Data processing method and device for low-speed unmanned driving path planning

Abstract

The invention discloses a data processing method and device for low-speed unmanned driving path planning. The method comprises the following steps: acquiring to-be-processed inspection data; performing recognition processing based on image semantic analysis on the to-be-processed inspection data to obtain obstacle feature data; performing prediction processing based on an obstacle time prediction model on the obstacle feature data to obtain obstacle time data, the obstacle time data being data used for representing obstacle time of the obstacle; according to the obstacle feature data and the obstacle time data, routing inspection path planning processing is conducted on the robot, obstacle planning path data are obtained, and the obstacle planning path data are data used for representing the routing inspection path of the corresponding robot within the obstacle time. The obstacle time in the inspection process is predicted, the inspection path of the robot is updated according to the predicted obstacle time, the robot does not need to repeatedly detect when encountering the same obstacle in multiple inspection processes, and the inspection efficiency of the robot is improved.

Description

Technical Field

[0001] The present application relates to the field of robotics, and more specifically, to a data processing method and device for low-speed unmanned driving path planning. Background Art

[0002] With the continuous development of robot technology, robots are widely used in various scenarios, such as daily inspections in parks where inspections are required. There are obstacles in the robot map, and because the environment is non-static, the obstacles in the map gradually change. When the robot encounters obstacles during operation, it needs to re-plan the operation route. For obstacles that exist in the map for a long time, the robot needs to re-plan the route every time, which makes the robot inspection efficiency low.

[0003] Therefore, this application is proposed to address the problem of low efficiency of robot inspection in the prior art. Summary of the invention

[0004] The main purpose of this application is to provide a data processing method and device for low-speed unmanned driving path planning, so as to solve the technical problem of low robot inspection efficiency in the prior art and achieve the technical effect of improving the robot inspection efficiency.

[0005] In order to achieve the above-mentioned purpose, in a first aspect of the present application, a data processing method for low-speed unmanned driving path planning is proposed, comprising:

[0006] Acquire inspection data to be processed, wherein the inspection data to be processed is data related to obstacles when the robot is inspecting;

[0007] Performing recognition processing based on image semantic analysis on the inspection data to be processed to obtain obstacle feature data, wherein the obstacle feature data is data used to represent obstacle features;

[0008] Performing prediction processing on the obstacle feature data based on an obstacle time prediction model to obtain obstacle time data, wherein the obstacle time data is data used to represent the obstacle time of the obstacle;

[0009] According to the obstacle feature data and the obstacle time data, the robot is subjected to inspection path planning processing to obtain obstacle planning path data, wherein the obstacle planning path data is data used to represent the robot inspection path corresponding to the obstacle time.

[0010] In some optional embodiments of the present application, the inspection data to be processed is subjected to recognition processing based on image semantic analysis to obtain obstacle feature data including:

[0011] Performing obstacle detection processing on the inspection data to be processed to obtain obstacle data, wherein the obstacle data is data used to represent obstacles existing in the inspection path;

[0012] Performing recognition processing based on shape features on the obstacle data to obtain obstacle shape feature data, wherein the obstacle shape feature is feature data used to represent the shape of the obstacle;

[0013] Performing recognition processing based on semantic features on the obstacle data to obtain obstacle semantic feature data, wherein the obstacle semantic feature data is feature data used to represent the semantics of the obstacle;

[0014] The obstacle feature data is obtained according to the obstacle shape feature data and the obstacle semantic feature data.

[0015] In some optional embodiments of the present application, the obstacle feature data is subjected to prediction processing based on an obstacle time prediction model to obtain obstacle time data;

[0016] Performing recognition processing on the obstacle feature data to obtain obstacle shape feature data and obstacle semantic feature data;

[0017] Matching the obstacle time corresponding to the obstacle shape feature in a preset obstacle model database to obtain first obstacle time data;

[0018] Performing semantic analysis on the obstacle semantic feature data to obtain second obstacle time data, wherein the second obstacle time data is data used to represent the obstacle time obtained through semantic analysis;

[0019] The obstacle time data is obtained according to the first obstacle time and the second obstacle time.

[0020] In some optional embodiments of the present application, the inspection path planning processing of the robot is performed according to the obstacle feature data and the obstacle time data, and the obstacle planning path data obtained includes:

[0021] Performing identification processing on the obstacle feature data to obtain first obstacle feature data, wherein the first obstacle feature data is data used to represent obstacle frequency characteristics;

[0022] The first obstacle feature data is subjected to a judgment process based on a preset obstacle frequency rule to judge whether the obstacle frequency feature corresponding to the first obstacle feature data satisfies the preset obstacle frequency rule,

[0023] If the obstacle frequency characteristics corresponding to the first obstacle feature data satisfy the preset obstacle frequency rule, updating the preset obstacle map according to the obstacle feature data to obtain updated obstacle map data, and performing inspection path planning processing on the robot according to the updated obstacle map data to obtain the obstacle planning path data;

[0024] If the obstacle frequency characteristics corresponding to the first obstacle feature data do not meet the preset obstacle frequency rules, the robot is inspected and path planned according to the obstacle feature data to obtain operation update data, wherein the operation update data is used to represent the path planning data of the robot from the obstacle to the destination.

[0025] In some optional embodiments of the present application, the inspection path planning processing of the robot is performed according to the obstacle feature data and the obstacle time data, and the obstacle planning path data obtained includes:

[0026] Performing identification processing on the obstacle feature data to obtain second obstacle feature data, wherein the second obstacle feature data is data used to represent a time feature of the obstacle;

[0027] performing obstacle time update processing on the second obstacle feature data and the obstacle time data to obtain obstacle time update data, wherein the obstacle time update data is data used to indicate obstacle update time;

[0028] The preset obstacle map is updated according to the obstacle feature data to obtain updated obstacle map data, and the inspection path planning of the robot is performed according to the updated obstacle map data to obtain process obstacle planning path data;

[0029] The planned path data when the process obstacle occurs is updated based on the obstacle time update data to obtain the obstacle planned path data.

[0030] In some optional embodiments of the present application, if the obstacle frequency characteristics corresponding to the first obstacle feature data do not meet the preset obstacle frequency rule, the robot is subjected to inspection path planning processing according to the obstacle feature data, and the operation update data obtained includes:

[0031] Performing identification processing on the obstacle feature data to obtain obstacle position feature data;

[0032] Get robot operation data;

[0033] Performing identification processing on the robot operation data based on the inspection points to obtain data of the points to be inspected, wherein the data of the points to be inspected are data used to indicate the inspection points that have not been completed by the robot;

[0034] The obstacle position feature data and the to-be-inspected point data are processed by inspection path planning to obtain the operation update data.

[0035] According to a second aspect of the present application, a data processing device for low-speed unmanned driving path planning is proposed, comprising:

[0036] A data acquisition module, used to acquire inspection data to be processed, wherein the inspection data to be processed is relevant data used to represent obstacles during robot inspection;

[0037] An obstacle module, used for performing recognition processing on the inspection data to be processed based on image semantic analysis to obtain obstacle feature data, wherein the obstacle feature data is data used to represent obstacle features;

[0038] An obstacle time module, used for performing prediction processing on the obstacle feature data based on the obstacle time prediction model to obtain obstacle time data, wherein the obstacle time data is data used to represent the obstacle time of the obstacle;

[0039] The path planning module is used to plan the inspection path of the robot according to the obstacle feature data and the obstacle time data to obtain obstacle planning path data, wherein the obstacle planning path data is data used to represent the robot inspection path corresponding to the obstacle time.

[0040] In some optional embodiments of the present application, the obstacle module includes:

[0041] An obstacle detection module, used to perform obstacle detection processing on the inspection data to be processed to obtain obstacle data, wherein the obstacle data is data used to represent obstacles existing in the inspection path;

[0042] A shape recognition module, used to perform recognition processing on the obstacle data based on shape features to obtain obstacle shape feature data, wherein the obstacle shape feature is feature data used to represent the shape of the obstacle;

[0043] A semantic recognition module performs recognition processing on the obstacle data based on semantic features to obtain obstacle semantic feature data, wherein the obstacle semantic feature data is feature data used to represent the semantics of the obstacle;

[0044] The obstacle feature module is used to obtain the obstacle feature data according to the obstacle shape feature data and the obstacle semantic feature data.

[0045] According to a third aspect of the present application, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the above-mentioned data processing method for low-speed unmanned driving path planning.

[0046] According to the fourth aspect of the present application, an electronic device is proposed, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the above-mentioned data processing method for low-speed unmanned driving path planning.

[0047] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0048] In the present application, inspection data to be processed is obtained, wherein the inspection data to be processed is the relevant data used to represent obstacles during robot inspection; the inspection data to be processed is subjected to recognition processing based on image semantic analysis to obtain obstacle feature data, wherein the obstacle feature data is data used to represent obstacle features; the obstacle feature data is subjected to prediction processing based on an obstacle time prediction model to obtain obstacle time data, wherein the obstacle time data is data used to represent obstacle time; the robot is subjected to inspection path planning processing based on the obstacle feature data and the obstacle time data to obtain obstacle planning path data, wherein the obstacle planning path data is data used to represent the corresponding robot inspection path within the obstacle time. By predicting the obstacle time of obstacles during the inspection process, the robot's inspection path is updated according to the predicted obstacle time, and the robot does not need to repeatedly detect the same obstacle when it encounters it during multiple inspections, thereby improving the robot's inspection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings constituting a part of this application are used to provide a further understanding of this application, so that other features, purposes and advantages of this application become more obvious. The schematic embodiment drawings and their descriptions of this application are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0050] Figure 1 A flow chart of a data processing method for low-speed unmanned driving path planning provided in this application;

[0051] Figure 2 A flow chart of a data processing method for low-speed unmanned driving path planning provided in this application;

[0052] Figure 3A flow chart of a data processing method for low-speed unmanned driving path planning provided in this application;

[0053] Figure 4 A schematic diagram of a data processing device for low-speed unmanned driving path planning provided by the present application;

[0054] Figure 5 A schematic diagram of another data processing device for low-speed unmanned driving path planning provided in this application. DETAILED DESCRIPTION

[0055] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0056] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0057] In the present application, the terms "upper", "lower", "left", "right", "front", "back", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings. These terms are mainly used to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to have a specific orientation, or to be constructed and operated in a specific orientation.

[0058] In addition, some of the above terms may be used to express other meanings in addition to indicating orientation or positional relationship. For example, the term "on" may also be used to express a certain dependency or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to specific circumstances.

[0059] In addition, the terms "installed", "set", "provided with", "connected", "connected", and "socketed" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be an internal connection between two devices, elements, or components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0060] In some optional embodiments of the present application, a data processing method for low-speed unmanned driving path planning is proposed. Figure 1 A flowchart of a data processing method for low-speed unmanned driving path planning provided in this application, such as Figure 1 As shown, the method comprises the following steps:

[0061] S101: Obtain inspection data to be processed;

[0062] The inspection data to be processed is data related to obstacles encountered during robot inspection;

[0063] S102: performing recognition processing based on image semantic analysis on the inspection data to be processed to obtain obstacle feature data;

[0064] The obstacle characteristic data is data used to represent the characteristics of the obstacle;

[0065] In some optional embodiments of the present application, a data processing method for low-speed unmanned driving path planning is proposed. Figure 2 A flowchart of a data processing method for low-speed unmanned driving path planning provided in this application, such as Figure 2 As shown, the method comprises the following steps:

[0066] S201: performing obstacle detection processing on the inspection data to be processed to obtain obstacle data;

[0067] The obstacle data is data used to represent obstacles existing in the inspection path;

[0068] S202: performing recognition processing on the obstacle data based on shape features to obtain obstacle shape feature data;

[0069] The obstacle shape feature is feature data used to represent the obstacle shape;

[0070] S2303: performing recognition processing on the obstacle data based on semantic features to obtain obstacle semantic feature data;

[0071] The obstacle semantic feature data is feature data used to represent the semantics of the obstacle;

[0072] S204: Obtain obstacle feature data according to the obstacle shape feature data and the obstacle semantic feature data.

[0073] S103: performing prediction processing on the obstacle feature data based on the obstacle time prediction model to obtain obstacle time data;

[0074] The obstacle time data is data used to indicate the obstacle time of an obstacle;

[0075] In some optional embodiments of the present application, a data processing method for low-speed unmanned driving path planning is proposed. Figure 3 A flowchart of a data processing method for low-speed unmanned driving path planning provided in this application, such as Figure 3 As shown, the method comprises the following steps:

[0076] S301: performing recognition processing on obstacle feature data to obtain obstacle shape feature data and obstacle semantic feature data;

[0077] S302: Matching the obstacle time corresponding to the obstacle shape feature in a preset obstacle model database to obtain first obstacle time data;

[0078] S303: performing semantic analysis on the obstacle semantic feature data to obtain second obstacle time data;

[0079] The second obstacle time data is data used to represent the obstacle time obtained through semantic analysis;

[0080] S304: Obtaining obstacle time data according to the first obstacle time and the second obstacle time.

[0081] S104: Perform inspection path planning processing on the robot according to the obstacle feature data and the obstacle time data to obtain obstacle planning path data.

[0082] The obstacle planning path data is data used to represent the corresponding robot inspection path within the obstacle time.

[0083] In some optional embodiments of the present application, a data processing method for low-speed unmanned driving path planning is proposed, comprising:

[0084] Performing identification processing on the obstacle feature data to obtain first obstacle feature data, wherein the first obstacle feature data is data used to represent obstacle frequency characteristics;

[0085] The first obstacle feature data is subjected to a judgment process based on a preset obstacle frequency rule to judge whether the obstacle frequency feature corresponding to the first obstacle feature data satisfies the preset obstacle frequency rule,

[0086] If the obstacle frequency characteristics corresponding to the first obstacle feature data satisfy the preset obstacle frequency rule, updating the preset obstacle map according to the obstacle feature data to obtain updated obstacle map data, and performing inspection path planning processing on the robot according to the updated obstacle map data to obtain the obstacle planning path data;

[0087] If the obstacle frequency characteristics corresponding to the first obstacle feature data do not meet the preset obstacle frequency rules, the robot is inspected and path planned according to the obstacle feature data to obtain operation update data, wherein the operation update data is used to represent the path planning data of the robot from the obstacle to the destination.

[0088] In some optional embodiments of the present application, a data processing method for low-speed unmanned driving path planning is proposed, if the obstacle frequency characteristics corresponding to the first obstacle characteristic data do not meet the preset obstacle frequency rule, the robot is inspected according to the obstacle characteristic data. The path planning process is performed to obtain operation update data, including:

[0089] Performing identification processing on the obstacle feature data to obtain obstacle position feature data;

[0090] Get robot operation data;

[0091] Performing identification processing on the robot operation data based on the inspection points to obtain data of the points to be inspected, wherein the data of the points to be inspected are data used to indicate the inspection points that have not been completed by the robot;

[0092] The obstacle position feature data and the to-be-inspected point data are processed by inspection path planning to obtain the operation update data.

[0093] In some optional embodiments of the present application, a data processing method for low-speed unmanned driving path planning is proposed, comprising:

[0094] Performing identification processing on the obstacle feature data to obtain second obstacle feature data, wherein the second obstacle feature data is data used to represent a time feature of the obstacle;

[0095] performing obstacle time update processing on the second obstacle feature data and the obstacle time data to obtain obstacle time update data, wherein the obstacle time update data is data used to indicate obstacle update time;

[0096] The preset obstacle map is updated according to the obstacle feature data to obtain updated obstacle map data, and the inspection path planning of the robot is performed according to the updated obstacle map data to obtain process obstacle planning path data;

[0097] The planned path data when the process obstacle occurs is updated based on the obstacle time update data to obtain the obstacle planned path data.

[0098] In some optional embodiments of the present application, a data processing device for low-speed unmanned driving path planning is provided. Figure 4 A schematic diagram of a data processing device for low-speed unmanned driving path planning provided in this application, such as Figure 4 As shown, including:

[0099] The data acquisition module 41 is used to acquire the inspection data to be processed, wherein the inspection data to be processed is the relevant data used to represent obstacles during the robot inspection;

[0100] The obstacle module 42 is used to perform recognition processing based on image semantic analysis on the inspection data to be processed to obtain obstacle feature data, wherein the obstacle feature data is data used to represent obstacle features;

[0101] The obstacle time module 43 is used to perform prediction processing on the obstacle feature data based on the obstacle time prediction model to obtain obstacle time data, wherein the obstacle time data is data used to represent the obstacle time of the obstacle;

[0102] The path planning module 44 is used to plan the inspection path of the robot according to the obstacle feature data and the obstacle time data to obtain obstacle planning path data, wherein the obstacle planning path data is data used to represent the inspection path of the robot corresponding to the obstacle time.

[0103] In some optional embodiments of the present application, a data processing device for low-speed unmanned driving path planning is provided. Figure 5 A schematic diagram of another data processing device for low-speed unmanned driving path planning provided by this application, such as Figure 5 As shown, including:

[0104] The obstacle detection module 51 is used to perform obstacle detection processing on the inspection data to be processed to obtain obstacle data, wherein the obstacle data is data used to represent obstacles existing in the inspection path;

[0105] A shape recognition module 52, configured to perform recognition processing on the obstacle data based on shape features to obtain obstacle shape feature data, wherein the obstacle shape feature is feature data used to represent the shape of the obstacle;

[0106] The semantic recognition module 53 performs recognition processing on the obstacle data based on semantic features to obtain obstacle semantic feature data, wherein the obstacle semantic feature data is feature data used to represent the semantics of the obstacle;

[0107] The obstacle feature module 54 is used to obtain obstacle feature data according to the obstacle shape feature data and the obstacle semantic feature data.

[0108] The specific manner of executing the operation of each unit in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0109] In summary, in the present application, the inspection data to be processed is obtained, wherein the inspection data to be processed is the relevant data used to represent obstacles during robot inspection; the inspection data to be processed is subjected to recognition processing based on image semantic analysis to obtain obstacle feature data, wherein the obstacle feature data is data used to represent obstacle features; the obstacle feature data is subjected to prediction processing based on an obstacle time prediction model to obtain obstacle time data, wherein the obstacle time data is data used to represent obstacle time; the robot is subjected to inspection path planning processing based on the obstacle feature data and the obstacle time data to obtain obstacle planning path data, wherein the obstacle planning path data is data used to represent the corresponding robot inspection path within the obstacle time. By predicting the obstacle time of obstacles during the inspection process, the robot's inspection path is updated according to the predicted obstacle time, and the robot does not need to repeatedly detect the same obstacle when it encounters it during multiple inspections, thereby improving the robot's inspection efficiency.

[0110] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0111] Obviously, those skilled in the art should understand that the above-mentioned units or steps of the present application can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present application is not limited to any specific combination of hardware and software.

[0112] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A data processing method for low-speed unmanned driving path planning, characterized in that: include: Acquire inspection data to be processed, wherein the inspection data to be processed is data related to obstacles when the robot is inspecting; Performing recognition processing based on image semantic analysis on the inspection data to be processed to obtain obstacle feature data, wherein the obstacle feature data is data used to represent obstacle features; Performing prediction processing on the obstacle feature data based on an obstacle time prediction model to obtain obstacle time data, wherein the obstacle time data is data used to represent the obstacle time of the obstacle; According to the obstacle feature data and the obstacle time data, the robot is subjected to inspection path planning processing to obtain obstacle planning path data, wherein the obstacle planning path data is data used to represent the robot inspection path corresponding to the obstacle time.

2. The data processing method according to claim 1, characterized in that: The inspection data to be processed is subjected to recognition processing based on image semantic analysis to obtain obstacle feature data including: Performing obstacle detection processing on the inspection data to be processed to obtain obstacle data, wherein the obstacle data is data used to represent obstacles existing in the inspection path; Performing recognition processing based on shape features on the obstacle data to obtain obstacle shape feature data, wherein the obstacle shape feature is feature data used to represent the shape of the obstacle; Performing recognition processing based on semantic features on the obstacle data to obtain obstacle semantic feature data, wherein the obstacle semantic feature data is feature data used to represent the semantics of the obstacle; The obstacle feature data is obtained according to the obstacle shape feature data and the obstacle semantic feature data.

3. The data processing method according to claim 1, characterized in that: Performing prediction processing on the obstacle feature data based on an obstacle time prediction model to obtain obstacle time data; Performing recognition processing on the obstacle feature data to obtain obstacle shape feature data and obstacle semantic feature data; Matching the obstacle time corresponding to the obstacle shape feature in a preset obstacle model database to obtain first obstacle time data; Performing semantic analysis on the obstacle semantic feature data to obtain second obstacle time data, wherein the second obstacle time data is data used to represent the obstacle time obtained through semantic analysis; The obstacle time data is obtained according to the first obstacle time and the second obstacle time.

4. The data processing method according to claim 1, characterized in that: According to the obstacle feature data and the obstacle time data, the robot is subjected to inspection path planning processing, and the obstacle planning path data obtained includes: Performing identification processing on the obstacle feature data to obtain first obstacle feature data, wherein the first obstacle feature data is data used to represent obstacle frequency characteristics; The first obstacle feature data is subjected to a judgment process based on a preset obstacle frequency rule to judge whether the obstacle frequency feature corresponding to the first obstacle feature data satisfies the preset obstacle frequency rule, If the obstacle frequency characteristics corresponding to the first obstacle feature data satisfy the preset obstacle frequency rule, updating the preset obstacle map according to the obstacle feature data to obtain updated obstacle map data, and performing inspection path planning processing on the robot according to the updated obstacle map data to obtain the obstacle planning path data; If the obstacle frequency characteristics corresponding to the first obstacle feature data do not meet the preset obstacle frequency rules, the robot is inspected and path planned according to the obstacle feature data to obtain operation update data, wherein the operation update data is used to represent the path planning data of the robot from the obstacle to the destination.

5. The data processing method according to claim 1, characterized in that: According to the obstacle feature data and the obstacle time data, the robot is subjected to inspection path planning processing, and the obstacle planning path data obtained includes: Performing identification processing on the obstacle feature data to obtain second obstacle feature data, wherein the second obstacle feature data is data used to represent a time feature of the obstacle; performing obstacle time update processing on the second obstacle feature data and the obstacle time data to obtain obstacle time update data, wherein the obstacle time update data is data used to indicate obstacle update time; The preset obstacle map is updated according to the obstacle feature data to obtain updated obstacle map data, and the inspection path planning of the robot is performed according to the updated obstacle map data to obtain process obstacle planning path data; The planned path data when the process obstacle occurs is updated based on the obstacle time update data to obtain the obstacle planned path data.

6. The data processing method according to claim 4, characterized in that: If the obstacle frequency characteristics corresponding to the first obstacle characteristic data do not satisfy the preset obstacle frequency rule, performing inspection path planning processing on the robot according to the obstacle characteristic data, and obtaining operation update data includes: Performing identification processing on the obstacle feature data to obtain obstacle position feature data; Get robot operation data; Performing inspection point-based identification processing on the robot operation data to obtain to-be-inspected point data, wherein the to-be-inspected point data is data used to indicate the unfinished inspection points of the robot; The obstacle position feature data and the to-be-inspected point data are processed by inspection path planning to obtain the operation update data.

7. A data processing device for low-speed unmanned driving path planning, characterized in that: include: A data acquisition module, used to acquire inspection data to be processed, wherein the inspection data to be processed is relevant data used to represent obstacles during robot inspection; An obstacle module, used for performing recognition processing on the inspection data to be processed based on image semantic analysis to obtain obstacle feature data, wherein the obstacle feature data is data used to represent obstacle features; An obstacle time module, used for performing prediction processing on the obstacle feature data based on the obstacle time prediction model to obtain obstacle time data, wherein the obstacle time data is data used to represent the obstacle time of the obstacle; The path planning module is used to plan the inspection path of the robot according to the obstacle feature data and the obstacle time data to obtain obstacle planning path data, wherein the obstacle planning path data is data used to represent the robot inspection path corresponding to the obstacle time.

8. The data processing device according to claim 7, characterized in that: Obstacle module, including: An obstacle detection module, used to perform obstacle detection processing on the inspection data to be processed to obtain obstacle data, wherein the obstacle data is data used to represent obstacles existing in the inspection path; A shape recognition module, used to perform recognition processing on the obstacle data based on shape features to obtain obstacle shape feature data, wherein the obstacle shape feature is feature data used to represent the shape of the obstacle; A semantic recognition module performs recognition processing on the obstacle data based on semantic features to obtain obstacle semantic feature data, wherein the obstacle semantic feature data is feature data used to represent the semantics of the obstacle; The obstacle feature module is used to obtain the obstacle feature data according to the obstacle shape feature data and the obstacle semantic feature data.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the data processing method for low-speed unmanned driving path planning as described in any one of claims 1-6.

10. An electronic device, characterized in that: include: at least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the data processing method for low-speed unmanned driving path planning as described in any one of claims 1-6.

Images