Mobile tool collision detection method and related equipment

Abstract

The present invention discloses a mobile tool collision detection method and related equipment to quickly and timely ensure the safety of mobile tool driving. The mobile tool collision detection method comprises: determining a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; aligning the center point of a first grid area occupied by the mobile tool in the target mobile tool occupation template with a position point to be detected in a constructed occupation grid map to obtain a second grid area occupied by the mobile tool in the occupation grid map, wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; and determining whether there is a collision risk of the mobile tool at the position point to be detected according to the occupation conditions of the first grid area and the second grid area.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a mobile tool collision detection method, a mobile tool collision detection device, a processing device, a computer-readable storage medium, a computer program product containing instructions, a chip system, a circuit system, a computer system and a mobile tool. Background Art

[0002] To ensure the safe driving of autonomous vehicles or highly intelligent driving vehicles, the environmental perception system, path planning system (i.e., behavior decision system) and driving control system are three essential subsystems. After the path planning system plans the driving path according to some existing path planning strategies, it transmits it to the driving control system, which controls the relevant components of the vehicle so that the vehicle drives according to the driving path. How to quickly and timely ensure that the planned driving path allows the mobile tool to drive safely is a technical problem that technicians in this field need to solve urgently. Summary of the invention

[0003] In view of the above technical problems, the present invention provides a mobile tool collision detection method to quickly and timely ensure the safety of the mobile tool's travel.

[0004] According to a first aspect of an embodiment of the present invention, a mobile tool collision detection method is provided, comprising:

[0005] Step 101: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0006] Step 102: align the center point of the first grid area occupied by the target mobile tool in the occupation template with the position point to be detected in the constructed occupation grid map, to obtain the second grid area occupied by the mobile tool in the occupation grid map, wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0007] Step 103: Determine whether there is a collision risk of the mobile tool at the position to be detected according to the occupation status of the first grid area and the second grid area.

[0008] In a second aspect of an embodiment of the present invention, a mobile tool collision detection method is provided. When a waypoint of a driving path is determined during path planning, the following steps are performed to determine whether the waypoint has a collision risk:

[0009] Step 201: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0010] Step 202: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the waypoint in the constructed occupation grid map to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0011] Step 203: Determine whether there is a collision risk for the mobile tool at the waypoint according to the occupancy status of the first grid area and the second grid area.

[0012] According to a third aspect of an embodiment of the present invention, a mobile tool collision detection method is provided. After receiving a driving path of a mobile tool, the method determines whether there is a collision risk in the driving path according to the following steps:

[0013] Step 301: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0014] Step 302: align the center point of the first grid area occupied by the target mobile tool in the occupation template with the position of a road point of the driving path in the constructed occupation grid map, so as to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0015] Step 303: determine whether there is a collision risk for the mobile tool at the waypoint according to the occupation status of the first grid area and the second grid area; if there is a collision risk, execute step 304; if there is no collision risk, execute step 305;

[0016] Step 304: determine that there is a collision risk in the driving path, and end the process;

[0017] Step 305: Select the next waypoint from the driving path, and execute steps 302 to 305 for the waypoint.

[0018] In a fourth aspect of an embodiment of the present invention, a mobile tool collision detection method is provided. After determining the driving state node of the state transition path of the mobile tool during the path planning process, the following steps are performed to determine whether the driving state node has a collision risk:

[0019] Step 401: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0020] Step 402: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the state travel node in the constructed occupation grid map to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0021] Step 403: Determine whether there is a collision risk at the driving state node according to the occupancy status of the first grid area and the second grid area.

[0022] According to a fifth aspect of an embodiment of the present invention, a mobile tool collision detection method is provided. After receiving a state transition path of a mobile tool, it is determined whether there is a collision risk in the state transition path according to the following steps:

[0023] Step 501: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0024] Step 502: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of a driving state node of the state transition path in the constructed occupation grid map to obtain a second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0025] Step 503, determining whether there is a collision risk at the driving state node according to the occupation status of the first grid area and the second grid area; if there is a collision risk, executing step 504, and if there is no collision risk, executing step 505;

[0026] Step 504: determine that there is a collision risk in the state transition path, and end the process;

[0027] Step 505, selecting a next driving state node from the state transition path, and executing step 502 for the driving state node if there is a next driving state node, and executing step 506 if there is no next driving state node in the state transition path;

[0028] Step 506: Determine that the state transition path has no collision risk, and end the process.

[0029] The mobile tool collision detection method provided in the first aspect to the fifth aspect of the embodiments of the present invention has some technical effects. Since a mobile tool occupation template containing various postures is pre-set, the target mobile tool occupation template can be quickly determined after the current posture of the mobile tool is determined. The center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template is aligned with the position point to be detected in the occupation grid map (the position point to be detected can be, for example, a certain waypoint planned in the mobile tool path planning process or a position point corresponding to a certain driving state node, or the position point to be detected can be, for example, a certain waypoint on the driving path or state transfer path obtained after path planning for the mobile tool or a position point corresponding to a driving state node). The second grid area occupied by the mobile tool in the occupation grid map can be quickly determined, so that it can be quickly determined whether there is a collision risk for the mobile tool at the position point to be detected / the driving path planned for the mobile tool according to the occupation status of the first grid area and the second grid area. There is no need to draw the mobile tool in real time in the occupation grid map according to the posture, vehicle model, and size of the mobile tool, thereby improving efficiency and speed.

[0030] According to a sixth aspect of an embodiment of the present invention, there is provided a mobile tool collision detection device, comprising:

[0031] A matching unit, used to determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0032] A grid area determination unit, used to align the center point of the first grid area occupied by the target mobile tool in the occupation template with the position point to be detected in the constructed occupation grid map, so as to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0033] The collision determination unit is used to determine whether there is a collision risk of the mobile tool at the position to be detected according to the occupancy status of the first grid area and the second grid area.

[0034] According to a seventh aspect of an embodiment of the present invention, there is provided a mobile tool collision detection device, comprising:

[0035] A first path planning unit is used to plan a path for the mobile tool and start the first collision detection unit when a waypoint of the driving path is determined during the path planning process;

[0036] The first collision detection unit is used to determine whether there is a collision risk at the waypoint according to the following steps: step 201, determining a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; step 202, aligning the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the waypoint in the constructed occupation grid map, to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; step 203, determining whether there is a collision risk of the mobile tool at the waypoint based on the occupation status of the first grid area and the second grid area.

[0037] According to an eighth aspect of an embodiment of the present invention, there is provided a mobile tool collision detection device, comprising:

[0038] The collision detection unit is used to determine whether there is a collision risk in the driving path according to the following steps after receiving the driving path of the mobile tool:

[0039] Step 301: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0040] Step 302: align the center point of the first grid area occupied by the target mobile tool in the occupation template with the position of a road point of the driving path in the constructed occupation grid map, so as to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0041] Step 303: determine whether there is a collision risk for the mobile tool at the waypoint according to the occupation status of the first grid area and the second grid area; if there is a collision risk, execute step 304; if there is no collision risk, execute step 305;

[0042] Step 304: determine that there is a collision risk in the driving path, and end the process;

[0043] Step 305: Select the next waypoint from the driving path, and execute steps 302 to 305 for the waypoint.

[0044] According to a ninth aspect of the embodiments of the present invention, there is provided a mobile tool collision detection device, comprising:

[0045] A second path planning unit, configured to trigger a second collision detection unit after determining a current driving state node of a state transition path of the mobile tool during the path planning process;

[0046] The second collision detection unit is used to determine whether there is a collision risk at the current driving state node according to the following steps:

[0047] Step 401: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0048] Step 402: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the state travel node in the constructed occupation grid map to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0049] Step 403: Determine whether there is a collision risk at the driving state node according to the occupancy status of the first grid area and the second grid area.

[0050] According to a tenth aspect of an embodiment of the present invention, there is provided a mobile tool collision detection device, comprising:

[0051] The collision detection unit is used to determine whether there is a collision risk in the state transition path according to the following steps after receiving the state transition path of the mobile tool:

[0052] Step 501: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0053] Step 502: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of a driving state node of the state transition path in the constructed occupation grid map to obtain a second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0054] Step 503, determining whether there is a collision risk at the driving state node according to the occupation status of the first grid area and the second grid area; if there is a collision risk, executing step 504, and if there is no collision risk, executing step 505;

[0055] Step 504: determine that there is a collision risk in the state transition path, and end the process;

[0056] Step 505, selecting a next driving state node from the state transition path, and executing step 502 for the driving state node if there is a next driving state node, and executing step 506 if there is no next driving state node in the state transition path;

[0057] Step 506: Determine that the state transition path has no collision risk, and end the process.

[0058] According to an eleventh aspect of the embodiments of the present invention, a processing device is provided, including:

[0059] The processor is used to execute the following steps: step 101, determining a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; step 102, aligning the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position point to be detected in the constructed occupation grid map, to obtain the second grid area occupied by the mobile tool in the occupation grid map, wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; step 103, determining whether there is a collision risk of the mobile tool at the position point to be detected based on the occupancy of the first grid area and the second grid area.

[0060] According to a twelfth aspect of the embodiments of the present invention, a processing device is provided, including:

[0061] A processor is used to determine, during the path planning process, a waypoint of a driving path, and to determine whether the waypoint has a collision risk according to the following steps: step 201, determining a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; step 202, aligning the center point of a first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the waypoint in a constructed occupation grid map, to obtain a second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; step 203, determining whether the mobile tool has a collision risk at the waypoint according to the occupation conditions of the first grid area and the second grid area.

[0062] According to a thirteenth aspect of the embodiment of the present invention, a processing device is provided, including:

[0063] A processor is used to determine whether there is a collision risk in the driving path after receiving the driving path of a mobile tool according to the following steps: Step 301, determine a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; Step 302, align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of a road point of the driving path in the constructed occupation grid map, and obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 303, determine whether there is a collision risk of the mobile tool at the road point according to the occupation status of the first grid area and the second grid area; if there is a collision risk, execute step 304, if there is no collision risk, execute step 305; Step 304, determine that there is a collision risk in the driving path, and end the process; Step 305, select the next road point from the driving path, and execute steps 302 to 305 for the road point.

[0064] According to a fourteenth aspect of the embodiments of the present invention, a processing device is provided, including:

[0065] A processor is used to determine whether there is a collision risk at the driving state node after determining the driving state node of the state transfer path of the mobile tool during the path planning process according to the following steps: Step 401, determine a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; Step 402, align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the state driving node in the constructed occupation grid map, and obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 403, determine whether there is a collision risk at the driving state node according to the occupation status of the first grid area and the second grid area.

[0066] According to a fifteenth aspect of the embodiments of the present invention, a processing device is provided, including:

[0067] The processor is used to determine whether there is a collision risk in the state transition path according to the following steps after receiving the state transition path of the mobile tool: step 501, determining a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; step 502, aligning the center point of a first grid area occupied by the mobile tool in the target mobile tool occupation template with a position of a driving state node of the state transition path in a constructed occupation grid map, and obtaining a second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center. According to the grid map; step 503, determine whether there is a collision risk at the driving state node according to the occupancy of the first grid area and the second grid area; if there is a collision risk, execute step 504, if there is no collision risk, execute step 505; step 504, determine whether there is a collision risk on the state transfer path, and end the process; step 505, select the next driving state node from the state transfer path, if there is a next driving state node, execute step 502 for the driving state node, if there is no next driving state node on the state transfer path, execute step 506; step 506, determine that there is no collision risk on the state transfer path, and end the process.

[0068] According to a sixteenth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, comprising a program or an instruction. When the program or the instruction is executed on a computer, the mobile tool collision detection method provided in the first aspect described above is implemented.

[0069] According to a seventeenth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, comprising a program or an instruction. When the program or the instruction is executed on a computer, the mobile tool collision detection method provided in the second aspect described above is implemented.

[0070] According to an eighteenth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, comprising a program or an instruction. When the program or the instruction is executed on a computer, the mobile tool collision detection method provided in the third aspect described above is implemented.

[0071] According to a nineteenth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, comprising a program or an instruction. When the program or the instruction is executed on a computer, the mobile tool collision detection method provided in the fourth aspect is implemented.

[0072] According to a twentieth aspect of an embodiment of the present invention, there is provided a computer-readable storage medium, comprising a program or an instruction. When the program or the instruction is executed on a computer, the mobile tool collision detection method provided in the fifth aspect described above is implemented.

[0073] According to a twenty-first aspect of the embodiments of the present invention, there is provided a computer program product comprising instructions, wherein when the computer program product is run on a computer, the computer is enabled to execute the mobile tool collision detection method provided in the first aspect.

[0074] According to a twenty-second aspect of the embodiments of the present invention, there is provided a computer program product comprising instructions, wherein when the computer program product is run on a computer, the computer is enabled to execute the mobile tool collision detection method provided in the second aspect.

[0075] According to a twenty-third aspect of the embodiments of the present invention, there is provided a computer program product comprising instructions, wherein when the computer program product is run on a computer, the computer is enabled to execute the mobile tool collision detection method provided in the third aspect.

[0076] According to a twenty-fourth aspect of the embodiments of the present invention, there is provided a computer program product comprising instructions, wherein when the computer program product is run on a computer, the computer is enabled to execute the mobile tool collision detection method provided in the fourth aspect.

[0077] According to a twenty-fifth aspect of the embodiments of the present invention, there is provided a computer program product comprising instructions, wherein when the computer program product is run on a computer, the computer is enabled to execute the mobile tool collision detection method provided in the fifth aspect above.

[0078] According to a twenty-sixth aspect of an embodiment of the present invention, a chip system is provided, comprising a processor, wherein the processor is coupled to a memory, wherein the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the mobile tool collision detection method provided in the first aspect is implemented.

[0079] According to a twenty-seventh aspect of an embodiment of the present invention, a chip system is provided, comprising a processor, wherein the processor is coupled to a memory, wherein the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the mobile tool collision detection method provided in the second aspect is implemented.

[0080] According to a twenty-eighth aspect of an embodiment of the present invention, a chip system is provided, comprising a processor, wherein the processor is coupled to a memory, wherein the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the mobile tool collision detection method provided in the third aspect is implemented.

[0081] According to a twenty-ninth aspect of an embodiment of the present invention, a chip system is provided, comprising a processor, wherein the processor is coupled to a memory, wherein the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the mobile tool collision detection method provided in the fourth aspect is implemented.

[0082] In the thirtieth aspect of the embodiments of the present invention, a chip system is provided, including a processor, wherein the processor is coupled to a memory, and the memory stores program instructions. When the program instructions stored in the memory are executed by the processor, the mobile tool collision detection method provided in the fifth aspect is implemented.

[0083] According to a thirty-first aspect of the embodiments of the present invention, there is provided a circuit system, the circuit system comprising a processing circuit, the processing circuit being configured to execute the mobile tool collision detection method provided in the first aspect above.

[0084] According to a thirty-second aspect of the embodiments of the present invention, a circuit system is provided, the circuit system comprising a processing circuit, the processing circuit being configured to execute the mobile tool collision detection method provided in the second aspect above.

[0085] According to a thirty-third aspect of the embodiments of the present invention, a circuit system is provided, the circuit system comprising a processing circuit, the processing circuit being configured to execute the mobile tool collision detection method provided in the aforementioned third aspect.

[0086] According to a thirty-fourth aspect of the embodiments of the present invention, a circuit system is provided, wherein the circuit system includes a processing circuit, and the processing circuit is configured to execute the mobile tool collision detection method provided in the fourth aspect.

[0087] According to a thirty-fifth aspect of the embodiments of the present invention, there is provided a circuit system, the circuit system comprising a processing circuit, the processing circuit being configured to execute the mobile tool collision detection method provided in the fifth aspect above.

[0088] In a thirty-sixth aspect of an embodiment of the present invention, a computer system is provided, comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method provided in the first aspect above.

[0089] In the thirty-seventh aspect of the embodiments of the present invention, a computer system is provided, comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method provided in the second aspect above.

[0090] In a thirty-eighth aspect of an embodiment of the present invention, a computer system is provided, comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method provided in the aforementioned third aspect.

[0091] According to a thirty-ninth aspect of an embodiment of the present invention, a computer system is provided, comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method provided in the fourth aspect.

[0092] In the 40th aspect of the embodiments of the present invention, a computer system is provided, comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method provided in the aforementioned fifth aspect.

[0093] In a forty-first aspect of an embodiment of the present invention, a mobile tool is provided, comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method provided in the first aspect above.

[0094] In a forty-second aspect of the embodiments of the present invention, a mobile tool is provided, comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method provided in the second aspect above.

[0095] In a forty-third aspect of the embodiments of the present invention, a mobile tool is provided, comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method provided in the third aspect above.

[0096] According to a forty-fourth aspect of the embodiments of the present invention, a mobile tool is provided, comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method provided in the fourth aspect.

[0097] In a forty-fifth aspect of the embodiments of the present invention, a mobile tool is provided, comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method provided in the fifth aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0099] Figure 1 , Figure 1A and Figure 1B Flowcharts 1, 2 and 3 of the mobile tool collision detection method provided in Embodiment 1 of the present invention;

[0100] Figure 2 This is a schematic diagram of a template occupied by a moving tool in the first embodiment of the present invention;

[0101] Figure 3A , 3B 3C are schematic diagrams of the target moving tool occupying the template, the occupying grid map and the second grid area of ​​the moving tool in the occupying grid map in accordance with the first embodiment of the present invention;

[0102] Figure 4A , 4B 4C are schematic diagrams of the target moving tool occupying the template, the occupying grid map and the second grid area of ​​the moving tool in the occupying grid map in accordance with the first embodiment of the present invention;

[0103] Figure 5A , 5B 5C are schematic diagrams of the target moving tool occupying the template, the occupying grid map and the second grid area of ​​the moving tool in the occupying grid map in accordance with the first embodiment of the present invention;

[0104] Fig. 6A , 6B 6C are schematic diagrams of the target moving tool occupying the template, the occupying grid map and the second grid area of ​​the moving tool in the occupying grid map in accordance with the first embodiment of the present invention;

[0105] Figure 7 , Fig. 7A and Figure 7B Flowcharts 1, 2 and 3 of the mobile tool collision detection method in Embodiment 2 of the present invention;

[0106] Figure 8 , Fig. 8A , Figure 8B and Figure 8C Flowcharts 1, 2, 3 and 4 of the mobile tool collision detection method in Embodiment 3 of the present invention;

[0107] Fig. 9 , Fig. 9C , Fig.9D and Fig.9E The flowcharts of the first, second, third and fourth of constructing the state transition path in the fourth embodiment of the present invention are as follows;

[0108] Fig. 9A , Fig. 9B A schematic diagram of a state transition space for determining a current driving state node in a fourth embodiment of the present invention;

[0109] Fig.9F , Figure 9G and Figure 9H A diagram showing a process of changes in the node value and the number of times a node is selected of a driving state node in a fourth embodiment of the present invention;

[0110] Fig.10 , Fig. 10A and Fig. 10B Flowcharts 1, 2, and 3 of the mobile tool collision detection method in Embodiment 5 of the present invention;

[0111] Fig.11 , Fig.11A and Fig. 11B Flowcharts 1, 2, and 3 of the mobile tool collision detection method in Embodiment 6 of the present invention;

[0112] Fig.12 , Fig. 12A and Fig. 12B Schematic diagram of the structure of a mobile tool collision detection device in Embodiment 7 of the present invention;

[0113] Fig.13 , Fig.13A and Fig. 13B It is a structural schematic diagram of a mobile tool collision detection device in Embodiment 8 of the present invention;

[0114] Fig.14 It is a structural schematic diagram of a mobile tool collision detection device in Embodiment 10 of the present invention;

[0115] Fig.15is a schematic diagram of a computer program product in Embodiment 17 of the present invention;

[0116] Fig.16 , 17 1 and 18 are schematic diagrams of the structure of the mobile tool system in Embodiment 20 of the present invention;

[0117] Fig.19 is a schematic diagram of the structure of a computer system in Embodiment 20 of the present invention;

[0118] Fig. 20 This is a schematic diagram of the structure of the computer system in Embodiment 20 of the present invention. DETAILED DESCRIPTION

[0119] The terms "first" and "second" in the specification and drawings of the present application are used to distinguish different objects, or to distinguish different treatments of the same object, rather than to describe the specific order of objects. In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes other steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way. In the embodiments of the present application, "A and / or B" means A and B, A or B. "A, and / or B, and / or C" means any one of A, B, and C, or any two of A, B, and C, or A, B, and C. In the embodiments of the present application, "A, B, or C" means any one of A, B, and C.

[0120] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0121] The mobile tool collision detection method provided in the embodiment of the present invention can be applied to a mobile tool with a driving function, or applied to other devices (such as a cloud server) with a function of controlling the driving of the mobile tool. The mobile tool can implement the mobile tool collision detection method provided in the embodiment of the present application through the components (including hardware and software) it contains. Alternatively, other devices (such as a cloud server) are used to implement the mobile tool collision detection method provided in the embodiment of the present application, and send the collision detection result to the mobile tool.

[0122] In an embodiment of the present invention, the mobile tool can be any movable tool, such as a vehicle (such as a passenger car, a bus, a coach, a van, a truck, a truck, a trailer, a trailer, a crane, an excavator, a bulldozer, a road train, a sweeper, a sprinkler truck, a garbage truck, an engineering vehicle, a rescue vehicle, a logistics vehicle, an AGV (Automated Guided Vehicle), etc.), a motorcycle, a bicycle, a tricycle, a trolley, a tire crane, an overhead crane, a quay crane, a robot, a sweeper, a balance car, an aircraft, a ship, a submarine, a train, etc. The present application does not strictly limit the type of mobile tools and will not list them all here.

[0123] Embodiment 1

[0124] See also Figure 1 , is a flow chart of a mobile tool collision detection method provided in Embodiment 1 of the present invention, the method comprising steps 101 to 103, wherein:

[0125] Step 101: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0126] Step 102: align the center point of the first grid area occupied by the target mobile tool in the occupation template with the position point to be detected in the constructed occupation grid map, to obtain the second grid area occupied by the mobile tool in the occupation grid map, wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0127] Step 103: Determine whether there is a collision risk of the mobile tool at the position to be detected according to the occupation status of the first grid area and the second grid area.

[0128] In some optional embodiments, Figure 1The method flow shown may further include step 100. In some optional embodiments, step 100 is performed first and then step 101; in some optional embodiments, step 101 is performed first and then step 100; in some optional embodiments, step 100 and step 101 are performed simultaneously. The present application has no strict requirements on the order in which step 100 and step 101 are performed. Figure 1A It is shown that step 100 is arranged before step 101, wherein: step 100, constructing an occupation grid map with the current position of the mobile tool as the center.

[0129] In some optional embodiments, the Figure 1 The method flow shown may further include step 100A. In some optional embodiments, step 100A is performed first and then step 101; in some optional embodiments, step 101 is performed first and then step 100A; in some optional embodiments, step 100A and step 101 are performed simultaneously. The present application has no strict requirements on the order in which step 100A and step 101 are performed. Figure 1B It is shown that step 100A is arranged before step 101, wherein: step 100A, receiving the occupancy grid map.

[0130] In some optional embodiments, the mobile tool occupation template is a grid map pre-constructed with the mobile tool as the center, and the grid area occupied by the mobile tool is pre-marked in the grid map according to the size, shape and posture of the mobile tool. Figure 2 As shown, taking a semi-trailer as an example, a semi-trailer of the same size and shape occupies different grid areas in the grid map in different postures. Figure 2 The figure only illustrates several of the postures. Those skilled in the art can construct mobile tool occupation templates of different postures according to different granularities based on actual needs.

[0131] In some optional embodiments, in the aforementioned step 101, after determining the current posture of the mobile tool, a target mobile tool occupation template that matches the current posture of the mobile tool is searched from the mobile tool occupancy template. For example, if there is a mobile tool occupation template in the mobile tool occupation template whose posture is consistent with the current posture of the mobile tool, then the mobile tool occupation template is used as the target mobile tool occupation template; if there is no mobile tool occupation template in the mobile tool occupation template whose posture is consistent with the current posture of the mobile tool, then the mobile tool occupation template whose posture is closer to the posture of the mobile tool is used as the target mobile tool occupation template.

[0132] In some optional embodiments, the step 103 determines whether there is a risk of collision of the mobile tool at the position to be detected based on the occupation of the first grid area and the second grid area, specifically including: if a preset number (the preset number can be flexibly set by those skilled in the art according to actual conditions, and this application does not strictly limit it) of grids in the second grid area are marked as occupied by obstacles, then it is determined that there is a risk of collision of the mobile tool at the position to be detected. The value of each grid in the mobile tool occupation template is 0. The target mobile tool occupies the template as shown in FIG. Figure 3A As shown, the moving tool occupies 36 grids in the first grid area of ​​the target moving tool template; each grid in the constructed occupied grid map is marked as "occupied" or "unoccupied" according to the occupancy status, for example, "occupied" can be marked with 1 and "unoccupied" can be marked with 0, as shown in FIG. Figure 3B As shown in FIG. 1 , the occupancy grid map is constructed; the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template is aligned with the position point to be detected in the occupancy grid map to obtain the second grid area occupied by the mobile tool in the occupancy grid map, as shown in FIG. Figure 3C As shown, the second grid area includes 36 grids, and the 36 grids in the first grid area correspond to the 36 grids in the second grid area. There is no grid marked as "occupied" in the second grid area, so it can be determined that there is no collision risk for the mobile tool at the position to be detected.

[0133] In some optional embodiments, the step 103 determines whether there is a collision risk for the mobile tool at the position to be detected based on the occupation of the first grid area and the second grid area, specifically including: calculating a collision assessment value used to characterize the probability of collision based on the occupation of the first grid area and the second grid area, and determining whether there is a collision risk for the mobile tool at the position to be detected based on the collision assessment value. For example, it is determined whether the collision assessment value is greater than or equal to a preset value, and if so, it is determined that there is a collision risk for the mobile tool at the position to be detected, and if not, it is determined that there is no collision risk for the mobile tool at the position to be detected.

[0134] In some optional embodiments, a collision evaluation value used to characterize the collision probability is calculated based on the occupancy of the first grid area and the second grid area. The specific implementation may be as follows: the sum of the products of the occupancy probability of the grids in the first grid area and the occupancy probability of the corresponding grids in the second grid area is taken as the collision evaluation value. Figure 4A As shown in , the first grid area contains 36 grids, and the grid occupancy probability is 1. The values ​​of each grid in the grid map are as follows: Figure 4BThe center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template is aligned with the position point to be detected in the occupation grid map to obtain the second grid area occupied by the mobile tool in the occupation grid map. The second grid area contains 36 grids, as shown in FIG. Figure 4C The product of the occupancy probability of the 36 grids in the first grid area and the occupancy probability of the 36 grids in the second grid area is summed (for example, the i-th grid in the first grid area is represented by Ai, and the i-th grid in the second grid area is represented by Bi, and the collision evaluation value is calculated as ∑A i B i ), and the collision assessment value is 2.9.

[0135] In some optional embodiments, the values ​​of each grid in the mobile tool occupation template are set to binary values ​​according to a preset occupation rule; after constructing the occupation grid map with the current position of the mobile tool as the center, it also includes: setting the values ​​of the grids in the occupation grid map according to the occupation rule. In step 104, determining whether the mobile tool has a collision risk at the position to be detected based on the occupation of the first grid area and the second grid area specifically includes: performing a binary operation on the values ​​of the grids in the first grid area and the corresponding grids in the second grid area, and determining whether the mobile tool has a collision risk at the position to be detected based on the operation result.

[0136] In some optional embodiments, the occupation rule is that when the grid is occupied by an obstacle or a mobile tool, its value is set to 1, otherwise it is set to 0; the binary operation is a binary "and" operation; in step 103, the grids in the first grid area are subjected to a binary operation with the values ​​of the corresponding grids in the second grid area, and the operation result is used to determine whether there is a risk of collision of the mobile tool at the position to be detected, specifically including: performing a binary "and" operation on the values ​​of each grid in the grid area and the values ​​of the corresponding grids in the occupied grid map, and if there are more than a preset number (the preset number can be flexibly set by technicians in this field according to actual conditions, and is not strictly limited here) and the result of the "and" operation is 1, it is determined that the mobile tool has a risk of collision at the position to be detected. Figure 5A As shown, the target moving tool occupies the template, and the values ​​of the 36 grids in the first grid area occupied by the moving tool are all 1, and the values ​​of the other grids are 0; Figure 5B As shown, the grid occupied by obstacles in the occupied grid map has a value of 1, and the grid not occupied by obstacles has a value of 0; the center point of the first grid area is aligned with the position point to be detected in the occupied grid map to obtain the second grid area occupied by the mobile tool in the occupied grid map, as shown in FIG. Figure 5CAs shown, the 36 grids contained in the second grid area are obtained. The 36 grids in the first grid area correspond to the 36 grids in the second grid area one by one. Ai represents the i-th grid in the first grid area, and Bi represents the i-th grid in the second grid area. The grids Ai and Bi are ANDed, and if 1 is obtained in the operation result, it can be determined whether the mobile tool has a collision risk at the position to be detected.

[0137] In some optional embodiments, the occupation rule is that when the grid is occupied by an obstacle or a mobile tool, its value is set to 0, otherwise it is set to 1; the binary operation is a binary "or" operation; the grid of the first grid area is binary operated with the value of the corresponding grid in the second grid area, and it is determined whether the mobile tool has a collision risk at the position to be detected according to the operation result, specifically including: the grid of the first grid area is binary operated with the value of the corresponding grid in the second grid area, and it is determined whether the mobile tool has a collision risk at the position to be detected according to the operation result, specifically including: the value of each grid in the grid area is binary ORed with the value of the corresponding grid in the occupied grid map, if there are more than a preset number (the value of the preset number can be flexibly set by technicians in this field according to actual needs, and this application does not strictly limit it) and the result of the OR operation is 0, it is determined that the mobile tool has a collision risk at the position to be detected. Fig. 6A As shown, the target moving tool occupies the template, and the values ​​of the 36 grids in the first grid area occupied by the moving tool are all 0, and the values ​​of the other grids are 1; Figure 6B As shown, the grids occupied by obstacles in the occupied grid map have a value of 0, and the grids not occupied by obstacles have a value of 1; the center point of the first grid area is aligned with the position point to be detected in the occupied grid map to obtain the second grid area occupied by the mobile tool in the occupied grid map, as shown in FIG. Figure 6C As shown, the second grid area contains 36 grids. The 36 grids in the first grid area correspond to the 36 grids in the second grid area one by one. Ai represents the i-th grid in the first grid area, and Bi represents the i-th grid in the second grid area. Ai and Bi are "or" operated, and if there is 0 in the operation result, it can be determined that the mobile tool has a collision risk at the position to be detected.

[0138] Embodiment 2

[0139] In some optional embodiments, the position point to be detected in the aforementioned embodiment 1 can be a waypoint of the driving path determined in the process of path planning (the waypoint includes the position information and driving state information of the mobile tool, the position information may include the coordinate information and driving direction information of the mobile tool, and the driving state information may include but is not limited to any one or more of the following information of the mobile tool: the linear speed, linear acceleration, linear acceleration, steering gear angle, steering wheel angle, steering wheel rotation angular velocity, steering wheel rotation angular acceleration, hanging box angle, etc. of the mobile tool). For example, in the process of path planning for the mobile tool, the aforementioned can be started each time a waypoint is determined. Figure 1 The collision detection method shown is used to determine whether the mobile tool has a collision risk at the waypoint. If there is a collision risk, the waypoint is abandoned and the waypoint is replanned. If there is no collision risk, the waypoint is retained and the next waypoint is planned.

[0140] Embodiment 2 of the present invention provides a mobile tool collision detection method, such as Figure 7 As shown, when a waypoint of a driving path is determined during the path planning process, the following steps 201 to 203 are followed to determine whether the waypoint has a collision risk, wherein:

[0141] Step 201: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0142] Step 202: align the center point of the first grid area occupied by the target mobile tool in the occupation template with the position of the waypoint in the occupation grid map to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0143] Step 203: Determine whether there is a collision risk of the mobile tool at the waypoint based on the occupation status of the first grid area and the second grid area. If there is a collision risk, abandon the waypoint and replan the waypoint.

[0144] In the aforementioned step 202, the position of the waypoint in the occupied grid map is obtained by mapping the longitude and latitude coordinates of the waypoint to the position point in the occupied grid map.

[0145] In some optional embodiments, the Figure 7The method flow shown may further include step 200. In some optional embodiments, step 200 is performed first and then step 201; in some optional embodiments, step 201 is performed first and then step 200; in some optional embodiments, step 200 and step 201 are performed simultaneously. The present application has no strict requirements on the order in which step 200 and step 201 are performed. Fig. 7A It is shown that step 200 is arranged before step 201, wherein: step 200, constructs an occupation grid map with the current position of the mobile tool as the center.

[0146] In some optional embodiments, the Figure 7 The method flow shown may further include step 200A. In some optional embodiments, step 200A is performed first and then step 201; in some optional embodiments, step 201 is performed first and then step 200A; in some optional embodiments, step 200A and step 201 are performed simultaneously. The present application has no strict requirements on the order in which step 200A and step 201 are performed. Figure 7B It is shown that step 200A is arranged before step 201, wherein: step 200A, receiving the occupancy grid map.

[0147] The specific implementation method of the aforementioned steps 200 to 203 is the same as the specific implementation principle of steps 100 to 103 in the aforementioned embodiment 1, and will not be repeated here.

[0148] Embodiment 3

[0149] In some optional embodiments, the position point to be detected in the aforementioned embodiment 1 may be a waypoint in the driving path obtained by the path planning of the mobile tool. For example, after the path planning is performed for the mobile tool to obtain the driving path, the aforementioned detection method may be initiated for the waypoint in the driving path. Figure 1 The mobile tool collision detection method shown is used to determine whether the mobile tool has a collision risk at the waypoint. If there is a collision risk, it is determined that the driving path has a collision risk, and the driving path of the mobile tool is replanned.

[0150] Embodiment 3 of the present invention provides a mobile tool collision detection method, such as Figure 8 As shown, after receiving the driving path of the mobile tool, the following steps 301 to 305 are followed to determine whether there is a collision risk in the driving path:

[0151] Step 301: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0152] Step 302: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of a road point of the driving path in the occupation grid map to obtain a second grid area occupied by the mobile tool in the occupation grid map;

[0153] Step 303: determine whether the mobile tool has a collision risk at the waypoint according to the occupation of the first grid area and the second grid area; if there is a collision risk, execute step 304; if not, determine whether the waypoint is the last waypoint of the driving path; if so, determine that there is no collision risk on the driving path; otherwise, execute step 305;

[0154] Step 304: determine that there is a collision risk in the driving path, and end the process;

[0155] Step 305: Select the next waypoint from the driving path, and execute steps 302 to 305 for the waypoint.

[0156] Of course, those skilled in the art can also Figure 8 The method flow shown in the figure can be extended to other alternative solutions to determine whether there is a collision risk in the driving path, such as Fig. 8A As shown, after receiving the driving path of the mobile tool, the following steps 301 to 307 are followed to determine whether there is a collision risk in the driving path:

[0157] Step 301: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0158] Step 302: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of a road point of the driving path in the occupation grid map to obtain a second grid area occupied by the mobile tool in the occupation grid map;

[0159] Step 303: Determine whether there is a collision risk for the mobile tool at the waypoint according to the occupation status of the first grid area and the second grid area; if there is a collision risk, execute step 304A; if there is no collision risk, execute step 305A;

[0160] Step 304A, marking the waypoint as having a collision risk, and executing step 305A;

[0161] Step 305A, determining whether the waypoint is the last waypoint in the driving path, if so, executing step 307, if not, executing step 306;

[0162] Step 306: Select the next waypoint from the driving path, and execute step 302 for the waypoint;

[0163] Step 307: determine whether the number of waypoints marked as having collision risks in the driving path is greater than a preset number (the value of the preset number can be flexibly set by technical personnel in this field according to actual needs, and this application does not strictly limit it). If so, determine that there is a collision risk on the driving path; otherwise, determine that there is no collision risk on the driving path.

[0164] In some optional embodiments, the Figure 8 The method flow shown may further include step 300. In some optional embodiments, step 300 is performed first and then step 301; in some optional embodiments, step 301 is performed first and then step 300; in some optional embodiments, step 300 and step 301 are performed simultaneously. The present application has no strict requirements on the order in which step 300 and step 301 are performed. Figure 8B It is shown that step 300 is arranged before step 301, wherein: step 300, constructs an occupation grid map with the current position of the mobile tool as the center.

[0165] In some optional embodiments, the Figure 8 The method flow shown may further include step 300A. In some optional embodiments, step 300A is performed first and then step 301; in some optional embodiments, step 301 is performed first and then step 300A; in some optional embodiments, step 300A and step 301 are performed simultaneously. The present application has no strict requirements on the order in which step 300A and step 301 are performed. Figure 8C It is shown that step 300A is arranged before step 301, wherein: step 300A, receiving the occupancy grid map.

[0166] The specific implementation method of the above steps 300 to 303 is the same as the specific implementation principle of steps 100 to 103 in the above embodiment 1, and will not be repeated here.

[0167] Embodiment 4

[0168] In some optional embodiments, in order to ensure that the driving path planned for the mobile tool is in accordance with the dynamic model of the mobile tool and is a driving path that the mobile tool can actually travel along, in the embodiments of the present invention, when planning the path for the mobile tool, multiple state transition paths can be first constructed according to the current driving state of the mobile tool, and then a target state transition path can be selected, and finally the waypoint sequence corresponding to the target state transition path is determined as the driving path of the mobile tool (the waypoint sequence corresponding to the target state transition path refers to the waypoints corresponding to each driving state node of the target state transition path). Since the state transition path represents the state transition relationship of the mobile tool from one driving state to another, that is, each adjacent driving state node on the planned state transition path is transferable, which is in accordance with the dynamic model of the mobile tool, therefore, the mobile tool travels along the driving path corresponding to the target state transition path in accordance with the dynamic model, can really travel along the driving path, and the effectiveness of the driving path is high.

[0169] In some optional embodiments, multiple state transition paths are constructed according to the current driving state of the mobile tool, which can be specifically constructed by Fig. 9 Steps A1 to A4 shown construct each state transition path:

[0170] Step A1, taking the current driving state of the mobile tool as the starting driving state node, and taking the starting driving state node as the current driving state node;

[0171] Step A2, determining the state transition space of the current driving state node, and searching in the state transition space of the current driving state node to obtain the next driving state node of the current driving state node;

[0172] Step A3, taking the next driving state node obtained in step A2 as the current driving state node, and repeatedly executing step A2; until a preset number of driving state nodes are generated;

[0173] Step A4: construct a state transition path according to the sequence of multiple driving state nodes.

[0174] In some optional embodiments, determining the state transition space of the current driving state node in step A2 specifically includes: taking the current driving state node as the target driving state node; determining the state transition space corresponding to the target driving state node; and determining the state transition space corresponding to the target driving state node as the state transition space of the current driving state node. Fig. 9AThis is just an exemplary description. Assume that a state transition path contains 4 driving state nodes, and the starting driving state node of the mobile tool is S1. The starting driving state node S1 of the mobile tool is taken as the current driving state node, and S1 is taken as the target driving state node. The state transition space of S1 is determined to be {a1, a2, a3, a4, a5}, and {a1, a2, a3, a4, a5} is taken as the state transition space of the current driving state node. A4 is selected from the state transition space {a1, a2, a3, a4, a5} as the next driving state node of the current driving state node S1, and a4 is stored; a4 is taken as the current driving state node, and a4 is taken as the target driving state node. The state transition space of a4 is determined to be {a41, a42, a43}, and {a41, a44, a45} is selected from the state transition space {a1, a2, a3, a4, a5} as the next driving state node of the current driving state node S1, and a4 is stored; a4 is taken as the current driving state node, and a4 is taken as the target driving state node. The state transition space of a4 is determined to be {a41, a42, a43}, and {a41, a44, a45} is selected from the state transition space {a1, a2, a3, a4, a5} as the next driving state node of the current driving state node S1, and a4 is stored; 42, a43} as the state transition space of the current driving state node, select a42 from {a41, a42, a43} as the next driving state node of the current driving state node a4, and store a42; take a42 as the current driving state node, and take a42 as the target driving state node, determine the state transition space of a42 {a421, a422, a423}, and take {a421, a422, a423} as the state transition space of the current driving state node, select a421 from {a421, a422, a423} as the next driving state node of the current driving state node a42, and store a421. S1, a4, a42, a421 form a state transition path (such as Fig. 9A Medium thick solid line), represented by S1>a4>a42>a421.

[0175] In some optional embodiments, determining the state transfer space of the current driving state node in step A2 specifically includes: taking all or part of the driving state nodes including the current driving state node in the state transfer space of the previous driving state node of the current driving state node as the target driving state node; determining the state transfer space corresponding to each target driving state node; and determining the union of the state transfer spaces corresponding to each target driving state node as the state transfer space of the current driving state node. Fig. 9BThis is just an exemplary description. It is assumed that a state transfer path includes 4 driving state nodes, and the starting driving state node of the mobile tool is S1. The starting driving state node S1 of the mobile tool is taken as the current driving state node, and S1 is taken as the target driving state node, and the state transition space of S1 is determined to be {a1, a2, a3, a4, a5}, and {a1, a2, a3, a4, a5} is taken as the state transition space of the current driving state node, and a4 is selected from the state transition space {a1, a2, a3, a4, a5} as the next driving state node of the current driving state node S1, and a4 is stored; a4 is taken as the current driving state node, and all the driving state nodes a1, a2, a3, a4 and a5 in the state transition space of the previous driving state node S1 of a4 are taken as the target driving state nodes, and the state transition spaces {a11, a12}, {a21}, {a31, a32}, {a41, a42, a43} and {a51, a52} (such as Fig. 9B , the state transition space of each target driving state node is represented by a dotted line), and the union of the state transition spaces of a1, a2, a3, a4 and a5 {a11, a12, a21, a31, a32, a41, a42, a43, a51, a52} is used as the state transition space of the current driving state node a4, a42 is selected from {a11, a12, a21, a31, a32, a41, a42, a43, a51, a52} as the next driving state node of the current driving state node a4, and a42 is stored; a42 is used as the current driving state node, and all the driving state nodes a11, a12, a21, a31, a32, a41, a42, a43, a51 and a52 in the state transition space of the previous driving state node a4 of a42 are used as the target driving state node. The state transition spaces of a11, a12, a21, a31, a32, a41, a42, a43, a51 and a52 are determined as the union of {a111}, {}, {a211, a212}, {a311}, {a411, a421, a422, a423, a424}, {}, {a521}. , a411, a421, a422, a423, a424, a521} as the state transition space of the current driving state node a42, select a421 from {a111, a211, a212, a311, a411, a421, a422, a423, a424, a521} as the next driving state node of the current driving state node a42, and store a421. S1, a4, a42, a421 form a state transition path (such as Fig. 9BThe thick solid line shown is expressed by S1>a4>a42>a421.

[0176] In some optional embodiments, determining the state transition space corresponding to each target driving state node specifically includes: querying the state transition space corresponding to the target driving state node from a preset state transition library.

[0177] In some optional embodiments, the target driving state node is matched with the driving state nodes in the state transfer library. If there is a driving state node consistent with the target driving state node, the state transfer space corresponding to the driving state node is used as the state transfer space corresponding to the target driving state node; if there is no driving state node consistent with the target driving state node in the state transfer library, a driving state node that is relatively similar to the target driving state node is determined from the state transfer library, and the state transfer space of the driving state node is determined as the state transfer space corresponding to the target driving state node. In some optional embodiments, a driving state node that is relatively similar to the target driving state node can be searched from the state transfer library by using algorithms such as kd tree, ball-tree or octree.

[0178] In some optional embodiments, in step A2, a Monte Carlo Tree Search (MCTS) method may be used to search for the next driving state node of the current driving state node in the state transition space of the current driving state node.

[0179] The state transition library may be a pre-set state transition library corresponding to the mobile tool, and the state transition library may be pre-constructed according to the driving trajectory of the mobile tool or other mobile tools of the same type.

[0180] In some optional embodiments, the state transition library can be obtained in advance through the following steps: acquiring multiple driving trajectories corresponding to the mobile tool; for each driving trajectory, sampling the trajectory points in the driving trajectory to obtain a waypoint sequence corresponding to the driving trajectory; for each waypoint sequence, converting the waypoints in the waypoint sequence into corresponding driving state nodes in turn to obtain a state transition sequence corresponding to the waypoint sequence; according to each state transition sequence, obtaining a state transition space corresponding to each driving state node in the state transition sequence; and determining the set of state transition spaces corresponding to each driving state node as the state transition library corresponding to the mobile tool.

[0181] In some optional embodiments, the waypoint includes location information and driving status information of the mobile tool, and the driving status node corresponding to the waypoint can be obtained by selecting the driving parameters included in the driving status node from the driving status information of the waypoint.

[0182] In the above-mentioned embodiment, on the one hand, since a state transition library is pre-set, in the process of constructing a state transition path, the state transition space of each target driving state node can be obtained by directly querying the state transition library, which can improve the speed of determining the state transition space of each driving state node, thereby improving the speed and efficiency of state transition path construction as a whole. On the other hand, since the state transition library is pre-constructed according to the driving trajectory of the mobile tool, it can be ensured that the transfer between the driving state nodes in the state transition library is physically feasible and conforms to the dynamic model of the mobile tool, so it can be ensured that the constructed state transition path is physically feasible, and the mobile tool can transfer from the previous driving state node of the state transition path to the next driving state node along the state transition path while conforming to the dynamic model.

[0183] In some optional embodiments, the state transition space corresponding to each target driving state node is determined, and the specific implementation is as follows:

[0184] For each target driving state node, the following steps are performed: for each driving parameter of the target driving state node, the target value of the driving parameter is determined, and the current value and the target value of the driving parameter are discretized to obtain a discrete point sequence; the discrete point sequences corresponding to the driving parameters of the target driving state node are combined to obtain multiple driving state nodes, and the multiple driving state nodes constitute the state transition space of the target driving state node. In some optional embodiments, the target value of the driving parameter of the target driving state node can be a preset value, or it can be determined according to the environmental information of the current driving of the mobile tool, or it can be determined according to the attribute parameters of the mobile tool itself. For example, if the driving parameter is the speed of the mobile tool, the target value corresponding to the speed can be the speed limit value of the lane where the mobile tool is currently located; if the driving parameter is the steering wheel angle of the mobile tool, the target value corresponding to the steering wheel angle can be the maximum angle or minimum angle of the steering wheel angle; if the driving parameter is the box angle of the mobile tool, the target value of the box angle can be the minimum value or maximum value of the box angle of the mobile tool. Those skilled in the art can flexibly set the target value of each driving parameter according to different driving parameters, and this application does not make strict restrictions. Since the variables of the driving parameters of the mobile tool are quantities that can change continuously, there are infinite possible states. Through the above-mentioned embodiment, each driving parameter can be discretized to obtain a limited number of discrete points. Therefore, the state transition space constructed according to the discrete points of each driving parameter of the driving state node is a bounded search space, which can improve the search speed of the state transition space.

[0185] Assume that each driving state node of the mobile tool contains three driving parameters, which are represented by v, θ, It means that the current value of v and the target value are discretized to obtain the first discrete point sequence [v1,v2,…,v m ]; discretize the current value and target value of θ to obtain a second discrete point sequence [θ1, θ2, …, θ n ];Will The current value and target value of are discretized to obtain the third discrete point sequence containing k discrete points The discrete points in the first discrete point sequence, the second discrete point sequence and the third discrete point sequence are combined to obtain m×n×k parameter combinations, each parameter combination represents a driving parameter combination of a driving state node, that is, m×n×k driving state nodes are obtained, and the m×n×k driving state nodes constitute the state transition space of the target driving state node. The aforementioned m, n, and k are all natural numbers preset to be greater than or equal to 1. In some optional embodiments, the values ​​of the N discrete points obtained by discretizing the current value and the target value of the driving parameter are arithmetic difference values.

[0186] In some optional embodiments, in the process of constructing each state transition path, the following step A5 is further performed after step A4, such as Fig. 9C As shown, where:

[0187] Step A5: setting a first evaluation value for indicating the quality of the waypoint sequence for the waypoint sequence corresponding to the state transition path constructed in step A4.

[0188] In some optional embodiments, taking the first evaluation value as a score as an example, the first evaluation value of the waypoint sequence can be obtained by weighted summing any one or more of the following parameters: parameter 1, the offset distance between the waypoint sequence and the center line of the lane where the mobile tool is located (the offset distance can be, for example, the average distance between each waypoint in the waypoint sequence and the center line, or it can also be the maximum distance between each waypoint in the waypoint sequence and the center line, or it can also be the minimum distance between each waypoint in the waypoint sequence and the longitudinal direction), parameter 2, the similarity between the waypoint sequence and the driving path obtained by the previous plan; parameter 3, the distance that the waypoint sequence extends in the forward direction of the mobile tool relative to the driving path obtained by the previous plan. Those skilled in the art can set the types of the above parameters according to actual needs, and this application does not strictly limit them.

[0189] In some optional embodiments, in the process of constructing each state transition path, the following step A6 is further performed after step A5, such as Fig.9D As shown, where:

[0190] Step A6: modify the node value and the number of times selected of each driving state node in the state transition path according to the first evaluation value corresponding to the waypoint sequence of the state transition path, wherein the node value is used to indicate the quality of the driving state node.

[0191] In the embodiment of the present invention, the node value of the driving state node can be expressed by a score or a level, which is not strictly limited in this application. Taking the node value expressed by a score as an example, it is assumed that after a state transition path is constructed, the road point sequence corresponding to the state transition path is evaluated to obtain the corresponding evaluation value n. The node value of the driving state node on the state transition path is modified according to the evaluation value of the road point sequence, which can be specifically implemented by but not limited to any of the following methods: in an optional embodiment, the evaluation value n is directly updated to the node value of each driving state node on the state transition path; in an optional embodiment, the evaluation value n and the node value of the driving state node are weighted averaged to obtain the new node value of the driving state node; in an optional embodiment, the evaluation value n is multiplied by a preset coefficient to obtain the node value of the driving state node. Those skilled in the art can determine how to modify the node value of the driving state node on the state transition path according to the evaluation value n according to actual needs, which is not strictly limited in this application.

[0192] In some optional embodiments, after each state transition path is constructed, the number of times each driving state node on the state transition path is selected is accumulated by 1, and the number of times each driving state node is selected is stored.

[0193] In some optional embodiments, in the process of constructing each state transition path, the following step A7 is further performed after step A5, such as Fig.9E As shown, where:

[0194] Step A7: modifying the node value and the number of times selected of each driving state node in the state transition path and the driving state node in the state transition space of each driving state node according to the first evaluation value corresponding to the waypoint sequence of the state transition path.

[0195] Assume that after a state transition path is constructed, the waypoint sequence corresponding to the state transition path is evaluated to obtain the corresponding evaluation value n. The driving state node on the state transition path is called the main node, and the state driving node in the state transition space of the previous main node of the main node is called the brother node of the main node. Fig.9F As shown, the state transition space of the initial state driving node S1 is {a1, a2, a3, a4, a5}, and the node value and the number of times selected of each driving state node are initialized to 0; suppose a state transition path is constructed as S1>a4>a42>a421, such as Figure 9GAs shown. a4, a42, a421 in the state transition path are called master nodes, the driving state nodes a1, a2, a3, a5 in the transfer state space of S1 are called brother nodes of the master node a4, the driving state nodes a21, a31, a41, a43, a51, a52 in the state transition space of the master node a4 are called brother nodes of the master node a42; the driving state nodes a211, a212, a313, a411, a422, a423, a521 in the state transition space of the master node a42 are called brother nodes of the master node a421. The node value and the number of times selected of each driving state node in the state transfer space of each driving state node in the state transfer path are modified according to the waypoint sequence evaluation value n. Specifically, it can be achieved by but not limited to the following methods: for each main node on the state transfer path, the following steps are performed: the evaluation value n and the node value of the main node are weighted averaged to obtain the new node value of the main node, and the number of times the main node is selected is accumulated by 1; for each sibling node of the main node, the similarity between the main node and the sibling node is calculated (the similarity is a value less than or equal to 1), the product of the evaluation value n and the similarity is used as the evaluation score, the evaluation score and the node value of the sibling node are weighted averaged to obtain the new node value of the sibling node, and the number of times the sibling node is currently selected is accumulated by the similarity. Figure 9H The node value and the number of times selected of each driving state node are modified according to the evaluation value of the waypoint sequence of the newly generated state transition path S1>a4>a42>a421.

[0196] In some optional embodiments, in the aforementioned step A2, the searching for the next driving state node of the current driving state node in the state transfer space of the current driving state node specifically includes: judging whether each driving state node in the state transfer space of the current driving state node is optional; and selecting the next driving state node of the current driving state node from the optional driving state nodes according to the node value and the number of times the optional driving state node is selected.

[0197] In some optional embodiments, the next driving status node of the current driving status node is selected from the optional driving status nodes according to the node value and the number of times the optional driving status nodes are selected, specifically including: for each optional driving status node, a second evaluation value of the driving status node is calculated according to the node value and the number of times the driving status node is selected, the second evaluation value is used to indicate the priority of the driving status node being selected; according to the second evaluation value of the optional driving status node, the driving status node with the highest priority is selected as the next driving status node in the current driving status node.

[0198] In some optional embodiments, judging whether each driving state node in the state transfer space of the current driving state node is selectable specifically includes: judging whether the driving state node has a collision risk, and if so, the driving state node is not selectable.

[0199] In some optional embodiments, the unselectable conditions may include but are not limited to any one or more of the following: unselectable condition 1, the driving state node has a collision risk, unselectable condition 2, the driving parameter value of the driving state node is unreasonable, unselectable condition 3, the transfer from the current driving state node to the driving state node is unreasonable. Of course, those skilled in the art can also flexibly set the unselectable conditions according to actual conditions, and the above-mentioned unselectable conditions 1 to unselectable conditions 3 are only some examples.

[0200] In some optional embodiments, the driving parameter value of the driving state node is unreasonable, which means that the value of the driving parameter exceeds the preset value range, or the value between any two or more driving parameters does not conform to the kinematic model of the mobile tool. For example, the driving speed of the driving state node reaches 300km / h.

[0201] In some optional embodiments, the transfer from the current driving state node to the driving state node is unreasonable, for example, the change between the value of a driving parameter of the driving state node and the corresponding driving parameter of the previous driving state node does not conform to the kinematic model of the mobile tool. For example, the steering wheel angle of the driving state node is 540° on the right, while the steering wheel angle of the previous driving state node of the driving state node is 540° on the left. Since the time interval between the driving state nodes is relatively close, the steering wheel angle change difference is too large in a short period of time, which obviously does not conform to the kinematic model of the mobile tool. For example, the driving speed of the driving state node is 130km / h, while the driving speed of the previous driving state node of the driving state node is 1km / h. Since the time interval between the driving state nodes is relatively close, the driving speed change is too large in a short period of time, which obviously does not conform to the kinematic model of the mobile tool.

[0202] However, how to quickly and efficiently determine whether the planned driving state transfer path is safe to avoid collision when the mobile tool travels according to the road point sequence corresponding to the driving state transfer path is a technical problem that needs to be solved urgently by those skilled in the art. One solution is that in the process of planning the state transfer path for the mobile tool, each driving state node is planned to determine whether there is a collision risk for the driving state node. If there is a collision risk for the driving state node, the driving state node is abandoned and a new driving state node is selected. Please refer to the following embodiment 5; another solution is that after a state transfer path is planned for the mobile tool, it is determined whether there is a collision risk for the state transfer path. If there is a collision risk for the state transfer path, the state transfer path is replanned for the mobile tool. Please refer to the following embodiment 6 for details; another solution is that in the process of planning the state transfer path for the mobile tool, when the rose obtains a driving state node, it is determined whether there is a collision risk for the driving state node, and after completing the planning under the state transfer path, it is determined whether there is a collision risk for the state moving path.

[0203] Embodiment 5

[0204] Embodiment 5 of the present invention provides a mobile tool collision detection method, such as Fig.10 As shown, after determining the driving state node of the state transition path of the mobile tool during the path planning process, the following steps 401 to 403 are followed to determine whether the driving state node has a collision risk:

[0205] Step 401: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0206] Step 402: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the state travel node in the occupation grid map to obtain the second grid area occupied by the mobile tool in the occupation grid map;

[0207] Step 403: Determine whether there is a collision risk at the driving state node according to the occupancy status of the first grid area and the second grid area.

[0208] In step 402, the position of the state driving node in the grid map is to convert the driving state into the coordinates of the mobile tool in space and map them to the coordinates of the grid map.

[0209] In some optional embodiments, the Fig.10The method flow shown may further include step 400. In some optional embodiments, step 400 is performed first and then step 401; in some optional embodiments, step 401 is performed first and then step 400; in some optional embodiments, step 400 and step 401 are performed simultaneously. This application has no strict requirements on the order in which step 400 and step 401 are performed. Fig. 10A It is shown that step 400 is arranged before step 401, wherein: step 400, constructs an occupation grid map with the current position of the mobile tool as the center.

[0210] In some optional embodiments, the Fig.10 The method flow shown may further include step 400A. In some optional embodiments, step 400A is performed first and then step 401; in some optional embodiments, step 401 is performed first and then step 400A; in some optional embodiments, step 400A and step 401 are performed simultaneously. The present application has no strict requirements on the order in which step 400A and step 401 are performed. Fig. 10B It is shown that step 400A is arranged before step 401, wherein: step 400A, receiving the occupancy grid map.

[0211] The specific implementation method of the above steps 400 to 403 is the same as the specific implementation principle of steps 100 to 103 in the above embodiment 1, and will not be repeated here.

[0212] Embodiment 6

[0213] Embodiment 6 of the present invention provides a mobile tool collision detection method, such as Fig.11 As shown, after receiving the state transition path of the mobile tool, the following steps 501 to 506 are followed to determine whether the state transition path has a collision risk:

[0214] Step 501: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0215] Step 502: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of a driving state node of the state transition path in the occupation grid map to obtain a second grid area occupied by the mobile tool in the occupation grid map;

[0216] Step 503, determining whether there is a collision risk at the driving state node according to the occupation status of the first grid area and the second grid area; if there is a collision risk, executing step 504, and if there is no collision risk, executing step 505;

[0217] Step 504: determine that there is a collision risk in the state transition path, and end the process;

[0218] Step 505, selecting a next driving state node from the state transition path, and executing step 502 for the next driving state node if there is a next driving state node, and executing step 506 if there is no next driving state node in the state transition path;

[0219] Step 506: Determine that the state transition path has no collision risk, and end the process.

[0220] In some optional embodiments, the Fig.11 The method flow shown may further include step 500. In some optional embodiments, step 500 is performed first and then step 501; in some optional embodiments, step 501 is performed first and then step 500; in some optional embodiments, step 500 and step 501 are performed simultaneously. The present application has no strict requirements on the order in which step 500 and step 501 are performed. Fig.11A It is shown that step 500 is arranged before step 501, wherein: step 500, constructs an occupation grid map with the current position of the mobile tool as the center.

[0221] In some optional embodiments, the Fig.11 The method flow shown may further include step 500A. In some optional embodiments, step 500A is performed first and then step 501; in some optional embodiments, step 501 is performed first and then step 500A; in some optional embodiments, step 500A and step 501 are performed simultaneously. The present application has no strict requirements on the order in which step 500A and step 501 are performed. Fig. 11B It is shown that step 500A is arranged before step 501, wherein: step 500A, receiving the occupancy grid map.

[0222] The specific implementation method of the above steps 500 to 503 is the same as the specific implementation principle of steps 100 to 103 in the above embodiment 1, and will not be repeated here.

[0223] Embodiment 7

[0224] Embodiment 7 of the present application provides a mobile tool collision detection device, and the mobile tool collision detection device can be divided into functional modules according to the mobile tool collision detection method provided in the above embodiment 1. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. The division of modules in the embodiment of the present application is schematic, which is only a logical function division, and there may be other division methods in actual implementation. The mobile tool collision detection device has the function of implementing any one of the mobile tool collision detection methods in the above embodiment 1. The function can be implemented by hardware, or it can be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0225] In an optional embodiment, the mobile tool collision detection device can be divided into the following types according to its functions: Fig.12 As shown, it includes a matching unit 11, a grid area determination unit 12 and a collision determination unit 13, wherein:

[0226] A matching unit 11, configured to determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0227] A grid area determination unit 12 is used to align the center point of the first grid area occupied by the target mobile tool in the occupation template with the position point to be detected in the constructed occupation grid map, so as to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0228] The collision determination unit 13 is used to determine whether there is a collision risk of the mobile tool at the position to be detected according to the occupation status of the first grid area and the second grid area.

[0229] In some optional embodiments, the occupied grid map used by the grid area determination unit 12 can be generated by one of the modules of the mobile tool collision detection device, or it can be received from other devices that are communicatively connected to the mobile tool collision detection device, which is not strictly limited in the present application.

[0230] In some optional embodiments, Fig.12 The device shown may further include a map construction unit 10, such as Fig. 12A As shown, wherein: a map construction unit 10 is used to construct an occupancy grid map with the current position of the mobile tool as the center.

[0231] In some optional embodiments, Fig.12 The device shown may further include a receiving unit 14, such as Fig. 12B As shown, wherein: the receiving unit 14 is used to receive the occupancy grid map.

[0232] In some optional embodiments, how the matching unit 11 specifically matches and obtains the target mobile tool occupation template, and how the mobile tool occupation template is set, can be found in the relevant content of step 101 in the first embodiment, which will not be repeated here.

[0233] In some optional embodiments, the specific implementation of the grid area determination unit 12 may refer to the contents related to step 102 in the first embodiment, which will not be repeated here.

[0234] In some optional embodiments, the specific implementation of the collision determination unit 13 may refer to the contents related to step 103 in the first embodiment, which will not be repeated here.

[0235] In some optional embodiments, the mobile tool collision detection device can be set on the mobile tool or on a cloud computer.

[0236] Embodiment 8

[0237] Embodiment eight of the present application provides a mobile tool collision detection device, which can divide the functional modules of the mobile tool path planning device according to the mobile tool collision detection method provided in the above embodiment two. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. The division of modules in the embodiments of the present application is schematic, which is only a logical function division, and there may be other division methods in actual implementation. The mobile tool collision detection device has the function of implementing any one of the mobile tool collision detection methods in the above embodiment two. This function can be implemented by hardware, or it can be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0238] In an optional embodiment, the mobile tool collision detection device can be divided into the following types according to its functions: Fig.13 As shown, it includes a first path planning unit 21 and a first collision detection unit 22, wherein:

[0239] A first path planning unit 21 is used to plan a path for the mobile tool and start the first collision detection unit 22 when a waypoint of the driving path is determined during the path planning process;

[0240] The first collision detection unit 22 is used to determine whether there is a collision risk at the waypoint according to the following steps 201 to 203: Step 201, determine a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; Step 202, align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the waypoint in the constructed occupation grid map, and obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 203, determine whether there is a collision risk of the mobile tool at the waypoint based on the occupancy of the first grid area and the second grid area.

[0241] In some optional embodiments, the occupancy grid map used by the first collision detection unit 22 can be generated by one of the modules of the mobile tool collision detection device, or can be received from other devices that are communicatively connected to the mobile tool collision detection device, which is not strictly limited in the present application.

[0242] In some optional embodiments, Fig.13 The device shown may further include a map construction unit 20, such as Fig.13A As shown, wherein: a first map construction unit 20 is used to construct an occupation grid map with the current position of the mobile tool as the center.

[0243] In some optional embodiments, Fig.13 The device shown may further include a first receiving unit 23, such as Fig. 13B As shown, wherein: the first receiving unit 23 is used to receive the occupancy grid map.

[0244] The specific implementation of the above steps 201 to 203 can refer to steps 101 to 103 in the first embodiment, which will not be repeated here.

[0245] Embodiment 9

[0246] Embodiment 9 of the present invention provides a mobile tool collision detection device, including:

[0247] The collision detection unit is used to determine whether there is a collision risk in the driving path according to the following steps 301 to 305 after receiving the driving path of the mobile tool:

[0248] Step 301: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0249] Step 302: align the center point of the first grid area occupied by the target mobile tool in the occupation template with the position of a road point of the driving path in the constructed occupation grid map, so as to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0250] Step 303: determine whether there is a collision risk for the mobile tool at the waypoint according to the occupation status of the first grid area and the second grid area; if there is a collision risk, execute step 304; if there is no collision risk, execute step 305;

[0251] Step 304: determine that there is a collision risk in the driving path, and end the process;

[0252] Step 305: Select the next waypoint from the driving path, and execute steps 302 to 305 for the waypoint.

[0253] In some optional embodiments, the collision detection unit may receive the driving path of the mobile tool from a path planning unit located on the mobile tool. The path planning unit may be, for example, a module disposed on the mobile tool that can plan a driving path for the mobile tool.

[0254] In some optional embodiments, the collision detection unit may also receive the driving path of the mobile tool from a cloud server. The cloud server is provided with a module that can plan the driving path for the mobile tool.

[0255] In some optional embodiments, in order to ensure that the driving path planned for the mobile tool is in accordance with the dynamic model of the mobile tool and is a driving path that the mobile tool can actually travel along, in the embodiments of the present invention, when planning the path for the mobile tool, multiple state transition paths can be first constructed according to the current driving state of the mobile tool, and then a target state transition path can be selected, and finally the waypoint sequence corresponding to the target state transition path is determined as the driving path of the mobile tool. Since the state transition path represents the state transition relationship of the mobile tool from one driving state to another, that is, each adjacent driving state node on the planned state transition path is transferable, which is in accordance with the dynamic model of the mobile tool, the mobile tool travels along the driving path corresponding to the target state transition path in accordance with the dynamic model, can actually travel along the driving path, and the effectiveness of the driving path is high.

[0256] However, how to quickly and efficiently determine whether the planned driving state transfer path is safe to avoid collision when the mobile tool travels according to the road point sequence corresponding to the driving state transfer path is a technical problem that needs to be solved urgently by those skilled in the art. One solution is that in the process of planning the state transfer path for the mobile tool, each driving state node is planned to determine whether there is a collision risk for the driving state node. If there is a collision risk for the driving state node, the driving state node is abandoned and a new driving state node is selected. Please refer to the following embodiment 10; another solution is that after a state transfer path is planned for the mobile tool, it is determined whether there is a collision risk for the state transfer path. If there is a collision risk for the state transfer path, the state transfer path is re-planned for the mobile tool. Please refer to the following embodiment 11 for details; another solution is that in the process of planning the state transfer path for the mobile tool, when the rose obtains a driving state node, it is determined whether there is a collision risk for the driving state node, and after completing the planning under the state transfer path, it is determined whether there is a collision risk for the state moving path.

[0257] Embodiment 10

[0258] Embodiment 10 of the present invention provides a mobile tool collision detection device, such as Fig.14 As shown, it includes a second path planning unit 31 and a second collision detection unit 32, wherein:

[0259] The second path planning unit 31 is used to trigger the second collision detection unit 32 after determining the current driving state node of the state transition path of the mobile tool during the path planning process;

[0260] The second collision detection unit 32 is used to determine whether there is a collision risk at the current driving state node according to the following steps 401 to 403: Step 401, determine a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; Step 402, align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the state driving node in the constructed occupation grid map, and obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 403, determine whether there is a collision risk at the driving state node according to the occupancy of the first grid area and the second grid area.

[0261] In some optional embodiments, the occupancy grid map used by the second collision detection unit 32 can be generated by one of the modules of the mobile tool collision detection device, or can be received from other devices that are communicatively connected to the mobile tool collision detection device, which is not strictly limited in the present application.

[0262] In some optional embodiments, the second path planning unit 31 constructs a plurality of state transition paths according to the current driving state of the mobile tool, which can be specifically implemented through the aforementioned steps A1 to A4, which will not be described in detail here.

[0263] In some optional embodiments, after constructing each state transition path, the second path planning unit 31 may further perform the following step A5, wherein: step A5, setting a first evaluation value for indicating the quality of the waypoint sequence corresponding to the state transition path constructed in step A4.

[0264] In some optional embodiments, the second path planning unit 31 may further execute step A6 after executing step A5, wherein: step A6, modifying the node value and the number of times selected of each driving state node in the state transition path according to the first evaluation value corresponding to the waypoint sequence of the state transition path, the node value is used to indicate the quality of the driving state node.

[0265] In some optional embodiments, the second path planning unit 31 may further execute step A7 after executing step A5, wherein: step A7, modifies the node value and the number of times selected of each driving state node in the state transition path and the driving state node in the state transition space of each driving state node according to the first evaluation value corresponding to the waypoint sequence of the state transition path.

[0266] Embodiment 11

[0267] The eleventh embodiment of the present invention provides a mobile tool collision detection device, the device comprising a collision detection unit, wherein:

[0268] The collision detection unit is used to determine whether there is a collision risk in the state transition path according to the following steps 501 to 506 after receiving the state transition path of the mobile tool:

[0269] Step 501: Determine a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates;

[0270] Step 502: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of a driving state node of the state transition path in the constructed occupation grid map to obtain a second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center;

[0271] Step 503, determining whether there is a collision risk at the driving state node according to the occupation status of the first grid area and the second grid area; if there is a collision risk, executing step 504, and if there is no collision risk, executing step 505;

[0272] Step 504: determine that there is a collision risk in the state transition path, and end the process;

[0273] Step 505, selecting a next driving state node from the state transition path, and executing step 502 for the driving state node if there is a next driving state node, and executing step 506 if there is no next driving state node in the state transition path;

[0274] Step 506: Determine that the state transition path has no collision risk, and end the process.

[0275] Embodiment 12

[0276] In some optional embodiments, Embodiment 12 of the present invention provides a processing device, including a processor and a memory. The processor is connected to the memory (such as interconnected via a bus). Optionally, the processing device may also include a transceiver, which connects the processor and the memory, and the transceiver is used to receive / send data. The processor can perform the operations of any one of the mobile tool collision detection implementation schemes and various feasible implementation schemes provided in the aforementioned Embodiments 1, 2, 3, 5, and 6, and / or other operations described in the embodiments of the present application.

[0277] For example, in some optional embodiments, the processor is used to execute the following steps 101 to 103, wherein: step 101, determining a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupancy template; step 102, aligning the center point of the first grid area occupied by the mobile tool in the target mobile tool occupancy template with the position point to be detected in the constructed occupancy grid map to obtain the second grid area occupied by the mobile tool in the occupancy grid map, wherein the occupancy grid map is an occupancy grid map constructed with the current position of the mobile tool as the center; step 103, determining whether there is a collision risk of the mobile tool at the position point to be detected based on the occupancy of the first grid area and the second grid area.

[0278] In some optional embodiments, the processor is used to determine the waypoints of the driving path during the path planning process, and judge whether there is a collision risk at the waypoints according to the following steps 201 to 203: Step 201, determine a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; Step 202, align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the waypoint in the constructed occupation grid map, and obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 203, determine whether there is a collision risk for the mobile tool at the waypoint based on the occupancy of the first grid area and the second grid area.

[0279] In some optional embodiments, the processor is used to determine whether there is a collision risk on the driving path after receiving the driving path of the mobile tool according to the following steps 301 to 305: Step 301, determine a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; Step 302, align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of a waypoint of the driving path in the constructed occupation grid map, and obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 303, determine whether there is a collision risk on the mobile tool at the waypoint according to the occupation status of the first grid area and the second grid area; if there is a collision risk, execute step 304, if there is no collision risk, execute step 305; Step 304, determine that there is a collision risk on the driving path, and end the process; Step 305, select the next waypoint from the driving path, and execute steps 302 to 305 for the waypoint.

[0280] In some optional embodiments, the processor is used to determine the driving state node of the state transfer path of the mobile tool during the path planning process, and then determine whether there is a collision risk at the driving state node according to the following steps 401 to 403: Step 401, determine a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupancy template; Step 402, align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupancy template with the position of the state driving node in the constructed occupancy grid map to obtain the second grid area occupied by the mobile tool in the occupancy grid map; wherein the occupancy grid map is an occupancy grid map constructed with the current position of the mobile tool as the center; Step 403, determine whether there is a collision risk at the driving state node according to the occupancy status of the first grid area and the second grid area.

[0281] In some optional embodiments, the processor is used to determine whether there is a collision risk in the state transition path after receiving the state transition path of the mobile tool according to the following steps 501 to 506: Step 501, determine a target mobile tool occupation template that matches the posture of the mobile tool from a preset mobile tool occupation template; Step 502, align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of a driving state node of the state transition path in the constructed occupation grid map, and obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is based on the current state of the mobile tool. An occupied grid map is constructed with the position as the center; step 503, determining whether the driving state node has a collision risk according to the occupancy of the first grid area and the second grid area; if there is a collision risk, execute step 504, and if there is no collision risk, execute step 505; step 504, determining whether the state transition path has a collision risk, and ending the process; step 505, selecting the next driving state node from the state transition path, if there is a next driving state node, execute step 502 for the driving state node, if there is no next driving state node in the state transition path, execute step 506; step 506, determining that the state transition path has no collision risk, and ending the process.

[0282] Embodiment 13

[0283] In some optional embodiments, the present application also provides a mobile tool collision detection device, including a non-volatile storage medium and a central processing unit, the non-volatile storage medium stores an executable program, the central processing unit is connected to the non-volatile storage medium, and executes the executable program to implement any one of the mobile tool collision detection methods provided in Example 1, Example 2, Example 3, Example 5 and Example 6 of the present application.

[0284] Embodiment 14

[0285] In some optional embodiments, embodiment fourteen of the present invention provides a computer-readable storage medium, including a program or instruction. When the program or instruction is run on a computer, any one of the mobile tool collision detection methods provided in embodiment one, embodiment two, embodiment three, embodiment five and embodiment six is ​​implemented.

[0286] Embodiment 15

[0287] In some optional embodiments, embodiment 15 of the present invention provides a computer program product comprising instructions, which includes computer execution instructions. When the computer program product runs on a computer, the computer executes any one of the mobile tool collision detection methods provided in embodiment 1, embodiment 2, embodiment 3, embodiment 5 and embodiment 6.

[0288] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using a software program, it can appear in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0289] Embodiment 16

[0290] In some optional embodiments, embodiment sixteen of the present invention provides a chip system, including a processor, the processor is coupled to a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, any one of the mobile tool collision detection methods provided in embodiment one, embodiment two, embodiment three, embodiment five and embodiment six is ​​implemented.

[0291] Embodiment 17

[0292] In some optional embodiments, the mobile tool collision detection methods provided in Example 1, Example 2, Example 3, Example 5 and Example 6 can be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or encoded on other non-transitory media or products.

[0293] Fig.15 Schematically illustrates a conceptual partial view of an example computer program product arranged according to at least some of the embodiments presented here, the example computer program product includes a computer program for executing a computer process on a computing device. In one embodiment, the example computer program product is provided using a signal-bearing medium. The signal-bearing medium may include one or more program instructions, which when run by one or more processors can provide any one of the mobile tool collision detection methods provided in the above embodiments one, two, three, five and six. For example, one or more features in any of the aforementioned mobile tool collision detection methods can be undertaken by one or more instructions associated with the signal-bearing medium. In some examples, the signal-bearing medium may include a computer-readable medium, such as, but not limited to, a hard drive, a compact disk (CD), a digital video disc (DVD), a digital tape, a memory, a ROM or a RAM, etc. In some embodiments, the signal-bearing medium may include a computer-recordable medium, such as, but not limited to, a memory, a read / write (R / W) CD, a R / W DVD, etc. In some embodiments, the signal-bearing medium may include a communication medium, such as, but not limited to, a digital and / or analog communication medium (e.g., a fiber optic cable, a waveguide, a wired communication link, a wireless communication link, etc.).

[0294] Embodiment 18

[0295] In some optional embodiments, embodiment eighteen of the present invention provides a circuit system, which includes a processing circuit, and the processing circuit is configured to execute any one of the mobile tool collision detection methods provided in embodiment one, embodiment two, embodiment three, embodiment five and embodiment six.

[0296] Embodiment 19

[0297] In some optional embodiments, embodiment 19 of the present invention provides a computer system comprising a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement a mobile tool collision detection method as described in any one of embodiments 1, 2, 3, 5 and 6.

[0298] Embodiment 20

[0299] like Fig.16 As shown in FIG. 1 , an exemplary mobile tool system 100 provided by an embodiment of the present invention is provided. The mobile tool system 100 is mounted on a mobile tool, and the mobile tool can be controlled by the mobile tool system 100 to achieve unmanned driving or nearly unmanned driving. The structure of the mobile tool system can be as follows: Fig.16 As shown, it includes an external environment sensor 110 , a positioning sensor 120 , an internal sensor 130 , a map database 140 , a navigation system 150 , an actuator 160 , and a computer system 170 .

[0300] In some optional embodiments, the external environment sensor 110 is a detection device for detecting the surrounding environment information of the mobile tool, for example, it may include but is not limited to at least one of a camera, a radar (Radar) and a laser radar (LIDAR). The camera is a shooting device for shooting the surrounding environment of the mobile tool. The camera can be set at the front end, side, etc. of the mobile tool, and the camera can be a single-lens camera or a binocular camera. The camera transmits the collected data to the computer system 170. The radar uses radio waves to detect objects around the mobile tool. The radio waves are, for example, millimeter waves. The radar sends radio waves around the mobile tool and receives radio waves reflected by the object to detect the object. The radar can, for example, output the distance or direction of the object as object information to the computer system 170. The laser radar uses light to detect objects outside the mobile tool. The laser radar sends light around the mobile tool and receives light reflected by the object, thereby measuring the distance to the reflection point and detecting the object. The laser radar can, for example, output the distance or direction of the object as object information to the computer system 170.

[0301] In some optional embodiments, the positioning sensor 120 may include one or more positioning modules, such as one or more of a GPS (Global Positioning System) positioning module, a Beidou positioning system, an IMU (Inertial Measurement Unit) positioning module, a visual-IMU odometer obtained by combining a camera and an IMU, a combined navigation module obtained by combining a GNSS (Global Navigation Satellite System) and an IMU, etc. The positioning sensor 120 outputs the positioning information for positioning the mobile tool to the computer system 170.

[0302] In some optional embodiments, the internal sensor 130 is a detector that detects information corresponding to the driving state of the mobile tool. The internal sensor 130 may include, for example, at least one of an IMU, a speed sensor, an acceleration sensor, a steering wheel sensor, and a steering gear sensor. In some optional embodiments, the internal sensor 130 may also include at least one of an accelerator pedal sensor, a brake pedal sensor, and a yaw rate sensor. The speed sensor is a detector that detects the speed of the mobile tool, and the speed sensor transmits the speed information of the mobile tool to the computer system 170. The acceleration sensor is a detector that detects the acceleration of the mobile tool, and the acceleration sensor transmits information including the acceleration of the mobile tool to the computer system 170. The steering wheel sensor is a detector that detects the rotation state of the steering wheel, and the detection value of the rotation state is, for example, a steering wheel angle, a steering wheel angular velocity, a steering wheel rotation angular acceleration, etc., and transmits the steering wheel angle, the steering wheel angular velocity, and the steering wheel rotation angular acceleration of the mobile tool to the computer system 170. The steering gear sensor is a detector that detects the steering gear angle, and transmits the steering gear angle to the computer system 170. The yaw rate sensor is a detector that detects the yaw rate (rotational angular velocity) of the mobile tool around the vertical axis of the center of gravity, and a gyroscope sensor can be used, for example. The yaw rate sensor transmits yaw rate information including the yaw rate of the mobile tool to the computer system 170. The accelerator pedal sensor is, for example, a detector that detects the amount of accelerator pedal depression. The accelerator pedal sensor is, for example, disposed on the shaft portion of the accelerator pedal of the mobile tool. The accelerator pedal sensor transmits operation information corresponding to the amount of accelerator pedal depression to the computer system 170. The brake pedal sensor is, for example, a detector that detects the amount of brake pedal depression. The brake pedal sensor is, for example, disposed on the shaft portion of the brake pedal. The brake pedal sensor can also detect the operating force of the brake pedal (the force applied to the brake pedal, the pressure of the master cylinder, etc.). The brake pedal sensor transmits operation information corresponding to the amount of brake pedal depression or the operating force to the computer system 170.

[0303] In some optional embodiments, the map database 140 is a database with high-precision map information. The map database 140 is, for example, formed in a HDD (Hard Disk Drive) mounted on a mobile tool. The high-precision map information includes, for example, lane line information, location information, road shape information, traffic light information, traffic sign information, intersection and branch intersection location information, etc.

[0304] In some optional embodiments, the navigation system 150 calculates the navigation route of the mobile tool based on the location information of the mobile tool positioned by the positioning sensor 120 and the map information of the map database 140. The navigation system 150, for example, transmits the information of the target navigation route of the mobile tool to the computer system 170. In addition, the navigation system 150 can be a local system set on the mobile tool, or a cloud system that can communicate with the mobile tool.

[0305] In some optional embodiments, the actuator 160 is a device for executing the driving control of the mobile tool, and the actuator 160 includes at least a throttle actuator, a brake actuator, and a steering wheel actuator. The throttle actuator controls the amount of air supplied to the engine (throttle opening) according to the control signal transmitted by the computer system 170, thereby controlling the driving force of the mobile tool. Of course, if the mobile tool is a hybrid tool or an electric tool, the mobile tool may not include a throttle actuator, and the control signal from the computer system 170 is input to the motor as a power source to control the driving force. The brake actuator controls the brake system according to the control signal from the computer system 170, thereby controlling the braking force applied to the wheels of the mobile tool. As the brake system, for example, a hydraulic brake system can be used. The steering wheel actuator controls the drive of the auxiliary motor that controls the steering torque in the electric power steering system according to the control signal from the computer system 170. Thus, the steering wheel actuator controls the steering torque (steering torque) of the mobile tool.

[0306] In some optional embodiments, the computer system 170 may be an electronic control unit having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), etc. In the computer system 170, various controls are performed by loading a program stored in the ROM into the RAM and executing it by the CPU. The computer system 170 may also be composed of a plurality of electronic control units.

[0307] In some optional embodiments, the computer system 170 may include a memory and one or more processors in communication with the memory; the memory stores instructions (e.g., program logic) executable by the one or more processors, and the instructions are executed by the one or more processors to enable the one or more processors to implement various functions, such as positioning fusion function, perception function, driving state determination function, path planning function (i.e., decision-making function), and driving control function. In some optional embodiments, the memory may also contain additional instructions, including instructions for sending data to, receiving data from, interacting with, and / or controlling one or more of the external environment sensor 110, the positioning sensor 120, the internal sensor 130, the map database 140, the navigation system 150, the actuator 160, and other peripheral devices.

[0308] In some optional embodiments, the computer system 170 may also be a plurality of computing devices that control individual components or subsystems of the mobile tool 100 in a distributed manner.

[0309] In some optional embodiments, the perception module 170B identifies the external conditions of the mobile tool based on the detection results of the external environment sensor 110, which may include, for example, the position of the white line relative to the driving lane of the mobile tool or the position of the center of the lane, the road width, the shape of the road, etc. In addition, the external conditions may also be the conditions of objects such as obstacles around the mobile tool, which may include, for example, information distinguishing between fixed obstacles and mobile obstacles, the position of obstacles relative to the mobile tool, the moving direction of obstacles relative to the mobile tool, the relative speed of obstacles relative to the mobile tool, etc. The driving state determination module 170C identifies the driving state of the mobile tool based on the detection results of the internal sensor 130, which may include, for example, speed, acceleration, steering wheel angle, steering wheel rotation angular velocity, steering wheel rotation cross acceleration, hanging box angle, etc.

[0310] In some optional embodiments, the functions are divided into Fig.17 As shown, the computer system 170 may include a positioning fusion module 170A, a perception module 170B, a driving state determination module 170C, a path planning module 170D, and a driving control module 170E. The path planning module 170D plans a driving path for the mobile tool. In some optional embodiments, Fig.17 The modules included in the computing system 170 shown can all be deployed on a mobile tool. In some optional embodiments, Fig.17 All modules included in the computer system 170 are deployed on a cloud server, and the modules set on the cloud server communicate with related devices or modules on the mobile tool through existing wireless communication methods. Fig.17Some modules in the computer system 170 shown are deployed on the mobile tool, and other modules are deployed on the cloud server. The modules deployed on the cloud server and the modules deployed on the mobile tool can communicate through existing wireless communication mechanisms. For example, the positioning fusion module 170A, the perception module 170B, the driving state determination module 170C and the driving control module 170E are deployed on the mobile tool, and the path planning module 170D is deployed on the cloud server. Those skilled in the art can flexibly set the location where each module in the computer system 170 is deployed according to actual needs, and this application does not make strict restrictions.

[0311] like Fig.17 The path planning module 170D shown, in some optional embodiments, when the path planning module 170D plans a driving path for a mobile tool, each time a waypoint is planned, the path planning module 170D executes the mobile tool collision detection method provided in the aforementioned embodiment 2 to determine whether there is a collision risk at the waypoint. If there is no collision risk at the waypoint, the path planning module 170D continues to plan the next waypoint of the driving path. If there is a collision risk at the waypoint, the path planning module 170D abandons the waypoint and re-plans a new waypoint.

[0312] like Fig.17 The path planning module 170D shown, in some optional embodiments, after planning a driving path for the mobile tool, the path planning module 170D executes the mobile tool collision detection method provided in the aforementioned embodiment three to determine whether there is a collision risk on the driving path. If there is no collision risk on the driving path, the driving path is sent to the driving control module 170E. If there is a collision risk on the driving path, the driving path is abandoned and a new driving path is replanned.

[0313] like Fig.17The path planning module 170D shown, in some optional embodiments, when planning a path for a mobile tool, the path planning module 170D can first construct multiple state transition paths according to the current driving state of the mobile tool, and then select a target state transition path, and finally determine the waypoint sequence corresponding to the target state transition path as the driving path of the mobile tool. In some optional embodiments, after the path planning module 170D determines the driving state node of the state transition path of the mobile tool during the path planning process, it executes the mobile tool collision detection method provided in the aforementioned embodiment 5 to determine whether the driving state node has a collision risk, if the driving state node has a collision risk, the driving state node is abandoned and a new driving state node is replanned, if the driving state node does not have a collision risk, the next driving state node is continued to be planned. In an optional embodiment, after planning a state transition path, the path planning module 170D executes the mobile tool collision detection method provided in the aforementioned embodiment 6 to determine whether the state transition path has a collision risk, if the state transition path has a collision risk, the state transition path is abandoned, if the state transition path does not have a collision risk, the state transition path is retained.

[0314] In some optional embodiments, the functions are divided into Fig.18 As shown, the computer system 170 may include a positioning fusion module 170A, a perception module 170B, a driving state determination module 170C, a path planning module 170D, a driving control module 170E and a collision detection module 170F. The path planning module 170D plans a driving path for the mobile tool. In some optional embodiments, Fig.18 The modules included in the computing system 170 shown can all be deployed on a mobile tool. In some optional embodiments, Fig.18 All modules included in the computer system 170 are deployed on a cloud server, and the modules deployed on the cloud server communicate with related devices or modules on the mobile tool through existing wireless communication methods. Fig.18Some modules in the computer system 170 shown are deployed on the mobile tool, and other modules are deployed on the cloud server. The modules deployed on the cloud server and the modules deployed on the mobile tool can communicate through the existing wireless communication mechanism. For example: the positioning fusion module 170A, the perception module 170B, the driving state determination module 170C and the driving control module 170E are deployed on the mobile tool, and the path planning module 170D and the collision detection module 170F are deployed on the cloud server; another example: the positioning fusion module 170A, the perception module 170B, the driving state determination module 170C and the driving control module 170E, the path planning module 170D are set on the mobile tool, and the collision detection module 170F is deployed on the cloud server. Those skilled in the art can flexibly set the location where each module in the computer system 170 is deployed according to actual needs, and this application does not make strict restrictions.

[0315] like Fig.18 In the path planning module 170D shown, in some optional embodiments, when the path planning module 170D plans a driving path for the mobile tool, each time a waypoint is planned, the waypoint is sent to the collision detection module 170F; the collision detection module 170F executes the mobile tool collision detection method provided in the aforementioned embodiment 2 to determine whether the waypoint has a collision risk, and sends the collision risk result to the path planning module 170D. If the waypoint does not have a collision risk, the path planning module 170D continues to plan the next waypoint of the driving path; if the waypoint has a collision risk, the path planning module 170D abandons the waypoint and replans a new waypoint.

[0316] like Fig.18 The path planning module 170D shown, in some optional embodiments, after planning a driving path for the mobile tool, the path planning module 170D sends the driving path to the collision detection module 170F. The collision detection module 170F executes the mobile tool collision detection method provided in the aforementioned embodiment 3, determines whether there is a collision risk in the driving path, and sends the collision risk result to the path planning module 170D. If there is no collision risk in the driving path, the path planning module 170D sends the driving path to the driving control module 170E. If there is a collision risk in the driving path, the path planning module 170D abandons the driving path and replans a new driving path.

[0317] like Fig.18The path planning module 170D shown, in some optional embodiments, when planning a path for a mobile tool, the path planning module 170D can first construct multiple state transition paths according to the current driving state of the mobile tool, and then select a target state transition path, and finally determine the waypoint sequence corresponding to the target state transition path as the driving path of the mobile tool. In some optional embodiments, after the path planning module 170D determines the driving state node of the state transition path of the mobile tool during the path planning process, the driving state node is sent to the collision detection module 170F. The collision detection module 170F executes the mobile tool collision detection method provided in the aforementioned embodiment 5 to determine whether the driving state node has a collision risk, and sends the collision risk result to the path planning module 170D. If the driving state node has a collision risk, the path planning module 170D abandons the driving state node and replans a new driving state node. If the driving state node does not have a collision risk, the path planning module 170D continues to plan the next driving state node.

[0318] like Fig.18 In the path planning module 170D shown, in some optional embodiments, after planning a state transition path, the path planning module 170D sends the state transition path to the collision detection module 170F, and the collision detection module 170F executes the mobile tool collision detection method provided in the aforementioned embodiment 6 to determine whether there is a collision risk in the state transition path, and sends the collision risk result to the path planning module 170D. If there is a collision risk in the state transition path, the path planning module 170D abandons the state transition path, and if there is no collision risk in the state transition path, the path planning module 170D retains the state transition path.

[0319] In some optional embodiments, the computer system 170 may also be Fig.19In the structure shown, the computer system 170 is set on the mobile tool, and the computer system 170 may include a processor, and the processor is coupled to the system bus. The processor may be one or more processors, wherein each processor may include one or more processor cores. Optionally, the computer server may also include a display adapter, which may drive a display, and the display is coupled to the system bus. The system bus is coupled to the input and output (I / O) bus through a bus bridge. The I / O interface is coupled to the I / O bus. The I / O interface communicates with a variety of I / O devices, such as input devices (such as: keyboard, mouse, touch screen, etc.), multimedia disks, such as CD-ROM, multimedia interface, etc. Transceiver (can send and / or receive radio communication signals), camera and external USB interface. Optionally, the interface connected to the I / O interface may be a USB interface. The processor may be any conventional processor, including a reduced instruction set computing ("RISC") processor, a complex instruction set computing ("CISC") processor, or a combination of the above. Optionally, the processor may be a dedicated device such as an application-specific integrated circuit ("ASIC"). The computer system 170 may communicate with the software deployment server via a network interface. The network interface is a hardware network interface, such as a network card. The network can be an external network, such as the Internet, or an internal network, such as Ethernet or a virtual private network (VPN). Optionally, the network can also be a wireless network, such as a WiFi network, a cellular network, etc. The hard disk drive interface is coupled to the system bus. The hardware drive interface is connected to the hard disk drive. The system memory is coupled to the system bus. The data running in the system memory may include the operating system and application programs of the computer server. The operating system includes a shell and a kernel. The shell is an interface between the user and the kernel of the operating system. The shell is the outermost layer of the operating system. The shell manages the interaction between the user and the operating system: waiting for the user's input, interpreting the user's input to the operating system, and processing various operating system output results. The kernel consists of those parts of the operating system used to manage memory, files, peripherals, and system resources. Directly interacting with the hardware, the operating system kernel usually runs processes and provides communication between processes, provides CPU time slice management, interrupts, memory management, IO management, etc. The application program may include related programs of any path planning method provided in Example 1 and other related programs. The application program may also exist on the system of the software deployment server. In one embodiment, when an application needs to be executed, the computer system 170 may download the application from a software deployment server.

[0320] In some optional embodiments, the computer system 170 may also receive information from other computer systems or transfer information to other computer systems. Alternatively, the data received from the mobile tool may be transferred to another computer system, which may process the data. The data from the computer system 170 may be transmitted to a cloud computer system via a network, which may further process the data, and the cloud computer system may send the processing results to the computer system 170 via the network. Fig. 20As shown. The network and intermediate nodes may include various configurations and protocols, including the Internet, the World Wide Web, an intranet, a virtual private network, a wide area network, a local area network, a private network using one or more companies' proprietary communication protocols, Ethernet, WiFi, and HTTP (Hyper Text Transfer Protocol) and various combinations of the foregoing. Such communication may be performed by any device capable of transmitting data to and from other computer systems, such as a modem and a wireless interface. In one example, a cloud computer system may include a computer server, such as a load balancing server cluster. In order to receive, process and transmit data from computer system 170, the cloud computer system exchanges information with different nodes of the network. The cloud computer system may have a configuration similar to that of computer system 170, and have a processor, memory, instructions, and data. The cloud computer system may receive data (such as the current location of the mobile tool, the current driving status, etc.) from a computer system 170 on a mobile tool via a network such as a wireless communication network. For example, in the process of planning a driving path for a mobile tool, the computer system 170 sends the waypoint to the cloud computer system each time a waypoint is obtained in the planning; the cloud computer system executes the mobile tool collision detection method provided in the aforementioned embodiment 2 to determine whether the waypoint has a collision risk, and sends the collision risk result to the computer system 170. If the waypoint does not have a collision risk, the computer system 170 continues to plan the next waypoint of the driving path; if the waypoint has a collision risk, the computer system 170 abandons the waypoint and replans a new waypoint. For another example, after the computer system 170 plans a driving path for the mobile tool, it sends the driving path to the cloud computer system. The cloud computer system executes the mobile tool collision detection method provided in the aforementioned embodiment 3 to determine whether the driving path has a collision risk, and sends the collision risk result to the computer system 170. If the driving path does not have a collision risk, the computer system 170 sends the driving path to the driving control module 170E; if the driving path has a collision risk, the computer system 170 abandons the driving path and replans a new driving path. For example, when the computer system 170 is planning a path for a mobile tool, it can first construct multiple state transition paths according to the current driving state of the mobile tool, then select a target state transition path, and finally determine the waypoint sequence corresponding to the target state transition path as the driving path of the mobile tool.In some optional embodiments, after the computer system 170 determines the driving state node of the state transition path of the mobile tool during the path planning process, the driving state node is sent to the cloud computer system, and the cloud computer system executes the mobile tool collision detection method provided in the aforementioned embodiment 5 to determine whether the driving state node has a collision risk, and sends the collision risk result to the computer system 170; if the driving state node has a collision risk, the computer system 170 abandons the driving state node and replans a new driving state node, and if the driving state node does not have a collision risk, the computer system 170 continues to plan the next driving state node. For another example, after the computer system 170 plans a state transition path, it sends the state transition path to the cloud computer system, and the cloud computer system executes the mobile tool collision detection method provided in the aforementioned embodiment 6 to determine whether the state transition path has a collision risk, and sends the collision risk result to the computer system 170. If the state transition path has a collision risk, the computer system 170 abandons the state transition path, and if the state transition path does not have a collision risk, the computer system 170 retains the state transition path.

[0321] The basic principles of the present invention are described above in conjunction with specific embodiments. However, it should be pointed out that a person skilled in the art can understand that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including a processor, a storage medium, etc.) or a network of computing devices in the form of hardware firmware, software, or a combination thereof. This can be achieved by a person skilled in the art using their basic programming skills after reading the description of the present invention.

[0322] A person of ordinary skill in the art can understand that all or part of the steps carried out in the method of the above-mentioned embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0323] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0324] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0325] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0326] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0327] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0328] Although the above embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the above embodiments and all changes and modifications that fall within the scope of the present invention.

[0329] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A mobile tool collision detection method, characterized in that: include: Step 101: determining a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates, wherein the mobile tool occupation template is a grid map pre-constructed with the mobile tool as the center, and a grid area occupied by the mobile tool is pre-marked in the grid map according to the size, shape and posture of the mobile tool; Step 102: align the center point of the first grid area occupied by the target mobile tool in the occupation template with the position point to be detected in the constructed occupation grid map, to obtain the second grid area occupied by the mobile tool in the occupation grid map, wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 103: Determine whether there is a collision risk of the mobile tool at the position to be detected according to the occupation status of the first grid area and the second grid area.

2. The method according to claim 1, characterized in that In step 103, determining whether there is a collision risk of the mobile tool at the position to be detected according to the occupation status of the first grid area and the second grid area specifically includes: If a preset number of grids in the second grid area are marked as being occupied by obstacles, it is determined that there is a risk of collision of the mobile tool at the position to be detected.

3. The method according to claim 1, characterized in that: In step 103, determining whether there is a collision risk of the mobile tool at the position to be detected according to the occupation status of the first grid area and the second grid area specifically includes: According to the occupancy of the first grid area and the second grid area, a collision assessment value for characterizing the collision probability is calculated, and according to the collision assessment value, it is determined whether the mobile tool has a collision risk at the position to be detected.

4. The method according to claim 1, characterized in that: The values ​​of each grid in the mobile tool occupation template are set as binary values ​​according to the preset occupation rules; the values ​​of the grids in the occupation grid map are obtained according to the occupation rules; In the step 103, whether there is a risk of collision of the mobile tool at the position to be detected is determined based on the occupancy status of the first grid area and the second grid area, specifically including: performing binary operations on the values ​​of the grids in the first grid area and the corresponding grids in the second grid area, and determining whether there is a risk of collision of the mobile tool at the position to be detected based on the operation results.

5. The method according to claim 4, characterized in that The occupation rule is that when the grid is occupied by an obstacle or a moving tool, its value is set to 1, otherwise it is set to 0; the binary operation is a binary AND operation; Calculating the values ​​of the grids in the first grid area and the corresponding grids in the second grid area, and determining whether there is a collision risk of the mobile tool at the position to be detected according to the calculation result, specifically includes: The values ​​of each grid in the grid area are subjected to binary AND operations with the values ​​of the corresponding grids in the occupied grid map. If more than a preset number of AND operation results are 1, it is determined that the mobile tool has a risk of collision at the position to be detected.

6. The method according to claim 4, characterized in that The occupation rule is that when the grid is occupied by an obstacle or a moving tool, its value is set to 0, otherwise it is set to 1; the binary operation is a binary OR operation; Calculating the values ​​of the grids in the first grid area and the corresponding grids in the second grid area, and determining whether there is a collision risk of the mobile tool at the position to be detected according to the calculation result, specifically includes: The values ​​of each grid in the grid area are subjected to a binary OR operation with the values ​​of the corresponding grids in the occupied grid map. If more than a preset number of OR operation results are 0, it is determined that the mobile tool has a risk of collision at the position to be detected.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Step 100: construct an occupancy grid map with the current position of the mobile tool as the center.

8. The method according to any one of claims 1 to 6, characterized in that: The position point to be detected is a waypoint on the driving path of the mobile tool.

9. The method according to claim 8, characterized in that The waypoint includes location information and driving status information of the mobile tool; The location information includes at least one of coordinate information and driving direction information of the mobile tool; The driving state information includes at least one of the following: the linear speed, linear acceleration, steering gear angle, steering wheel angle, steering wheel rotation angular velocity, steering wheel rotation angular acceleration, and hanging box angle of the mobile tool.

10. The method according to claim 8, characterized in that The method further comprises: If it is determined that the mobile tool has a collision risk at the waypoint, the waypoint is abandoned and the waypoint is replanned.

11. The method according to claim 8, characterized in that The method further comprises: If it is determined that the mobile tool has a collision risk at the waypoint, marking the waypoint as having a collision risk; It is determined whether the number of waypoints marked as having a collision risk in the driving path is greater than a preset number, and if so, it is determined that there is a collision risk in the driving path.

12. The method according to any one of claims 1 to 11, characterized in that: The method further comprises: Constructing a plurality of state transition paths according to the current driving state of the mobile tool; Selecting a target state transition path from the multiple state transition paths; The waypoint sequence corresponding to the target state transition path is determined as the driving path of the mobile tool, wherein the waypoint sequence corresponding to the target state transition path is the waypoints corresponding to each driving state node of the target state transition path.

13. The method according to claim 12, characterized in that Constructing multiple state transition paths according to the current driving state of the mobile tool includes: Determine a state transition space of a current driving state node of the mobile tool, and search for a next driving state node of the current driving state node in the state transition space of the current driving state node; Taking the next driving state node as the current driving state node, and repeatedly performing the step of searching for the next driving state node until a preset number of driving state nodes are generated; A state transfer path is constructed according to the sequence of multiple driving state nodes.

14. The method according to claim 13, characterized in that The state transition space for determining the current driving state node of the mobile tool includes: Taking all or part of the driving state nodes in the state transfer space of the previous driving state node of the current driving state node, including the current driving state node, as the target driving state node; Determine the state transition space corresponding to each target driving state node; The union of the state transition spaces corresponding to the target driving state nodes is determined as the state transition space of the current driving state node.

15. The method according to claim 14, characterized in that Determining the state transition space corresponding to each target driving state node includes: For each driving parameter of each target driving state node, determining a target value of the driving parameter, and discretizing the current value and the target value of the driving parameter to obtain a discrete point sequence; The discrete point sequences corresponding to the driving parameters of the target driving state node are combined to obtain a plurality of driving state nodes, and the plurality of driving state nodes constitute a state transfer space of the target driving state node.

16. The method according to claim 15, It is characterized by: The driving parameter includes the speed of the mobile tool, and the target value corresponding to the speed is the speed limit of the lane where the mobile tool is currently located; The driving parameter includes a steering wheel angle of the mobile tool, and the target value corresponding to the steering wheel angle is the maximum angle or the minimum angle of the steering wheel angle; The driving parameter is the box-hanging angle of the mobile tool, and the target value corresponding to the box-hanging angle is the minimum value or the maximum value of the box-hanging angle of the mobile tool.

17. The method according to claim 14, characterized in that Determining the state transition space corresponding to each target driving state node includes: A state transition space corresponding to a target driving state node is queried from a preset state transition library, wherein the state transition library is pre-constructed according to a driving trajectory of the mobile tool or other mobile tools of the same type.

18. The method according to claim 17, characterized in that The state transfer library is obtained according to the following steps: Acquire multiple driving trajectories corresponding to the mobile tool; For each driving trajectory, sampling the trajectory points in the driving trajectory to obtain a waypoint sequence corresponding to the driving trajectory; For each waypoint sequence, converting the waypoints in the waypoint sequence into corresponding driving state nodes in sequence to obtain a state transition sequence corresponding to the waypoint sequence; According to each state transfer sequence, a state transfer space corresponding to each driving state node in the state transfer sequence is obtained; A set of state transition spaces corresponding to each driving state node is determined as a state transition library corresponding to the mobile tool.

19. The method according to claim 18, characterized in that Converting the waypoints in the waypoint sequence into corresponding driving state nodes comprises: The driving parameters included in the driving state node are selected from the driving state information of the waypoint to obtain the driving state node corresponding to the waypoint.

20. The method according to any one of claims 13 to 19, characterized in that: The method further comprises: setting a first evaluation value for the waypoint sequence for indicating the quality of the waypoint sequence; The node value and the number of times selected of each driving state node in the state transition path are modified according to the first evaluation value corresponding to the waypoint sequence of the state transition path, and the node value is used to indicate the quality of the driving state node.

21. The method according to claim 20, characterized in that The method further comprises: After each state transition path is constructed, the number of times each driving state node on the state transition path is selected is accumulated by 1, and the number of times each driving state node is selected is stored.

22. The method according to claim 20, characterized in that The method further comprises: The node value and the number of times selected of each driving state node in the state transition path and the driving state node in the state transition space of each driving state node are modified according to the first evaluation value corresponding to the waypoint sequence of the state transition path.

23. The method according to claim 22, characterized in that The driving state node on the state transition path is called a main node, and modifying the node value and the number of times selected of the driving state node in the state transition space of each driving state node in the state transition path according to the first evaluation value corresponding to the waypoint sequence of the state transition path includes: For each master node on the state transfer path: The evaluation value obtained by evaluating the waypoint sequence corresponding to the state transition path and the node value of the master node are weighted averaged to obtain the new node value of the master node, and the number of times the master node is selected is accumulated by 1.

24. The method according to claim 23, characterized in that The state travel node in the state transfer space of the previous main node of the main node is called the brother node of the main node, and the node value and the number of times selected of the state travel node in the state transfer space of each travel state node in the state transfer path are modified according to the first evaluation value corresponding to the waypoint sequence of the state transfer path, and further includes: For each sibling node of the master node: Calculate the similarity between the main node and the sibling node, take the product of the evaluation value and the similarity as the evaluation score, perform weighted average of the evaluation score and the node value of the sibling node to obtain the new node value of the sibling node, and accumulate the number of times the sibling node is selected to the similarity.

25. The method according to claim 13, characterized in that Searching for the next driving state node of the current driving state node in the state transition space of the current driving state node includes: Determine whether each driving state node in the state transition space of the current driving state node is selectable; According to the node value and the number of times the optional driving state node is selected, the next driving state node of the current driving state node is selected from the optional driving state nodes.

26. The method according to claim 25, characterized in that The unselectable conditions of the driving status node include at least one of the following: There is a collision risk at the driving state node, the value of the driving parameter of the driving state node is unreasonable, and the transfer from the current driving state node to the driving state node is unreasonable.

27. The method according to claim 25, characterized in that According to the node value and the number of times the optional driving state node is selected, selecting the next driving state node of the current driving state node from the optional driving state nodes includes: For each optional driving state node: Calculating a second evaluation value of the driving state node according to the node value and the number of times the driving state node is selected, wherein the second evaluation value is used to indicate the priority of the driving state node being selected; The driving state node with the highest priority is selected according to the second evaluation value of the optional driving state node as the next driving state node in the current driving state node.

28. A mobile tool collision detection method, characterized in that: When a waypoint of a driving route is determined during the path planning process, the following steps are followed to determine whether the waypoint has a collision risk: Step 201: determining a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates, wherein the mobile tool occupation template is a grid map pre-constructed with the mobile tool as the center, and a grid area occupied by the mobile tool is pre-marked in the grid map according to the size, shape and posture of the mobile tool; Step 202: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the waypoint in the constructed occupation grid map to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 203: Determine whether there is a collision risk for the mobile tool at the waypoint according to the occupancy status of the first grid area and the second grid area.

29. A mobile tool collision detection method, characterized in that: After receiving the driving path of the mobile tool, follow the steps below to determine whether there is a collision risk on the driving path: Step 301: determining a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates, wherein the mobile tool occupation template is a grid map pre-constructed with the mobile tool as the center, and the grid area occupied by the mobile tool is pre-marked in the grid map according to the size, shape and posture of the mobile tool; Step 302: align the center point of the first grid area occupied by the target mobile tool in the occupation template with the position of a road point of the driving path in the constructed occupation grid map, so as to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 303: determine whether there is a collision risk for the mobile tool at the waypoint according to the occupation status of the first grid area and the second grid area; if there is a collision risk, execute step 304; if there is no collision risk, execute step 305; Step 304: determine that there is a collision risk in the driving path, and end the process; Step 305: Select the next waypoint from the driving path, and execute steps 302 to 305 for the waypoint.

30. A mobile tool collision detection method, characterized in that: After determining the driving state nodes of the state transition path of the mobile tool during the path planning process, follow the steps below to determine whether there is a collision risk at the driving state nodes: Step 401: determining a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates, wherein the mobile tool occupation template is a grid map pre-constructed with the mobile tool as the center, and a grid area occupied by the mobile tool is pre-marked in the grid map according to the size, shape and posture of the mobile tool; Step 402: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of the state travel node in the constructed occupation grid map to obtain the second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 403: Determine whether there is a collision risk at the driving state node according to the occupancy status of the first grid area and the second grid area.

31. A mobile tool collision detection method, characterized in that: After receiving the state transition path of the mobile tool, follow the steps below to determine whether there is a collision risk on the state transition path: Step 501: determining a target mobile tool occupation template that matches the posture of the mobile tool from preset mobile tool occupation templates, wherein the mobile tool occupation template is a grid map pre-constructed with the mobile tool as the center, and a grid area occupied by the mobile tool is pre-marked in the grid map according to the size, shape and posture of the mobile tool; Step 502: align the center point of the first grid area occupied by the mobile tool in the target mobile tool occupation template with the position of a driving state node of the state transition path in the constructed occupation grid map to obtain a second grid area occupied by the mobile tool in the occupation grid map; wherein the occupation grid map is an occupation grid map constructed with the current position of the mobile tool as the center; Step 503, determining whether there is a collision risk at the driving state node according to the occupation status of the first grid area and the second grid area; if there is a collision risk, executing step 504, and if there is no collision risk, executing step 505; Step 504: determine that there is a collision risk in the state transition path, and end the process; Step 505, selecting a next driving state node from the state transition path, and executing step 502 for the driving state node if there is a next driving state node, and executing step 506 if there is no next driving state node in the state transition path; Step 506: Determine that the state transition path has no collision risk, and end the process.

32. A computer-readable storage medium, characterized in that: It comprises a program or an instruction, and when the program or the instruction is run on a computer, it implements the mobile tool collision detection method as described in any one of claims 1 to 31.

33. A computer program product comprising instructions, characterized in that When the computer program product runs on a computer, the computer is enabled to execute the mobile tool collision detection method according to any one of claims 1 to 31.

34. A chip system, characterized in that: It includes a processor, the processor is coupled to a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the mobile tool collision detection method according to any one of claims 1 to 31 is implemented.

35. A circuit system, characterized in that: The circuit system includes a processing circuit, and the processing circuit is configured to execute the mobile tool collision detection method as described in any one of claims 1 to 31.

36. A computer system, characterized in that: comprising a memory, and one or more processors communicatively connected to the memory; The memory stores instructions that can be executed by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method as described in any one of claims 1 to 31.

37. A mobile tool, characterized in that: comprising a memory, and one or more processors communicatively connected to the memory; The memory stores instructions that can be executed by the one or more processors, and the instructions are executed by the one or more processors so that the one or more processors implement the mobile tool collision detection method as described in any one of claims 1 to 31.

Images