Edge Sweeping Trajectory Planning Method, Device, Electronic Device, and Storage Medium

Abstract

The present application discloses a method, apparatus, electronic device, and storage medium for planning a side-edge cleaning trajectory. Among them, the method includes generating a global cleaning trajectory based on pre-loaded high-precision map data as the first planning information for an unmanned cleaning vehicle; based on the first planning information of the unmanned cleaning vehicle, planning the side-edge cleaning trajectory of the unmanned cleaning vehicle according to the relevant information of the unmanned cleaning vehicle and the boundary information of the current driving road, where the relevant information includes vehicle-related information, and the boundary information includes the road boundary environment on the current driving road of the vehicle. Through the present application, accurate side-edge cleaning trajectory planning is achieved, improving the cleaning efficiency and safety.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular, to a method and device for planning a side-sweeping trajectory, an electronic device, and a storage medium. Background Art

[0002] With the accelerating progress of urbanization, the workload of cleaning urban public areas is increasing, and as the main force of cleaning, it has become increasingly difficult to recruit cleaning workers. Therefore, the implementation of driverless cleaning vehicles has become an important way considered by all parties to solve this current contradiction.

[0003] In related technologies, the development of driverless cleaning vehicle technology has received increasing attention from all parties. One of the most common and core scenarios in the operation of driverless cleaning vehicles is side-sweeping cleaning. How to ensure that the cleaning vehicle can accurately perform side-sweeping cleaning operations is one of the key factors for the implementation and operation of driverless cleaning vehicles.

[0004] During the operation of a driverless cleaning vehicle, how to ensure the accuracy and safety of side driving is the key to the implementation of the technology. Therefore, how to generate a high-precision and high-safety side-sweeping path is particularly important. In some solutions, a method for planning a repeated cleaning path for the missed cleaning area after cleaning according to a preset route has been studied, but the method for generating the initial preset cleaning path has not been involved. In other solutions, a method for side-sweeping cleaning has been studied. It uses a virtual wall of a high-precision map to judge in real time whether it is in the side-sweeping cleaning area, and at the same time corrects the vehicle driving error through a sensor. However, the defects are that firstly, it needs to update the global path in real time based on high-precision map data, secondly, it is found through actual vehicle tests that the positioning using GPS+IMU is unreliable when driving along the edge, and at the same time, it does not update the road boundary in real time, but only evaluates and corrects the cleaning trajectory after side-sweeping cleaning, which will reduce the cleaning efficiency and cannot adapt to road changes. Summary of the Invention

[0005] Embodiments of the present application provide a method and device for planning a side-sweeping trajectory, an electronic device, and a storage medium, so as to achieve accurate planning of a side-sweeping trajectory, which can be used for a driverless cleaning vehicle.

[0006] Embodiments of the present application adopt the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for planning a side-sweeping trajectory, which is used for an unmanned sweeper. The method includes: generating a global sweeping trajectory as the first planning information for the unmanned sweeper according to pre-loaded high-precision map data; and planning the side-sweeping trajectory of the unmanned sweeper based on the first planning information of the unmanned sweeper, according to the relevant information of the unmanned sweeper and the boundary information of the current driving road, where the relevant information includes vehicle-related information, and the boundary information includes the road boundary environment on the current driving road of the vehicle.

[0008] In a second aspect, an embodiment of the present application further provides a device for planning a side-sweeping trajectory, which is used for an unmanned sweeper. The device includes: a first planning module, configured to generate a global sweeping trajectory as the first planning information for the unmanned sweeper according to pre-loaded high-precision map data; and a side-sweeping trajectory module, configured to plan the side-sweeping trajectory of the unmanned sweeper based on the first planning information of the unmanned sweeper, according to the relevant information of the unmanned sweeper and the boundary information of the current driving road, where the relevant information includes vehicle-related information, and the boundary information includes the road boundary environment on the current driving road of the vehicle.

[0009] In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, where the executable instructions, when executed, cause the processor to execute the method.

[0010] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to execute the method.

[0011] The above at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects:

[0012] The global sweeping trajectory is generated using pre-loaded high-precision map data as the first planning information for the unmanned sweeper, and the side-sweeping trajectory of the unmanned sweeper is planned according to the relevant information of the unmanned sweeper and the boundary information of the current driving road. Thus, an accurate side-sweeping trajectory can be generated in real time, improving the system efficiency while ensuring the accuracy of trajectory generation, and enhancing safety and robustness. Description of the Drawings

[0013] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments and descriptions thereof of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0014] Figure 1 It is a schematic flow chart of a method for planning a side-edge cleaning trajectory in an embodiment of the present application;

[0015] Figure 2 It is a schematic structural diagram of a device for planning a side-edge cleaning trajectory in an embodiment of the present application;

[0016] Figure 3 It is a schematic structural diagram of an electronic device in an embodiment of the present application. Detailed implementation manners

[0017] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part rather than all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application.

[0018] The following will, with reference to the drawings, detail the technical solutions provided by the embodiments of the present application.

[0019] The embodiment of the present application provides a method for planning a side-edge cleaning trajectory. As Figure 1 shown, a schematic flow chart of the method for planning a side-edge cleaning trajectory in the embodiment of the present application is provided. The method at least includes the following steps S110 to S120:

[0020] Step S110, generate a global cleaning trajectory as the first planning information of the driverless cleaning vehicle according to pre-loaded high-precision map data.

[0021] The pre-loaded high-precision map data refers to the high-precision map data collected and generated within a specific planning area. The high-precision map of the urban area where the driverless cleaning vehicle needs to work can be collected offline, and all specific areas that need to be cleaned are marked in the high-precision map. In addition, the high-precision map can be updated with data at a preset period to obtain the latest map data as offline data. Secondly, based on the high-precision map and the marked areas, all global cleaning trajectories are automatically generated. It should be noted that among the generated global trajectories, side-edge cleaning is used as one of the trajectory attributes.

[0022] In addition, for the generated global cleaning trajectory, based on the high-precision map data, the non-standard local areas are manually corrected to ensure the accuracy and rationality of the global trajectory. It can be understood that the manual correction can include manually adding map elements, manually adding smooth areas, manually adding POI information, etc.

[0023] Finally, based on the high-precision map data, when it is necessary to start the cleaning task for a certain area, the corresponding global trajectory is automatically selected and sent to the driverless cleaning vehicle, and the generated offline global cleaning trajectory is used as the first planning information.

[0024] As a preferred method, generating a cleaning global trajectory as the first planning information for the driverless cleaning vehicle according to the pre-loaded high-precision map data includes: collecting map data in the target area to obtain the pre-loaded high-precision map data; generating a cleaning global trajectory according to the high-precision map data and the marked area to be cleaned, where at least the trajectory information of edge cleaning is included in the attribute information of the cleaning global trajectory.

[0025] Step S120, based on the first planning information of the driverless cleaning vehicle, plan the edge cleaning trajectory of the driverless cleaning vehicle according to the relevant information of the driverless cleaning vehicle and the boundary information of the current driving road, where the relevant information includes vehicle-related information, and the boundary information includes the road boundary environment on the current driving road of the vehicle.

[0026] Based on the first planning information of the driverless cleaning vehicle, that is, the generated cleaning global trajectory, after considering the relevant information of the driverless cleaning vehicle and the boundary information of the current driving road, continuously optimize the path based on the first planning information, and finally plan an accurate edge cleaning trajectory in real time.

[0027] It can be understood that path planning can be performed in the planning module of the driverless cleaning vehicle and then sent to the control module for control.

[0028] The relevant information including vehicle-related information may include, but is not limited to, vehicle positioning information, vehicle speed information, etc., and the first planning path is adjusted accordingly.

[0029] The above vehicle-related information is obtained in real time and fed back to the planning module.

[0030] The boundary information including the road boundary environment on the current driving road of the vehicle may include, but is not limited to, obstacles that appear in the actual scene or objects on the path of the current planned path, or road boundary environment situations that do not meet the requirements of edge cleaning.

[0031] The above road boundary environment is obtained in real time and fed back to the planning module.

[0032] In one embodiment of the present application, based on the first planning information of the driverless sweeper, according to the relevant information of the driverless sweeper and the boundary information of the current driving road, planning the side-sweeping trajectory of the driverless sweeper further includes: based on the first planning information of the driverless sweeper, according to the relevant first information of the driverless sweeper, generating the second planning information of the driverless sweeper, where the relevant first information at least includes vehicle position information.

[0033] In specific implementation, based on the first planning information of the driverless sweeper, according to the vehicle position information of the driverless sweeper, generating the second planning information of the driverless sweeper. Preferably, in the present application, the lidar SLAM technology is used for positioning, which can achieve precise positioning when the driverless sweeper is close to the edge, sense and process the real-time point cloud data of the lidar, and calculate the vehicle position information in real time as the second planning information.

[0034] In addition, in another scenario, that is, when the autonomous sweeper is driving normally and not sweeping along the edge, the IMU+GPS / RTK combined navigation positioning method can be used for positioning. However, if only the GPS / RTK positioning method is used when sweeping along the edge, there may be oscillation errors in an environment with signal occlusion, especially in the presence of bridges and tunnels, which cannot meet the requirements of sweeping along the edge. Therefore, it is also necessary to supplement with the lidar SLAM positioning method.

[0035] In one embodiment of the present application, based on the first planning information of the driverless sweeper, according to the relevant information of the driverless sweeper and the boundary information of the current driving road, planning the side-sweeping trajectory of the driverless sweeper includes: based on the first planning information of the driverless sweeper, according to the first boundary information of the current driving road, generating the third planning information of the driverless sweeper, where the boundary first information at least includes road edge information.

[0036] Based on the first planning information of the driverless sweeper, according to the road edge information of the current driving road, generating the third planning information of the driverless sweeper. Considering that the initial high-precision map is collected and produced offline, in the actual process, the actual road environment may change. Therefore, it is necessary to sense the real-time data of sensors such as real-time lidar and cameras, identify the road boundary in real time and compare it with the offline map, and correct and update the actual map boundary through a fusion method to ensure that the vehicle truly sweeps along the edge.

[0037] Preferably, the perception of the driverless sweeper identifies the road edges in the planned path through sensors such as lidar and cameras, updates and corrects the map boundary in real time, and finally uses the updated and corrected map boundary as the third planning information.

[0038] In an embodiment of the present application, based on the first planning information of the driverless sweeper, according to the relevant information of the driverless sweeper and the boundary information of the current driving road, the side-edge cleaning trajectory of the driverless sweeper is planned, including: based on the first planning information of the driverless sweeper, according to the relevant first information of the driverless sweeper, the boundary first information of the current driving road, and the relevant second information of the driverless sweeper, the fourth planning information of the driverless sweeper is generated, where the relevant second information at least includes vehicle real-time state information; according to the second planning information, the third planning information, the fourth planning information, and the first planning information, the side-edge cleaning trajectory of the driverless sweeper is planned.

[0039] In specific implementation, based on the first planning information of the driverless sweeper, according to the relevant first information of the driverless sweeper, the boundary first information of the current driving road, and the vehicle real-time state information of the driverless sweeper, the fourth planning information of the driverless sweeper is generated.

[0040] Considering that the chassis information of the driverless sweeper during actual operation is an important basis for reflecting whether the vehicle is following the target trajectory normally. When planning the real-time trajectory, the planning module needs to use the current vehicle state as the feedback input to update the initial state of the plan in real time.

[0041] Preferably, the vehicle real-time state information fed back by the vehicle chassis is used as the fourth planning information.

[0042] Further, according to the second planning information, the third planning information, the fourth planning information, and the first planning information, the side-edge cleaning trajectory of the driverless sweeper is planned. That is to say, the planning module of the driverless sweeper, after receiving the first, second, third, and fourth planning information, plans and updates the side-edge cleaning trajectory of the vehicle in real time, and sends it to the control module of the driverless sweeper for tracking.

[0043] In an embodiment of the present application, planning the edge-cleaning trajectory of the driverless sweeper according to the second planning information, the third planning information, the fourth planning information, and the first planning information includes: intercepting corresponding trajectory information in the first planning information at each moment to determine whether the attribute in the current trajectory information includes an edge-cleaning trajectory; in the case where it is determined that the attribute in the current trajectory information includes an edge-cleaning trajectory, receiving the second planning information as vehicle positioning data in real time, using the received third planning information as real-time road boundary information, and using the fourth planning information as the initial state information for updating the real-time vehicle information, and planning the edge-cleaning trajectory of the driverless sweeper.

[0044] Specifically, when implementing, intercepting corresponding trajectory information in the first planning information at each moment to determine whether the attribute in the current trajectory information includes an edge-cleaning trajectory requires real-time judgment and feedback to the driverless sweeper planning module. Further, in the case where it is determined that the attribute in the current trajectory information includes an edge-cleaning trajectory, receiving the second planning information as vehicle positioning data in real time, using the received third planning information as real-time road boundary information, and using the fourth planning information as the initial state information for updating the real-time vehicle information, and planning the edge-cleaning trajectory of the driverless sweeper.

[0045] Since the first planning information is the global trajectory input for the trajectory planning of the driverless sweeper planning module, the planning module intercepts corresponding trajectory information in the first planning information at each moment, and at the same time determines whether the current trajectory attribute is an edge-cleaning trajectory, and the cleaning path that the actual vehicle needs to follow on the intercepted trajectory. Tracking means controlling the vehicle to follow the trajectory and drive according to the planned path.

[0046] In addition, when planning, the real-time positioning data of the driverless sweeper is required as the starting point, and the planning module receives the second planning information as vehicle positioning data in real time;

[0047] In addition, for the edge path, the driverless sweeper needs to be kept in an edge state at all times, otherwise there will be a problem of incomplete cleaning at the road edge. In order to avoid repeated cleaning due to incomplete cleaning, it is necessary to know the edge position of the current road at all times to ensure the edge cleaning of the driverless sweeper at all times. Therefore, the planning module uses the received third planning information as real-time road boundary information;

[0048] In addition, the planning module needs to know the current driving state of the driverless sweeper, and uses the fourth planning information as the initial state information for updating the real-time vehicle.

[0049] It should be noted that receiving the second planning information in real time as vehicle positioning data, using the received third planning information as real-time road boundary information, and using the fourth planning information as the initial state information for updating real-time vehicle information can optimize the trajectory simultaneously, or one or several of these pieces of information can be used to optimize the trajectory. Or, different priorities can be set according to the actual cleaning scenario. For example, certain areas need to be cleaned repeatedly, or certain areas need to be cleaned non-adjacent to the edge according to a temporary plan, etc.

[0050] In an embodiment of the present application, the relevant information of the driverless sweeper includes: determining the position information of the driverless sweeper based on the lidar SLAM positioning of the driverless sweeper; and the boundary information of the current driving road includes: obtaining the boundary information of the current driving road based on the sensors of the driverless sweeper; and updating the pre-loaded high-precision map data according to the comparison result between the boundary information of the current driving road and the pre-loaded high-precision map data.

[0051] Specifically, during implementation, the position information of the driverless sweeper is determined based on the lidar SLAM positioning of the driverless sweeper, and the boundary information of the current driving road is obtained based on the sensors of the driverless sweeper; the pre-loaded high-precision map data is updated according to the comparison result between the boundary information of the current driving road and the pre-loaded high-precision map data. The lidar SALM positioning is combined with real-time map boundary correction to achieve accurate correction during the path planning process, thus meeting the requirements of edge cleaning.

[0052] In the above steps, the lidar-based SLAM positioning is directly used to eliminate the influence of GPS positioning errors. And the real-time road boundary identified by the sensor device can adapt to possible changes in the road, improving the robustness of the edge path generation.

[0053] In an embodiment of the present application, the relevant information of the driverless sweeper further includes: the current vehicle state provided based on the chassis information of the driverless sweeper, which is used as a feedback input during the process of planning the edge cleaning trajectory of the driverless sweeper.

[0054] Specifically, during implementation, when the planning module plans the real-time trajectory, it needs to use the current vehicle state as a feedback input to update the initial state of the plan in real time. It is used as a feedback input during the process of planning the edge cleaning trajectory of the driverless sweeper.

[0055] The embodiment of the present application also provides an edge cleaning trajectory planning device 200, as Figure 2As shown in the figure, a structural schematic diagram of the edge cleaning trajectory planning device in the embodiment of the present application is provided. The edge cleaning trajectory planning device 200 at least includes: a first planning module 210 and an edge trajectory module 220, where:

[0056] In an embodiment of the present application, the first planning module 210 is specifically configured to: generate a global cleaning trajectory as the first planning information of the driverless cleaning vehicle according to the pre-loaded high-precision map data.

[0057] The pre-loaded high-precision map data refers to the high-precision map data collected and generated within a specific planning area. The high-precision map of the urban area where the driverless cleaning vehicle needs to work can be collected offline, and all specific areas that need to be cleaned are marked in the high-precision map. In addition, the high-precision map can be updated according to a preset cycle to obtain the latest map data as offline data. Secondly, based on the high-precision map and the marked areas, all global cleaning trajectories are automatically generated. It should be noted that among the generated global trajectories, edge cleaning is used as one of the trajectory attributes.

[0058] In addition, for the generated global cleaning trajectory, based on the high-precision map data, the non-standard local areas are manually corrected to ensure the accuracy and rationality of the global trajectory. It can be understood that the manual correction can include manually adding map elements, manually adding smooth areas, manually adding POI information, etc.

[0059] Finally, based on the high-precision map data, when it is necessary to start the cleaning task for a certain area, the corresponding global trajectory is automatically selected and sent to the driverless cleaning vehicle (driverless cleaning vehicle), and the generated offline global cleaning trajectory is used as the first planning information.

[0060] As a preferred method, the generating a global cleaning trajectory as the first planning information of the driverless cleaning vehicle according to the pre-loaded high-precision map data includes: collecting the map data in the target area to obtain the pre-loaded high-precision map data; generating a global cleaning trajectory according to the high-precision map data and the marked areas to be cleaned, where at least the trajectory information of edge cleaning is included in the attribute information of the global cleaning trajectory.

[0061] In an embodiment of the present application, the edge trajectory module 220 is specifically configured to: based on the first planning information of the driverless cleaning vehicle, that is, the generated global cleaning trajectory, after the relevant information of the driverless cleaning vehicle and the boundary information of the current driving road, continuously optimize the path based on the first planning information, and finally plan an accurate edge cleaning trajectory in real time.

[0062] It can be understood that the path planning can be performed in the planning module of the driverless cleaning vehicle and then sent to the control module for control.

[0063] The relevant information includes vehicle-related information, which may include but is not limited to vehicle positioning information, vehicle speed information, etc., and adjusts the first planned path in sequence.

[0064] The above vehicle-related information is obtained in real time and fed back to the planning module.

[0065] The boundary information includes the road boundary environment on the road where the vehicle is currently traveling, which may include but is not limited to obstacles that appear in the actual scene or objects on the path of the current planned path, or the road boundary environment situation that cannot meet the requirements of edge cleaning.

[0066] The above road boundary environment is obtained in real time and fed back to the planning module.

[0067] The method in this application can ensure the accuracy of edge cleaning through the global trajectory generated and corrected offline by the high-precision map, improve the system efficiency while saving system resources. In addition, directly using the lidar-based SLAM positioning eliminates the influence of GPS positioning errors. And the identified real-time road boundary can adapt to the possible changes of the road and improve the robustness of the edge cleaning path generation.

[0068] Finally, through the first, second, third, and fourth planning information, an accurate edge cleaning trajectory can be generated in real time, ensuring the accuracy, safety, and robustness of the trajectory generation while improving the system efficiency.

[0069] It can be understood that the above edge cleaning trajectory planning device can implement each step of the edge cleaning trajectory planning method provided in the foregoing embodiments. The relevant explanations about the edge cleaning trajectory planning method are applicable to the edge cleaning trajectory planning device and will not be elaborated here.

[0070] To better illustrate the implementation principle of the edge cleaning trajectory planning method in the embodiments of this application, the specific steps are as follows:

[0071] S1. Generate a global cleaning trajectory offline based on the high-precision map and the marked area.

[0072] S11. Collect the high-precision map of the urban area where the cleaning vehicle needs to work in an offline manner, and mark all specific areas that need to be cleaned in the high-precision map;

[0073] S12. Automatically generate all global cleaning trajectories based on the high-precision map and the marked area.

[0074] In the generated global trajectory, edge cleaning is taken as one of the trajectory attributes.

[0075] Based on the high-precision map data, manually correct certain non-standard local areas of the automatically generated global trajectory to ensure the accuracy and rationality of the global trajectory; when it is necessary to start the cleaning task in a certain area, automatically select the corresponding global trajectory and send it to the driverless cleaning vehicle; the generated offline global cleaning trajectory is used as the first planning information.

[0076] S2. The driverless cleaning vehicle accurately locates the vehicle position through lidar SLAM

[0077] During normal driving and non-edge cleaning, the vehicle can use the GPS+RTK positioning method for positioning. However, the GPS+RTK positioning method may have oscillation errors when cleaning along the edge, especially in environments with bridge holes and tunnels, and cannot meet the requirements of edge cleaning.

[0078] By using lidar SLAM for positioning, it is completely possible to achieve accurate positioning when cleaning along the edge. The perception processes the real-time point cloud data of the lidar, and calculates the vehicle position information in real time as the second planning information.

[0079] S3. The perception uses sensors such as lidar and cameras to identify the road edge and updates and corrects the map boundary in real time

[0080] Since the initial high-precision map is collected and made by connecting lines, in the actual process, the actual road environment may change. Therefore, it is necessary to perceive the real-time data of real-time lidar, cameras and other sensors, identify the road boundary in real time and compare it with the offline map, and correct and update the actual map boundary through the fusion method to ensure the vehicle's true edge cleaning.

[0081] The map boundary updated and corrected in real time is used as the third planning information.

[0082] S4. The real-time vehicle status information fed back by the vehicle chassis

[0083] The chassis information of the vehicle during actual operation is an important basis for reflecting whether the vehicle is following the target trajectory normally. When planning the real-time trajectory, the planning module needs to use the current vehicle status as the feedback input to update the initial state of the plan in real time.

[0084] The real-time vehicle status information fed back by the vehicle chassis is used as the fourth planning information.

[0085] S5. The planning module of the driverless cleaning vehicle plans the vehicle's edge cleaning trajectory as the trajectory input for control

[0086] The planning module of the driverless cleaning vehicle, after receiving the first, second, third, and fourth planning information, plans and updates the vehicle's edge cleaning trajectory in real time, and sends it to the control module for tracking.

[0087] S51. The first planning information is the global trajectory input for the trajectory planning of the unmanned sweeper planning module. At each moment, the planning module intercepts the corresponding trajectory information from the first planning information, and at the same time, it will judge whether the current trajectory attribute is a side-sweeping trajectory. The sweeping path that the actual vehicle needs to track on the intercepted trajectory;

[0088] S52. When planning, the real-time positioning data of the vehicle is required as the starting point, and the planning module receives the second planning information in real time as the vehicle positioning data;

[0089] S53. For the side-sweeping path, the vehicle needs to be kept in a side-sweeping state at all times. Otherwise, there will be a problem of incomplete sweeping at the road edge. In order to avoid repeated sweeping due to incomplete sweeping, it is necessary to know the position of the current road edge at all times to ensure side-sweeping of the vehicle at all times. Therefore, the planning module uses the received third planning information as the real-time road boundary information;

[0090] S54. The planning module needs to know the current driving state of the vehicle, and uses the fourth planning information as the information to update the initial state of the real-time vehicle;

[0091] Finally, based on the first, second, third, and fourth planning information, an accurate side-sweeping trajectory is planned in real time, which is used as the trajectory output for control, so as to control the autonomous sweeper to track the trajectory for sweeping operations.

[0092] Figure 3 It is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 3 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0093] The processor, network interface, and memory can be interconnected through an internal bus, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 3It is represented by only one bidirectional arrow, but it does not mean that there is only one bus or one type of bus.

[0094] A memory for storing programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0095] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a side-sweeping trajectory planning device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0096] Generate a global sweeping trajectory as the first planning information for the driverless sweeper according to the pre-loaded high-precision map data;

[0097] Based on the first planning information of the driverless sweeper, plan the side-sweeping trajectory of the driverless sweeper according to the relevant information of the driverless sweeper and the boundary information of the current driving road, where the relevant information includes vehicle-related information, and the boundary information includes the road boundary environment on the current driving road of the vehicle.

[0098] The above as in the present application Figure 1The method executed by the edge cleaning trajectory planning device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above method can be completed through the integrated logic circuit of the hardware in the processor or instructions in software form. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0099] The electronic device can also execute Figure 1 the method executed by the edge cleaning trajectory planning device in Figure 1 the illustrated embodiment and implement the functions of the edge cleaning trajectory planning device in

[0100] The embodiments of the present application also propose a computer-readable storage medium that stores one or more programs. The one or more programs include instructions that, when executed by an electronic device including multiple application programs, can enable the electronic device to execute Figure 1 the method executed by the edge cleaning trajectory planning device in the illustrated embodiment, and specifically used to execute:

[0101] Generate a cleaning global trajectory as the first planning information for the driverless cleaning vehicle according to the pre-loaded high-precision map data;

[0102] Based on the first planning information of the driverless sweeper, according to the relevant information of the driverless sweeper and the boundary information of the current driving road, a side-sweeping trajectory of the driverless sweeper is planned, where the relevant information includes vehicle-related information, and the boundary information includes the road boundary environment on the current driving road of the vehicle.

[0103] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the processes Figure 1 or multiple processes and / or blocks

[0105] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implement the functions specified in Figure 1 one or more of the processes Figure 1 or multiple processes and / or blocks

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the processes Figure 1 or multiple processes and / or blocks

[0107] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0108] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0109] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0110] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0111] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0112] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for planning the cleaning trajectory of the edge, wherein, For an autonomous sweeping vehicle, the method includes: Generating a global sweeping trajectory as the first planning information for the autonomous sweeping vehicle based on pre-loaded high-precision map data; Based on the first planning information of the autonomous sweeping vehicle, planning a side-scanning trajectory for the autonomous sweeping vehicle according to the relevant information of the autonomous sweeping vehicle and the boundary information of the current driving road, where the relevant information includes vehicle-related information, and the boundary information includes the road boundary environment on the current driving road of the vehicle; The planning of the side-scanning trajectory for the autonomous sweeping vehicle based on the first planning information of the autonomous sweeping vehicle according to the relevant information of the autonomous sweeping vehicle and the boundary information of the current driving road further includes: Generating second planning information for the autonomous sweeping vehicle based on the first planning information of the autonomous sweeping vehicle according to the relevant first information of the autonomous sweeping vehicle, where the relevant first information at least includes vehicle position information; Generating third planning information for the autonomous sweeping vehicle based on the first planning information of the autonomous sweeping vehicle according to the first boundary information of the current driving road, where the first boundary information at least includes road edge information; Generating fourth planning information for the autonomous sweeping vehicle based on the first planning information of the autonomous sweeping vehicle according to the relevant first information of the autonomous sweeping vehicle, the first boundary information of the current driving road, and the relevant second information of the autonomous sweeping vehicle, where the relevant second information at least includes vehicle real-time state information; Planning a side-scanning trajectory for the autonomous sweeping vehicle according to the second planning information, the third planning information, the fourth planning information, and the first planning information; The planning of the side-scanning trajectory for the autonomous sweeping vehicle according to the second planning information, the third planning information, the fourth planning information, and the first planning information includes: Judging whether the attribute in the current trajectory information includes a side-scanning trajectory by intercepting the corresponding trajectory information in the first planning information at each moment; When it is judged that the attribute in the current trajectory information includes a side-scanning trajectory, receiving the second planning information as vehicle positioning data in real time, taking the received third planning information as real-time road boundary information, and taking the fourth planning information as the initial state information for updating real-time vehicle information, and planning a side-scanning trajectory for the autonomous sweeping vehicle; Among them, the first planning information is an offline global sweeping trajectory automatically selected and sent to the autonomous sweeping vehicle by selecting a corresponding global trajectory when it is necessary to start a sweeping task for a certain area based on high-precision map data; The second planning information is to use lidar SLAM technology for positioning, achieve precise positioning when the autonomous sweeping vehicle is close to the edge, sense and process the real-time point cloud data of the lidar, and calculate the vehicle position information in real time; The third planning information is that the perception of the driverless sweeper uses lidar and camera sensors to identify the road edges in the planned path and updates and corrects the map boundary in real time, and finally the updated and corrected map boundary. The fourth planning information is based on the real-time vehicle status information fed back by the vehicle chassis.

2. The method according to claim 1, wherein Generating a global cleaning trajectory as the first planning information for the driverless sweeper according to the pre-loaded high-precision map data includes: Collecting map data in the target area to obtain the pre-loaded high-precision map data; Generating a global cleaning trajectory according to the high-precision map data and the marked area to be cleaned, where at least the trajectory information of cleaning along the edge is included in the attribute information of the global cleaning trajectory.

3. The method according to claim 1, wherein The relevant information of the driverless sweeper includes: Determining the position information of the driverless sweeper based on the lidar SLAM positioning of the driverless sweeper; And the boundary information of the current driving road includes: Obtaining the boundary information of the current driving road based on the sensors of the driverless sweeper; Updating the pre-loaded high-precision map data according to the comparison result between the boundary information of the current driving road and the pre-loaded high-precision map data.

4. A device for planning the cleaning trajectory of the edge, wherein, For a driverless sweeper, the device includes: A first planning module for generating a global cleaning trajectory as the first planning information for the driverless sweeper according to the pre-loaded high-precision map data; An edge-trajectory module for planning the edge-cleaning trajectory of the driverless sweeper based on the first planning information of the driverless sweeper, according to the relevant information of the driverless sweeper and the boundary information of the current driving road, where the relevant information includes vehicle-related information, and the boundary information includes the road boundary environment on the current driving road of the vehicle; Planning the edge-cleaning trajectory of the driverless sweeper based on the first planning information of the driverless sweeper, according to the relevant information of the driverless sweeper and the boundary information of the current driving road, further includes: Generating the second planning information of the driverless sweeper based on the first planning information of the driverless sweeper and the relevant first information of the driverless sweeper, where the relevant first information at least includes vehicle position information; Generating the third planning information of the driverless sweeper based on the first planning information of the driverless sweeper and the boundary first information of the current driving road, where the boundary first information at least includes road edge information; Generating the fourth planning information of the driverless sweeper based on the first planning information of the driverless sweeper, the relevant first information of the driverless sweeper, the boundary first information of the current driving road, and the relevant second information of the driverless sweeper, where the relevant second information at least includes vehicle real-time status information; Planning the edge-cleaning trajectory of the driverless sweeper according to the second planning information, the third planning information, the fourth planning information, and the first planning information; Planning the edge cleaning trajectory of the driverless sweeper according to the second planning information, the third planning information, the fourth planning information, and the first planning information includes: Judging whether the attribute in the current trajectory information includes an edge cleaning trajectory by intercepting the corresponding trajectory information in the first planning information at each moment; When it is judged that the attribute in the current trajectory information includes an edge cleaning trajectory, receiving the second planning information as vehicle positioning data in real time, using the received third planning information as real-time road boundary information, and using the fourth planning information as the initial state information for updating the real-time vehicle information, and planning the edge cleaning trajectory of the driverless sweeper; Wherein, the first planning information is an offline global cleaning trajectory automatically selected based on high-precision map data and sent to the driverless sweeper when starting to clean a certain area; The second planning information uses lidar SLAM technology for positioning, achieves precise positioning when the driverless sweeper is close to the edge, processes the real-time point cloud data of the lidar, and calculates the vehicle position information in real time; The third planning information is that the perception of the driverless sweeper identifies the road edge in the planned path through lidar and camera sensors, updates and corrects the map boundary in real time, and finally updates and corrects the map boundary in real time; The fourth planning information is based on the real-time state information of the vehicle fed back by the vehicle chassis.

5. An electronic device, comprising: A processor; And A memory arranged to store computer-executable instructions, the executable instructions, when executed, cause the processor to execute the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to execute the method according to any one of claims 1 to 3.

Images