance, many variables, and the need to be linked with other modules. Therefore, directly performing online planning at the vehicle end to generate a new path package or modify the original path package can reduce the redundant interaction between the vehicle end and the cloud end to improve its efficiency and stability. Additionally, due to the many variables in these two sections of the road, various external factors are considered when generating the path, and the path reusability is poor, that is, it is used and discarded immediately.

[0088] In step S150, the decision control module that can be deployed on the vehicle system side controls the vehicle driving based on the first path file or the second path file, and completes the path planning for driverless driving.

[0089] In the embodiment of this example, the present disclosure provides a complete four-layer system modeling method. Through the SysML system modeling language, requirements analysis, structural analysis, and activity description are carried out on the path planning system for semi-structured scenarios, and a path planning system software architecture and deployment method that meet the requirements analysis are formed during the modeling process. The present disclosure weighs the advantages and disadvantages of balancing centralized and decentralized systems, maximizes the execution efficiency of the vehicle side while retaining the ability of the vehicle side to handle special road sections and special situations, and takes into account the compatibility, stability, and efficiency of the system.

[0090] In the embodiment of this example, the method further includes:

[0091] The vehicle system side receives the first path file, and performs environmental detection based on the perception function module deployed on the vehicle system side to generate environmental information;

[0092] If the environmental information contains obstacle information, after the local path of the vehicle is processed for path smoothness by the smoother deployed on the vehicle system side of the path planning module, a second path file is generated based on the file generator deployed on the vehicle system side of the path planning module; the decision control module deployed on the vehicle system side controls the vehicle driving based on the second path file, and completes the path planning for driverless driving;

[0093] If the environmental information does not contain obstacle information, the decision control module deployed on the vehicle system side controls the vehicle driving based on the first path file, and completes the path planning for driverless driving.

[0094] In the embodiment of this example, as Figure 3As shown, the decision control module based on the in-vehicle system terminal can implement vehicle driving control based on the first path file or the second path file. When the in-vehicle system terminal does not detect obstacle information, it directly controls the vehicle driving according to the first path file. When the in-vehicle system terminal detects obstacle information, the in-vehicle system terminal can generate a second path file for locally modifying the path based on the first path file. The decision control module of the in-vehicle system terminal can implement the local detour path calculation and execution for obstacle recognition of the vehicle based on the second path file. It should be noted that although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that these steps must be executed in this specific order, or that all the steps shown must be executed to achieve the desired result. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution, etc.

[0095] In addition, in the embodiment of this example, a path planning system for driverless is also provided. Referring to Figure 2 As shown, the path planning system 200 for driverless can include: a system layer 210, an analysis layer 220, a design layer 230, and an implementation layer 240. Among them:

[0096] The system layer 210 includes a vehicle, a wireless communication network, auxiliary machines, and a central control server. The vehicle includes an in-vehicle control system, a positioning system, and sensors.

[0097] In the embodiment of this example, the system layer 210 defines the system composition and top-level requirements of the unmanned transportation system. According to its background, the system consists of driverless trucks, a wireless communication network, auxiliary machines, and a central control server. One or more operators can interact with the entire system through the central control server to assign transportation tasks to the trucks. With the help of its control system, positioning system, and sensors, the trucks can complete tasks autonomously, safely, and efficiently. Therefore, the top-level requirements can be summarized as autonomous transportation, driving safety, and operation efficiency.

[0098] The analysis layer 220 includes server requirements, perception requirements, planning requirements, and control requirements. The perception requirements include a perception function module at the in-vehicle system terminal. The control system includes a decision control module at the in-vehicle system terminal. The planning requirements include a path planning module. The path planning module includes an offline planner, a smoother, and a file generator deployed at the cloud control scheduling system terminal, and an online planner, a smoother, and a file generator deployed at the in-vehicle system terminal.

[0099] In the embodiments of this example, the analysis layer 220 derives system-level requirements into sub-requirements, including server requirements, perception requirements, planning requirements, and control requirements. Among them, the control requirements and perception requirements correspond to the decision control module and the perception function module on the vehicle-mounted system side respectively. The decision control module is responsible for executing the tracking task according to the path package file and the task file, while the perception function module is responsible for detecting obstacles and sending the obstacle information to other modules for use in obstacle avoidance parking and obstacle bypass driving. Since this invention focuses on the path planning system, only the planning requirements are provided here.

[0100] The design layer 230 is used to generate modular path planning.

[0101] The implementation layer 240 is used to generate a path package block diagram and a path planning process flow diagram based on the modular path planning.

[0102] In the embodiments of this example, as Figure 4 shown, it is a model diagram of the path planning system for the four-layer unmanned driving. The cloud side and the vehicle-mounted side of the system layer 210 respectively generate a first path file and a second path file through the requirement analysis of the analysis layer 220 and the offline planning module and the online planning module of the design layer 230, for the vehicle-mounted side of the implementation layer 240 to perform instruction implementation and complete system configuration.

[0103] In the embodiments of this example, the hierarchical requirements and conceptual design of the path planning system are described in detail through a four-layer system architecture and the SysML system modeling language. The overall design is sorted out through requirement diagrams, block diagrams, sequence diagrams, and activity diagrams, so that the designs of the three modules of the planner, smoother, and file generator of the path planning system match the design requirements of the unmanned transportation system, and have wide scenario adaptability and customizability. This solution deploys the path planning module to both the central control server and the vehicle control system at the same time, weighs the characteristics of the centralized and decentralized systems, makes full use of the computing efficiency of the central server, and improves the security, stability, and efficiency of the entire system.

[0104] It should be noted that although several modules or units of a path planning system 200 for unmanned driving are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0105] In addition, in the exemplary embodiments of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0106] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, method, or program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuit", "module", or "system" here.

[0107] Reference is now made to Figure 5 to describe the electronic device 500 according to such an embodiment of the present invention. Figure 5 The electronic device 500 shown is merely an example and should not impose any limitation on the functions and scope of use of the embodiments of the present invention.

[0108] As Figure 5 shown, the electronic device 500 is presented in the form of a general-purpose computing device. The components of the electronic device 500 may include, but are not limited to: at least one of the above-mentioned processing units 510, at least one of the above-mentioned storage units 520, a bus 530 connecting different system components (including the storage unit 520 and the processing unit 510), and a display unit 540.

[0109] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 510, so that the processing unit 510 executes the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of this specification. For example, the processing unit 510 can execute steps S110 to S130 as shown in Figure 1 .

[0110] The storage unit 520 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 5201 and / or a cache storage unit 5202, and may further include a read-only storage unit (ROM) 5203.

[0111] The storage unit 520 may further include a program / utility 5204 having a set (at least one) of program modules 5203. Such program modules 5205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0112] The bus 550 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0113] The electronic device 500 can also communicate with one or more external devices 570 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can also communicate with one or more devices that enable a user to interact with the electronic device 500, and / or communicate with any device that enables the electronic device 500 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 550. Moreover, the electronic device 500 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 560. As shown in the figure, the network adapter 560 communicates with other modules of the electronic device 500 through the bus 550. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0114] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or can be implemented by the way of software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0115] In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium, on which there is a program product capable of implementing the above method of this specification. In some possible embodiments, various aspects of the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of this specification.

[0116] Reference Figure 6 As shown, a program product 600 for implementing the above method according to an embodiment of the present invention is described. It can adopt a portable compact disc read-only memory (CD-ROM) and include program code, and can run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.

[0117] The program product may employ any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0118] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than a readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0119] The program code contained on the readable medium may be transmitted with any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0120] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0121] In addition, the above drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present invention, and are not for limiting purposes. It is easy to understand that the processes shown in the above drawings do not indicate or limit the chronological order of these processes. Additionally, it is also easy to understand that these processes may be executed, for example, synchronously or asynchronously in multiple modules.

[0122] Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include known common general knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and examples are only to be considered as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

[0123] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims

1. An unmanned path planning method, characterized in that, the method includes: Based on the position information of the vehicle's starting point, ending point, and task points, an offline planner deployed on the cloud control scheduling system side of the path planning module generates the global path of the vehicle; After the global path of the vehicle is processed for path smoothness by a smoother deployed on the cloud control scheduling system side of the path planning module, a first path file is generated by a file generator deployed on the cloud control scheduling system side of the path planning module, and the first path file is sent to the in-vehicle system side; The in-vehicle system side receives the first path file, and based on the perception function module deployed on the in-vehicle system side, conducts environmental detection to generate environmental information. An online planner deployed on the in-vehicle system side of the path planning module generates a local path according to the first path file and the environmental information; After the local path of the vehicle is processed for path smoothness by a smoother deployed on the in-vehicle system side of the path planning module, a second path file is generated by a file generator deployed on the in-vehicle system side of the path planning module according to the locally path after smoothness processing and the first path file; The decision control module deployed on the in-vehicle system side controls the vehicle's driving based on the first path file or the second path file to complete the path planning of unmanned driving; The method further includes: The global path of the vehicle is processed for path smoothness by a smoother deployed on the cloud control scheduling system side of the path planning module according to the curvature change rate and sampling resolution of the global path; The local path of the vehicle is processed for path smoothness by a smoother deployed on the in-vehicle system side of the path planning module according to the curvature change rate and sampling resolution of the local path; Wherein, the cloud side and the vehicle side use exactly the same smoother to improve the smoothness and resolution of the path.

2. The method according to claim 1, characterized in that, the method further includes: After a first path file is generated by a file generator deployed on the cloud control scheduling system side of the path planning module, the first path file is stored on the cloud control scheduling system side; After a second path file is generated by a file generator deployed on the in-vehicle system side of the path planning module and the vehicle driving control is completed based on the second path file, the second path file is deleted.

3. The method according to claim 1, characterized in that, The first path file / second path file in the method further includes: A path description file, which contains the vehicle's segmented path information; A task description file, which contains the vehicle's gear information.

4. The method according to claim 1, characterized in that, the method further includes: Based on the position information of the vehicle's loading task area access point and departure point, environmental detection is conducted based on the perception function module deployed on the in-vehicle system side to generate environmental information. An online planner deployed on the in-vehicle system side of the path planning module generates a local path according to the first path file and the environmental information.

5. The method according to claim 1, characterized in that, the method further includes: Based on the perception function module deployed on the vehicle system side, environmental detection is performed to generate environmental information. The terrain information and obstacle information in the environmental information are parsed. The online planner deployed on the vehicle system side of the path planning module generates an obstacle avoidance path based on the terrain information and obstacle information. A local path is generated based on the obstacle avoidance path and the first path file.

6. The method according to claim 1, wherein, the method further includes: The vehicle system side receives the first path file and performs environmental detection based on the perception function module deployed on the vehicle system side to generate environmental information; If the environmental information contains obstacle information, after the local path of the vehicle is processed for path smoothness by the smoother deployed on the vehicle system side of the path planning module, a second path file is generated by the file generator deployed on the vehicle system side of the path planning module; The decision control module deployed on the vehicle system side controls the vehicle driving based on the second path file to complete the path planning for driverless driving; If the environmental information does not contain obstacle information, the decision control module deployed on the vehicle system side controls the vehicle driving based on the first path file to complete the path planning for driverless driving.

7. An electronic device, wherein, it includes a processor; and a memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is implemented.

8. A computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images