Data processing method and device for robot path planning

Abstract

The invention discloses a data processing method and device for robot path planning. The method comprises the following steps: acquiring to-be-processed data; key frame extraction processing is carried out on the to-be-processed data to obtain to-be-recognized key frame data, and the to-be-recognized key frame data is data used for representing key frames in environment data collected by robot operation; performing key frame matching processing on the to-be-identified key frame data and preset map data to obtain matching result data; and if the matching result data is that the to-be-identified key frame data is not matched with the preset map data key frame, performing temporary map construction processing on the to-be-processed data to obtain temporary path planning data. According to the method, the current position of the robot is judged by matching the environment data acquired during operation of the robot with the preset map, and temporary map construction and path planning are performed on the unmatched robot, so that path planning of the lost robot is realized.

Description

Technical Field

[0001] The present application relates to the field of robotics, and in particular, to a data processing method and device for robot path planning. Background Art

[0002] When mobile robots perform navigation tasks in complex environments, they are often lost, such as when they are powered on in a non-initial position or restarted after a power failure, which leads to the failure of their navigation tasks. For robots that lack GPS or positioning signals, how to determine the position of the lost robot and return it to the normal working path is an urgent problem to be solved.

[0003] Therefore, this application is filed to address the above problems. Summary of the invention

[0004] The main purpose of the present application is to provide a data processing method and device for robot path planning, so as to solve the technical problem in the prior art that it is difficult to plan the path of a lost robot.

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

[0006] Acquire data to be processed, wherein the data to be processed is relevant data used to represent the operation of the robot;

[0007] Performing key frame extraction processing on the data to be processed to obtain key frame data to be identified, wherein the key frame data to be identified is data used to represent key frames in the environmental data collected by the robot during operation;

[0008] Perform key frame matching processing on the key frame data to be identified and the preset map data to obtain matching result data;

[0009] If the matching result data indicates that the key frame data to be identified does not match the preset map data key frame, a temporary map construction process is performed on the data to be processed to obtain temporary path planning data.

[0010] Furthermore, the key frame data to be identified is subjected to key frame matching processing with the preset map data, and the matching result data obtained includes:

[0011] Performing positioning feature extraction processing on the key frame data to be identified to obtain positioning feature data to be identified;

[0012] Performing a matching process based on positioning features on the positioning feature data to be identified and the key frame in the preset map data to obtain matching feature data, wherein the matching feature data is data used to indicate the matching degree of the positioning features between the key frame data to be identified and the key frame in the preset map data;

[0013] Compare the matching feature data with a preset matching feature threshold,

[0014] If the matching degree corresponding to the matching feature data is greater than or equal to the preset matching feature threshold, first matching result data is obtained, wherein the first matching result data includes matching key frame data, and the matching key frame data is key frame data in the preset map data corresponding to the matching feature data;

[0015] If the matching degree corresponding to the matching feature data is less than the preset matching feature threshold, second matching result data is obtained, wherein the second matching result data includes newly created key frame data, and the newly created key frame data is the key frame data to be identified.

[0016] Furthermore, the positioning feature data to be identified is matched with the key frame in the preset map data based on the positioning feature, and the matching feature data obtained includes:

[0017] Performing feature similarity-based evaluation processing on the positioning feature data to be identified to obtain feature similarity data, wherein the feature similarity data is data used to represent the similarity between positioning features in the key frame to be identified;

[0018] Performing feature point extraction processing on the positioning feature data to be identified to obtain feature point data, wherein the feature point data is data used to represent the number of positioning features in the key frame to be identified;

[0019] The feature similarity data and the feature point data are screened based on the positioning feature screening rule,

[0020] If the feature similarity data and the feature point data satisfy the positioning feature screening rule, obtaining the positioning feature data to be matched;

[0021] If the feature similarity data and the feature point data do not satisfy the positioning feature screening rule, obtain updated positioning feature data to be identified, until the feature similarity data and feature point data corresponding to the updated positioning feature data to be identified satisfy the positioning feature screening rule, and obtain the positioning feature data to be matched, wherein the updated positioning feature data to be identified is the positioning feature data extracted from the updated key frame data to be identified through positioning features;

[0022] The positioning feature data to be matched is matched with the key frame in the preset map data based on the positioning feature to obtain the matching feature data.

[0023] Further, if the matching result data indicates that the key frame data to be identified does not match the preset map data key frame, a temporary map construction process is performed on the data to be processed to obtain temporary path planning data, including:

[0024] Performing key frame extraction processing on the data to be processed to obtain temporary key frame data, wherein the temporary key frame is key frame data used to represent the construction of a temporary map;

[0025] Performing a temporary map construction process based on a mapping algorithm on the temporary key frame data to obtain temporary map data, wherein the temporary map data is map data used to represent the environment in which the robot is located;

[0026] Perform path planning processing on the robot according to the temporary map data to obtain the temporary path planning data.

[0027] Further, performing path planning processing on the robot according to the temporary map data to obtain the temporary path planning data includes:

[0028] Performing operation target decision processing based on the target exploration model on the temporary map data to obtain temporary operation target data, wherein the temporary operation target data includes temporary target position data, which is position data for indicating the temporary operation target point of the robot;

[0029] Performing position recognition processing on the data to be processed to obtain initial position data, wherein the initial position data is data used to represent the current operating position of the robot;

[0030] Perform path planning processing on the initial position data and the temporary target position data to obtain the temporary path planning data.

[0031] Furthermore, the method further comprises:

[0032] If the matching result data is that the key frame data to be identified matches the preset map data key frame, obtaining the matching key frame data;

[0033] Performing position recognition processing on the matching key frame data to obtain running position data, wherein the running position data is data used to represent the running position of the robot;

[0034] Performing task target decision processing on the data to be processed to obtain task target position data, wherein the task target position data is position data for indicating the task target point of the robot;

[0035] The running position data and the task target position data are processed by path planning based on the preset map data to obtain path planning data.

[0036] Further, the task target decision processing is performed on the data to be processed to obtain the task target position data including:

[0037] Performing recognition processing of preset points on the preset map data to obtain a plurality of preset point data, wherein the plurality of preset point data is data for representing a plurality of preset points in the preset map;

[0038] The plurality of preset point data are screened based on the running path to obtain task target position data, wherein the task target position data is position data for indicating preset points that meet the preset running path rules.

[0039] According to a second aspect of the present application, a data processing device for robot path planning is proposed, comprising:

[0040] A data acquisition module, used to acquire data to be processed, wherein the data to be processed is relevant data used to represent the operation of the robot;

[0041] A key frame extraction module, used to perform key frame extraction processing on the data to be processed to obtain key frame data to be identified, wherein the key frame data to be identified is data used to represent key frames in the environmental data collected by the robot during operation;

[0042] A matching module, used for performing key frame matching processing on the key frame data to be identified and the preset map data to obtain matching result data;

[0043] The path planning module performs temporary map construction processing on the data to be processed to obtain temporary path planning data if the matching result data indicates that the key frame data to be identified does not match the key frame of preset map data.

[0044] According to a third aspect of the present application, a computer-readable storage medium is provided, 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 robot path planning.

[0045] 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 robot path planning.

[0046] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0047] In the present application, data to be processed is obtained, wherein the data to be processed is related data used to represent the operation of the robot; key frame extraction processing is performed on the data to be processed to obtain key frame data to be identified, wherein the key frame data to be identified is data used to represent the key frame in the environmental data collected by the robot operation; the key frame data to be identified is matched with the preset map data to obtain matching result data; if the matching result data is that the key frame data to be identified does not match the key frame of the preset map data, a temporary map construction processing is performed on the data to be processed to obtain temporary path planning data. The current robot position is determined by matching the environmental data collected by the robot operation with the preset map, and temporary map construction and path planning are performed on the unmatched robot to achieve path planning for the lost robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] 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:

[0049] Figure 1 A flow chart of a data processing method for robot path planning provided in this application;

[0050] Figure 2 A flow chart of a data processing method for robot path planning provided in this application;

[0051] Figure 3 A flow chart of a data processing method for robot path planning provided in this application;

[0052] Figure 4 A flow chart of a data processing method for robot path planning provided in this application;

[0053] Figure 5 A schematic diagram of a data processing device for robot path planning provided in this application. DETAILED DESCRIPTION

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] 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.

[0059] In an optional embodiment of the present application, a data processing method for robot path planning is proposed. Figure 1 A flow chart of a data processing method for robot path planning provided in this application, such as Figure 1 As shown, the method comprises the following steps:

[0060] S101: Obtaining data to be processed;

[0061] The data to be processed are relevant data used to represent the operation of the robot. The data to be processed include the robot's own information about the robot's operation and external information collected through sensors, etc. The robot's own information includes preset map data pre-stored by the robot, the preset map data is the map data of the robot's working area, and the robot's operating status information, including operating status-related data such as the robot's power, speed, and posture; the external information collected by the robot includes external environment information, which can be environmental image data collected by a camera, environmental data collected by an ultrasonic sensor, environmental data collected by a lidar sensor, etc.

[0062] S102: performing key frame extraction processing on the data to be processed to obtain key frame data to be identified;

[0063] The key frame data to be identified is the data used to represent the key frames in the environmental data collected during the operation of the robot. The environmental data collected in the data to be processed are identified, and key frames are extracted from the above-collected environmental data to obtain the key frames to be identified, so as to match the key frames to be identified with the key frames in the preset map stored by the robot to realize the positioning of the robot.

[0064] S103: performing key frame matching processing on the key frame data to be identified and the preset map data to obtain matching result data;

[0065] In another optional embodiment of the present application, a data processing method for robot path planning is proposed. Figure 2 A flow chart of a data processing method for robot path planning provided in this application, such as Figure 2 As shown, the method comprises the following steps:

[0066] S201: extracting positioning features from key frame data to be identified, and obtaining positioning feature data to be identified;

[0067] S202: performing matching processing based on positioning features on the positioning feature data to be identified and the key frames in the preset map data to obtain matching feature data;

[0068] The matching feature data is data used to indicate the matching degree between the key frame data to be identified and the positioning features of the key frame in the preset map data;

[0069] In an optional embodiment of the present application, a data processing method for robot path planning is proposed. Figure 3 A flow chart of a data processing method for robot path planning provided in this application, such as Figure 3 As shown, the method comprises the following steps:

[0070] S301: performing feature similarity-based evaluation processing on the feature data to be identified and located to obtain feature similarity data;

[0071] The feature similarity data is data used to represent the similarity between positioning features in the key frame to be identified. The key frame to be identified includes multiple positioning features. Similarity evaluation is performed on the multiple positioning features in the key frame to be identified to obtain the similarity of the positioning features in the key frame to be identified, so as to determine whether matching and positioning can be performed based on the key frame to be identified and the key frame of the preset map according to the similarity of the positioning features.

[0072] S302: extracting feature points from the feature data to be identified and located to obtain feature point data;

[0073] The feature point data is data used to represent the number of positioning features in the key frame to be identified;

[0074] S303: performing screening processing on the feature similarity data and the feature point data based on the positioning feature screening rule to obtain the positioning feature data to be matched;

[0075] If the feature similarity data is less than or equal to the preset feature similarity threshold, a result of feature similarity is obtained; if the feature similarity is greater than the preset feature similarity threshold, a result of feature dissimilarity is obtained; if the number of feature points corresponding to the feature point data is greater than or equal to the preset feature point threshold, a result of sufficient features is obtained; if the number of feature points corresponding to the feature point data is less than the preset feature point threshold, a result of insufficient features is obtained;

[0076] The feature similarity data and feature point data are screened based on the positioning feature screening rules, including:

[0077] If the feature similarity data and the feature point data do not satisfy the positioning feature screening rule, obtain and update the positioning feature data to be identified, until the feature similarity data and the feature point data corresponding to the updated positioning feature data to be identified satisfy the positioning feature screening rule, and obtain the positioning feature data to be matched, and the updated positioning feature data to be identified is the positioning feature data extracted from the updated key frame data to be identified through the positioning feature;

[0078] If the features are similar and / or insufficient, the feature similarity data and feature point data do not meet the positioning feature screening rules; update the acquisition environment information, obtain the updated key frame data to be identified, perform positioning feature extraction on the updated key frame data to be identified, and obtain the updated positioning feature data to be identified, and repeat the above-mentioned positioning feature screening process based on the feature similarity data and feature point data on the updated positioning feature data to be identified, until the feature similarity data and feature point data corresponding to the updated positioning feature data to be identified meet the positioning feature screening rules, and obtain the positioning feature data to be matched.

[0079] If the feature similarity data and the feature point data meet the positioning feature screening rules, the positioning feature data to be matched is obtained;

[0080] If the features are not similar and the features are sufficient, and if the feature similarity data and the feature point data satisfy the positioning feature screening rules, the positioning feature data to be matched is obtained, and the positioning feature data to be matched is the positioning feature data to be identified.

[0081] S304: performing matching processing based on positioning features on the positioning feature data to be matched and the key frames in the preset map data to obtain matching feature data.

[0082] In an embodiment of the present application, by screening the collected key frames based on the similarity of positioning features and the number of positioning features, the low matching accuracy caused by invalid features and fewer features when matching with a preset map is reduced, thereby achieving the technical effect of improving the key frame matching accuracy.

[0083] S203: Compare the matching feature data with a preset matching feature threshold to obtain matching result data.

[0084] In an optional embodiment of the present application, a data processing method for robot path planning is proposed, and matching result data is obtained based on the comparison result of matching feature data and a preset matching feature threshold. The matching result data includes first matching result data and second matching result data.

[0085] If the matching degree corresponding to the matching feature data is greater than or equal to a preset matching feature threshold, first matching result data is obtained, wherein the first matching result data includes matching key frame data, and the matching key frame data is key frame data in the preset map data corresponding to the matching feature data;

[0086] If the matching degree corresponding to the matching feature data is less than the preset matching feature threshold, second matching result data is obtained, wherein the second matching result data includes newly created key frame data, and the newly created key frame data is the key frame data to be identified.

[0087] S104: Perform path planning processing on the data to be processed according to the matching result data to obtain path planning data.

[0088] If the matching result data indicates that the key frame data to be identified does not match the preset map data key frame, a temporary map construction process is performed on the data to be processed to obtain temporary path planning data.

[0089] In an optional embodiment of the present application, a data processing method for robot path planning is proposed, comprising:

[0090] S401: performing key frame extraction processing on the data to be processed to obtain temporary key frame data;

[0091] The temporary key frame is key frame data used to represent the construction of a temporary map;

[0092] S402: Performing temporary map construction processing on the temporary key frame data based on a mapping algorithm to obtain temporary map data;

[0093] Temporary map data is map data used to represent the robot's environment. The temporary map is constructed by the collected temporary key frame data through the SLAM mapping algorithm to obtain a temporary map so that the robot can plan its path when the robot is lost and its position is uncertain.

[0094] S403: Perform path planning processing on the robot according to the temporary map data to obtain temporary path planning data.

[0095] In an optional embodiment of the present application, a data processing method for robot path planning is proposed, comprising:

[0096] The temporary map data is processed for operation target decision based on the target exploration model to obtain temporary operation target data, wherein the temporary operation target data includes temporary target position data, and the temporary target position data is position data for indicating the temporary operation target point of the robot; the data to be processed is processed for position recognition to obtain initial position data, wherein the initial position data is data for indicating the current operation position of the robot; the initial position data and the temporary target position data are processed for path planning to obtain temporary path planning data.

[0097] The temporary map data is subjected to operation target decision processing based on the target exploration model, and the decision on the robot's operation target is realized by autonomously exploring the temporary map, including: when performing target point extraction processing on the temporary map data, a plurality of process target points are obtained; the paths of the plurality of process target points and the current position are respectively calculated to obtain first decision feature data, the first decision feature data is feature data used to represent the length of the path between the process target point and the current position; second decision feature extraction is performed on the plurality of process target points to obtain second decision feature data, the second decision feature data is feature data used to represent that the process target point can collect environmental information; decisions are made on the plurality of process target points according to the first decision feature data and the second decision feature data to obtain temporary operation target data; path planning is performed according to the temporary operation target data to avoid path planning for the robot when the preset map is not determined, until the key frame data collected by the robot matches the key frame data of the preset map, the robot loss state ends, and path planning is performed according to the preset map.

[0098] In another optional embodiment of the present application, a data processing method for robot path planning is proposed, comprising:

[0099] If the matching result data is a match between the key frame data to be identified and the key frame of the preset map data, the matching key frame data is obtained, and the matching key frame data is the key frame data in the preset map data corresponding to the matching feature data; the matching key frame data is processed for position recognition to obtain running position data, wherein the running position data is data used to represent the running position of the robot; the data to be processed is processed for task target decision to obtain task target position data, wherein the task target position data is position data used to represent the task target point of the robot; the running position data and the task target position data are processed for path planning based on the preset map data to obtain path planning data.

[0100] In another optional embodiment of the present application, a data processing method for robot path planning is proposed, comprising:

[0101] The preset map data is processed for identifying preset points to obtain a plurality of preset point data, wherein the plurality of preset point data are data for representing the plurality of preset points in the preset map; the plurality of preset point data are processed for screening based on the running path to obtain task target position data, wherein the task target position data are position data for representing the preset points that satisfy the preset running path rules, including: extracting features based on the path distance of the preset point data to obtain first running path feature data, wherein the first running path feature data are feature data for representing the path distance between the preset point and the current position; extracting features based on the point type of the preset point data to obtain second running path feature data, wherein the second running path data are feature data for representing the type of the preset point; obtaining robot running status data, wherein the robot running status data include robot power data and robot task data; screening the preset points according to the above robot running status data and the first running path feature data and the second running path feature data to obtain the task target point data.

[0102] In another optional embodiment of the present application, a data processing device for robot path planning is proposed. Figure 5 A schematic diagram of a data processing device for robot path planning provided in this application, such as Figure 5 As shown, including:

[0103] A data acquisition module 51 is used to acquire data to be processed, wherein the data to be processed is relevant data used to represent the operation of the robot;

[0104] A key frame extraction module 52 is used to perform key frame extraction processing on the data to be processed to obtain key frame data to be identified, wherein the key frame data to be identified is data used to represent key frames in the environmental data collected by the robot during operation;

[0105] A matching module 53 is used to perform key frame matching processing on the key frame data to be identified and the preset map data to obtain matching result data;

[0106] The path planning module 54 performs path planning processing on the data to be processed according to the matching result data to obtain path planning data.

[0107] If the matching result data indicates that the key frame data to be identified does not match the preset map data key frame, a temporary map construction process is performed on the data to be processed to obtain temporary path planning 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 data to be processed is obtained, wherein the data to be processed is the relevant data used to represent the operation of the robot; the data to be processed is subjected to key frame extraction processing to obtain key frame data to be identified, wherein the key frame data to be identified is the data used to represent the key frame in the environmental data collected by the operation of the robot; the key frame data to be identified is subjected to key frame matching processing with the preset map data to obtain matching result data; if the matching result data is that the key frame data to be identified does not match the key frame of the preset map data, the data to be processed is subjected to temporary map construction processing to obtain temporary path planning data. The current robot position is determined by matching the environmental data collected by the operation of the robot with the preset map, and the unmatched robot is subjected to temporary map construction and path planning to achieve path planning for the lost robot.

[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 robot path planning, characterized in that: include: Acquire data to be processed, wherein the data to be processed is relevant data used to represent the operation of the robot; Performing key frame extraction processing on the data to be processed to obtain key frame data to be identified, wherein the key frame data to be identified is data used to represent key frames in the environmental data collected by the robot during operation; Perform key frame matching processing on the key frame data to be identified and the preset map data to obtain matching result data; If the matching result data indicates that the key frame data to be identified does not match the preset map data key frame, a temporary map construction process is performed on the data to be processed to obtain temporary path planning data.

2. The data processing method according to claim 1, characterized in that: The key frame data to be identified is processed with the preset map data for key frame matching, and the matching result data obtained includes: Performing positioning feature extraction processing on the key frame data to be identified to obtain positioning feature data to be identified; Performing a matching process based on positioning features on the positioning feature data to be identified and the key frame in the preset map data to obtain matching feature data, wherein the matching feature data is data used to indicate the matching degree of the positioning features between the key frame data to be identified and the key frame in the preset map data; Compare the matching feature data with a preset matching feature threshold, If the matching degree corresponding to the matching feature data is greater than or equal to the preset matching feature threshold, first matching result data is obtained, wherein the first matching result data includes matching key frame data, and the matching key frame data is key frame data in the preset map data corresponding to the matching feature data; If the matching degree corresponding to the matching feature data is less than the preset matching feature threshold, second matching result data is obtained, wherein the second matching result data includes newly created key frame data, and the newly created key frame data is the key frame data to be identified.

3. The data processing method according to claim 2, characterized in that: The positioning feature data to be identified is matched with the key frame in the preset map data based on the positioning feature to obtain the matching feature data including: Performing feature similarity-based evaluation processing on the positioning feature data to be identified to obtain feature similarity data, wherein the feature similarity data is data used to represent the similarity between positioning features in the key frame to be identified; Performing feature point extraction processing on the positioning feature data to be identified to obtain feature point data, wherein the feature point data is data used to represent the number of positioning features in the key frame to be identified; The feature similarity data and the feature point data are screened based on the positioning feature screening rule, If the feature similarity data and the feature point data satisfy the positioning feature screening rule, obtaining the positioning feature data to be matched; If the feature similarity data and the feature point data do not satisfy the positioning feature screening rule, obtain updated positioning feature data to be identified, until the feature similarity data and feature point data corresponding to the updated positioning feature data to be identified satisfy the positioning feature screening rule, and obtain the positioning feature data to be matched, wherein the updated positioning feature data to be identified is the positioning feature data extracted from the updated key frame data to be identified through positioning features; The positioning feature data to be matched is matched with the key frame in the preset map data based on the positioning feature to obtain the matching feature data.

4. The data processing method according to claim 1, characterized in that: If the matching result data indicates that the key frame data to be identified does not match the preset map data key frame, a temporary map construction process is performed on the data to be processed to obtain temporary path planning data, including: Performing key frame extraction processing on the data to be processed to obtain temporary key frame data, wherein the temporary key frame is key frame data used to represent the construction of a temporary map; Performing a temporary map construction process based on a mapping algorithm on the temporary key frame data to obtain temporary map data, wherein the temporary map data is map data used to represent the environment in which the robot is located; Perform path planning processing on the robot according to the temporary map data to obtain the temporary path planning data.

5. The data processing method according to claim 4, characterized in that: Performing path planning processing on the robot according to the temporary map data to obtain the temporary path planning data includes: Performing operation target decision processing based on the target exploration model on the temporary map data to obtain temporary operation target data, wherein the temporary operation target data includes temporary target position data, which is position data for indicating the temporary operation target point of the robot; Performing position recognition processing on the data to be processed to obtain initial position data, wherein the initial position data is data used to represent the current operating position of the robot; Perform path planning processing on the initial position data and the temporary target position data to obtain the temporary path planning data.

6. The data processing method according to claim 1, characterized in that: The method further comprises: If the matching result data is that the key frame data to be identified matches the preset map data key frame, obtaining the matching key frame data; Performing position recognition processing on the matching key frame data to obtain running position data, wherein the running position data is data used to represent the running position of the robot; Performing task target decision processing on the data to be processed to obtain task target position data, wherein the task target position data is position data for indicating the task target point of the robot; The running position data and the task target position data are processed by path planning based on the preset map data to obtain path planning data.

7. The data processing method according to claim 6, characterized in that: The task target decision processing is performed on the data to be processed to obtain the task target location data including: Performing recognition processing of preset points on the preset map data to obtain a plurality of preset point data, wherein the plurality of preset point data is data for representing a plurality of preset points in the preset map; The plurality of preset point data are screened based on the running path to obtain task target position data, wherein the task target position data is position data for indicating preset points that meet the preset running path rules.

8. A data processing device for robot path planning, characterized in that: include: A data acquisition module, used to acquire data to be processed, wherein the data to be processed is relevant data used to represent the operation of the robot; A key frame extraction module, used to perform key frame extraction processing on the data to be processed to obtain key frame data to be identified, wherein the key frame data to be identified is data used to represent key frames in the environmental data collected by the robot during operation; A matching module, used for performing key frame matching processing on the key frame data to be identified and the preset map data to obtain matching result data; The path planning module performs temporary map construction processing on the data to be processed to obtain temporary path planning data if the matching result data indicates that the key frame data to be identified does not match the key frame of preset map 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 robot path planning according to any one of claims 1 to 7.

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 robot path planning described in any one of claims 1-7.

Images