Robotic autonomous exploration method and apparatus

Abstract

The application discloses a robot autonomous exploration method and device. The method comprises the following steps: obtaining to-be-processed data, wherein the to-be-processed data comprises start point data and end point data; performing exploration point generation processing on the start point data and the end point data to obtain exploration point data; performing exploration path generation processing on the exploration point data to obtain exploration path data; obtaining environment exploration data, wherein the environment exploration data is environment data collected by a robot in an unknown region according to the exploration path data; and performing map construction processing on the environment exploration data to obtain target exploration map data. The start and end points of the robot are used to generate exploration points of the robot in the unknown region, the exploration path is determined according to the exploration points, the robot collects environment data according to the exploration path, and the map construction is performed to obtain the target exploration map, so that the map construction in the unknown region is realized, and the robot can autonomously explore and construct a map in the unknown region.

Description

Technical Field

[0001] This application relates to the field of robotics, and more specifically, to a method and apparatus for autonomous exploration by a robot. Background Technology

[0002] With the continuous development of robotics technology, robots are widely used in various fields. Robots can autonomously move point-to-point using navigation systems, but this relies heavily on a global map for autonomous navigation. Currently, robot map data is primarily generated by personnel manually controlling the robot to navigate through the work environment, consuming significant manpower and resulting in low efficiency. Furthermore, when the work environment changes, the robot struggles to autonomously explore unknown areas, leading to a low degree of autonomy. Requiring personnel to manually re-control the robot to update the global map in these unfamiliar areas is also inefficient.

[0003] Therefore, this application is made in response to the problems in the prior art. Summary of the Invention

[0004] The main objective of this application is to provide a method and apparatus for autonomous robot exploration, in order to solve the problem of existing robots exploring unknown areas, and to achieve the technical effect of improving the degree of robot autonomy and exploration efficiency.

[0005] To achieve the above objectives, the first aspect of this application proposes a method for autonomous robot exploration, comprising:

[0006] Acquire data to be processed, wherein the data to be processed includes start point data and end point data, the start point data being data used to represent the robot's start point, and the end point data being data used to represent the robot's end point;

[0007] The starting point data and the ending point data are processed to generate exploration points, which are used to represent exploration points in unknown areas of the robot.

[0008] The exploration point data is processed to generate exploration paths, thereby obtaining exploration path data, wherein the exploration path data is used to represent the path of the robot running in an unknown area;

[0009] Acquire environmental exploration data, wherein the environmental exploration data is used to represent environmental data of unknown areas collected by the robot based on the exploration path data;

[0010] The environmental exploration data is processed to construct a map, resulting in target exploration map data, which is used to represent unknown areas.

[0011] Further, the starting point data and the ending point data are processed to generate exploration points, resulting in exploration point data including:

[0012] The data to be processed is identified to obtain initial map data, wherein the initial map data is map data used to represent the robot's initial area;

[0013] The initial map data and the starting point data are processed to generate exploration points, resulting in the first exploration point data;

[0014] The first exploration point data and the termination point data are processed to generate exploration points, resulting in the second exploration point data.

[0015] The exploration point data is obtained based on the first exploration point data and the second exploration point data.

[0016] Further, the initial map data and the starting point data are processed to generate exploration points, resulting in first exploration point data including:

[0017] The initial map data is subjected to boundary region identification processing to obtain boundary region data, wherein the boundary region data is used to represent the boundary between the initial map and the unknown region;

[0018] The boundary region data is subjected to target point filtering processing to obtain process target point data, wherein the process target point data is data used to represent points on the boundary region;

[0019] The starting point data and the process target point data are processed based on path distance to generate exploration points, thereby obtaining the first exploration point data.

[0020] Furthermore, the exploration point data is processed to generate exploration paths, resulting in exploration path data including:

[0021] The exploration point data is identified to obtain first exploration point data and second exploration point data;

[0022] The starting point data and the first exploration point data are processed to generate a first exploration path, resulting in first exploration path data.

[0023] The second exploration point data and the termination point data are processed to generate a second exploration path, resulting in second exploration path data.

[0024] The first exploration point data and the second exploration point data are processed to generate a third exploration path, resulting in third exploration path data.

[0025] The exploration path data is obtained based on the first exploration path data, the second exploration path data, and the third exploration path data.

[0026] Furthermore, the environmental exploration data is processed to construct a map, resulting in target exploration map data including:

[0027] The environmental exploration data is identified and processed to obtain first environmental exploration data and second environmental exploration data, wherein the first environmental exploration data is used to represent environmental data of a first unknown area collected by the robot during operation, and the second environmental exploration data is used to represent environmental data of a second unknown area collected by the robot during operation;

[0028] The first environmental exploration data and the second environmental exploration data are respectively processed based on keyframes to obtain the first exploration map data and the second exploration map data;

[0029] The first exploration map data and the second exploration map data are subjected to keyframe-based map matching processing with the initial map data to obtain the process exploration map data;

[0030] The process exploration map data is globally optimized to obtain the target exploration map data.

[0031] Furthermore, the first environmental exploration data undergoes keyframe-based map construction processing to obtain the first exploration map data, which includes:

[0032] The first environment exploration data is processed by keyframe extraction to obtain first environment keyframe data, wherein the first environment keyframe data is keyframe data used to represent the construction of a first unknown area map;

[0033] The first environment keyframe data is processed by a map building algorithm to obtain the first environment map data, wherein the first environment map data is map data used to represent the environment of the first unknown area.

[0034] The first environmental map data and the initial map data are subjected to map update processing based on keyframe matching to obtain the first exploration map data, wherein the first exploration map data is robot map data used to represent a first unknown area.

[0035] According to a second aspect of this application, a robotic autonomous exploration device is proposed, comprising:

[0036] The data acquisition module is used to acquire data to be processed, wherein the data to be processed includes start point data and end point data, the start point data is data used to represent the robot's start point, and the end point data is data used to represent the robot's end point;

[0037] The exploration point module is used to perform exploration point generation processing on the starting point data and the ending point data to obtain exploration point data, wherein the exploration point data is data used to represent exploration points in unknown areas of the robot;

[0038] The exploration path module is used to process the exploration point data to generate exploration paths, thereby obtaining exploration path data, wherein the exploration path data is data used to represent the robot's running path in an unknown area;

[0039] An exploration data acquisition module is used to acquire environmental exploration data, wherein the environmental exploration data is used to represent environmental data of unknown areas collected by the robot based on the exploration path data;

[0040] The map building module performs map building processing on the environmental exploration data to obtain target exploration map data, wherein the target exploration map data is map data used to represent unknown areas.

[0041] Furthermore, the exploration point module includes:

[0042] The identification module is used to identify the data to be processed and obtain initial map data, wherein the initial map data is map data used to represent the initial area of ​​the robot;

[0043] The first exploration point module is used to perform exploration point generation processing on the initial map data and the starting point data to obtain the first exploration point data;

[0044] The second exploration point module is used to perform exploration point generation processing on the first exploration point data and the termination point data to obtain the second exploration point data.

[0045] An exploration point generation module is used to obtain the exploration point data based on the first exploration point data and the second exploration point data.

[0046] According to a third aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing the computer to perform the above-described robot autonomous exploration method.

[0047] According to a fourth aspect of this 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, the computer program being executed by the at least one processor to cause the at least one processor to perform the above-described robot autonomous exploration method.

[0048] The technical solutions provided by the embodiments of this application may include the following beneficial effects:

[0049] In this application, the following steps are taken: First, data to be processed is acquired, including start point data and end point data. The start point data represents the robot's starting point, and the end point data represents the robot's ending point. Second, exploration point generation processing is performed on the start point data and the end point data to obtain exploration point data, which represents exploration points within an unknown area of ​​the robot. Third, exploration path generation processing is performed on the exploration point data to obtain exploration path data, which represents the robot's running path within the unknown area. Fourth, environmental exploration data is acquired, representing environmental data collected by the robot in the unknown area based on the exploration path data. Fifth, map construction processing is performed on the environmental exploration data to obtain target exploration map data, which represents map data representing the unknown area. By generating exploration points for the robot in unknown areas based on its start and end points, determining exploration paths based on these points, and collecting environmental data along the exploration paths, the robot constructs a map from the collected environmental exploration data to obtain a target exploration map. This enables the robot to autonomously explore and map unknown areas, thus improving its level of autonomy. Attached Figure Description

[0050] The accompanying drawings, which form part of this application, are used to provide a further understanding of the application and to make other features, objects, and advantages of the application more apparent. The illustrative embodiments and descriptions of this application are used to explain the application and do not constitute an undue limitation of the application. In the drawings:

[0051] Figure 1 A flowchart of a robot autonomous exploration method provided in this application;

[0052] Figure 2 A flowchart of a robot autonomous exploration method provided in this application;

[0053] Figure 3 A flowchart of a robot autonomous exploration method provided in this application;

[0054] Figure 4 A schematic diagram of a robot autonomous exploration device provided in this application;

[0055] Figure 5 A schematic diagram of another robotic autonomous exploration device provided in this application. Detailed Implementation

[0056] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0057] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0058] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing this application and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation.

[0059] Furthermore, in addition to indicating location or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in some cases to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this application based on the specific circumstances.

[0060] Furthermore, the terms "installation," "setup," "equipped with," "connection," "linked," and "socketing" should be interpreted broadly. 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 an internal connection between two devices, components, or parts. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0061] In existing technologies, when robots build a global map, technicians mainly control the robots to walk through the work environment to construct the global map. For work environments with large areas and complex terrain, it consumes a lot of human resources for technicians to lead the robots through the work environment, resulting in a low degree of robot autonomy. Furthermore, when the location of the work environment area is constantly changing, the global map needs to be updated and constructed every time it changes. If the deployment personnel have to control the robots to walk through unknown areas to achieve the global map update, the efficiency is low.

[0062] To address the aforementioned problems in robot map building in existing technologies, this application proposes an automated robot exploration method. The robot plans exploration points within an unknown region based solely on the starting and ending points. An exploration path is generated within the unknown region based on these exploration points. The robot then runs along this path, collecting environmental information. Based on this collected information, map data is constructed within the unknown region, resulting in target exploration map data. This method enables autonomous exploration and map building within unknown regions, improving the robot's autonomy and map update efficiency.

[0063] In some optional embodiments of this application, a method for autonomous robot exploration is provided. Figure 1 A flowchart of a robot autonomous exploration method provided in this application is shown below. Figure 1 As shown, the method includes the following steps:

[0064] S101: Obtain the data to be processed;

[0065] The data to be processed includes start point data and end point data. The start point data is used to represent the robot's start point, and the end point data is used to represent the robot's end point.

[0066] S102: Perform exploration point generation processing on the starting point data and ending point data to obtain exploration point data;

[0067] Exploration point data refers to data used to represent exploration points within unknown areas of the robot;

[0068] In some optional embodiments of this application, a method for autonomous robot exploration is proposed. Figure 2 A flowchart of a robot autonomous exploration method provided in this application is shown below. Figure 2 As shown, the method includes:

[0069] S201: Identify the data to be processed to obtain initial map data;

[0070] The initial map data is used to represent the robot's initial area. The data to be processed undergoes recognition processing based on the initial map to obtain the initial map data, which includes first initial map data and second initial map data. If the robot has pre-stored a map of the initial area, this initial map data is the map data for that initial area; if the robot has not pre-stored a map of the current initial area, this initial map data is not present.

[0071] In an optional embodiment of this application, when a robot is deployed in a working environment, the robot does not store map data of the working environment. The robot autonomously explores and constructs a global map in the working environment. When the area of ​​the working environment changes, such as when the area of ​​the working environment expands, the global map of the original working environment area in the robot becomes the initial map data.

[0072] S202: Perform exploration point generation processing on the initial map data and starting point data to obtain the first exploration point data;

[0073] In some optional embodiments of this application, a method for autonomous robot exploration is proposed, including:

[0074] The initial map data is processed to identify boundary regions, which are used to represent the boundary between the initial map and the unknown area. The boundary region data is then processed to filter target points, which are used to represent points on the boundary region. Finally, the starting point data and the process target point data are processed to generate exploration points based on path distance, which are used to generate the first exploration point data.

[0075] In an optional embodiment of this application, when the area of ​​the robot's working environment changes, the initial map data is the global map of the original working environment. Boundary area data is identified based on the initial map data. The boundary area is where the known and unknown areas in the map are adjacent. Points on the boundary area are identified as candidate target points, resulting in multiple candidate target points. The multiple candidate target points are filtered based on a point selection algorithm to obtain the aforementioned process target point. The direction D1 of the first exploration point is determined based on the process target point and the starting point. The first exploration point is determined based on the direction of the first exploration point and the path distance. The path distance is used to represent the exploration area range, which can be a preset range L1. The position of the first exploration point from the preset range L1 of the starting point is calculated in the direction of the first exploration point to obtain the first exploration point.

[0076] In another optional embodiment of this application, when the robot is deployed in a completely new working environment, no relevant map data is stored in the robot. The robot explores autonomously in the completely new working environment and generates the first exploration point by: the robot collecting environmental data at the starting point, collecting keyframe data in the current starting point area, and constructing the starting point area map data based on the keyframe data in the starting point area. The starting point area map data is the initial map data. The exploration point generation process can be performed based on the above method according to the initial map data and the starting point data to obtain the first exploration point data.

[0077] S203: Perform exploration point generation processing on the first exploration point data and the termination point data to obtain the second exploration point data;

[0078] In an optional embodiment of this application, after obtaining the first exploration point data, first exploration path data is generated based on the first exploration point data. The robot runs according to the first exploration path data and collects keyframe data of the first exploration area. A map of the first exploration area is constructed based on the collected keyframe data of the first exploration area to obtain first exploration area map data. First process exploration point generation processing is performed based on the first exploration area map data and the first exploration point data to obtain first process exploration point data, including: identifying the boundary area of ​​the first exploration area map data to obtain first boundary area data; performing target point filtering processing on the first boundary area data to obtain first process target point data; performing path distance-based exploration point generation processing on the first exploration point data and the first process target point data to obtain first process exploration point data; repeating the above steps of generating process exploration point data until the distance between the process exploration point and the termination point data is less than or equal to a preset path distance to obtain second exploration point data, where the second exploration point data is the process exploration point data whose distance to the termination point is less than or equal to the preset path distance.

[0079] S204: Obtain exploration point data based on the first exploration point data and the second exploration point data.

[0080] When the robot explores autonomously, process exploration points are generated according to the above exploration point generation method. The exploration point data includes the first exploration point data, the second exploration point data, and the process exploration point data.

[0081] S103: Perform exploration path generation processing on the exploration point data to obtain exploration path data;

[0082] Exploration path data is used to represent the path the robot takes when operating in an unknown area;

[0083] In some optional embodiments of this application, a method for autonomous robot exploration is proposed. Figure 3 A flowchart of a robot autonomous exploration method provided in this application is shown below. Figure 3 As shown, the method includes:

[0084] The exploration point data is identified to obtain the first exploration point data and the second exploration point data; the starting point data and the first exploration point data are processed to generate a first exploration path to obtain the first exploration path data; the second exploration point data and the ending point data are processed to generate a second exploration path to obtain the second exploration path data; the first exploration point data and the second exploration point data are processed to generate a third exploration path to obtain the third exploration path data; and the exploration path data is obtained based on the first exploration path data, the second exploration path data, and the third exploration path data.

[0085] In an optional embodiment of this application, the starting point data and the first exploration point data are processed to generate a first exploration path, resulting in the first exploration path data including:

[0086] When the first exploration point is generated, the exploration point direction D1 is determined based on the process target point and the starting point. The first exploration point is obtained at the path distance L1 from the starting point on the first exploration point direction D1. The first exploration path is determined based on the first exploration point direction D1 and the path distance L1, and the exploration is repeated on the first exploration path. The first exploration path data is obtained based on the first exploration path and the repetition rules.

[0087] In another optional embodiment of this application, the second exploration point data and the termination point data are processed to generate a second exploration path, resulting in second exploration path data including:

[0088] When the second exploration point is generated, the distance between the process exploration point and the termination point is judged. When the distance between the process exploration point and the termination point is less than or equal to the preset path distance, the process exploration point is the second exploration point. The adjacent exploration points of the second exploration point are obtained. A reciprocating exploration path based on the preset reciprocating path distance is generated based on the adjacent exploration points and the second exploration point. A non-reciprocating exploration path is generated based on the second exploration point and the termination point. The second exploration path is generated based on the reciprocating exploration path and the non-reciprocating exploration path. For example, when a robot autonomously explores an unknown region Q1, the initial point is P0 and the ending point is P1. During the process of the robot autonomously exploring from the initial point P0 to the ending point P1 in the unknown region Q1, the exploration points include P2, P3, and P4. Among them, P4 is the process exploration point whose distance from the ending point P1 is less than or equal to the preset path distance, which is the second exploration point. The second exploration path data is generated based on the second exploration point P4 and the ending point P1, including: starting from the second exploration point, first generating a path with a preset reciprocating path distance in the direction of the adjacent process exploration point P3 to generate a reciprocating exploration path. After the reciprocating path, it runs from the direction of the second exploration point P4 and the ending point P1 to generate a non-reciprocating exploration path. The second exploration path is obtained based on the above reciprocating exploration path and the above non-reciprocating exploration path.

[0089] In another optional embodiment of this application, the third exploration path generation process is performed on the first exploration point data and the second exploration point data to obtain the third exploration path data, including:

[0090] The process of generating a third exploration path from the first and second exploration point data includes: generating exploration paths between adjacent process exploration points; generating exploration paths for any adjacent process exploration point; the adjacent process exploration of any process exploration point includes a first adjacent process exploration point and a second adjacent process exploration point, where the first adjacent process exploration point is the preceding adjacent exploration point and the second adjacent process exploration point is the following adjacent exploration point; the robot's exploration point operation sequence during autonomous exploration is the first adjacent process exploration point, the process exploration point, and the second adjacent process exploration point; generating a first reciprocating exploration path based on a preset reciprocating path distance based on the process exploration point and the first adjacent process exploration point; generating a non-reciprocating exploration path based on the process exploration point and the second adjacent process exploration point; generating a second reciprocating exploration path based on a preset path distance at the second adjacent process exploration point based on the path direction determined by the process exploration point and the second adjacent process exploration point; and obtaining the aforementioned third exploration path data based on the first reciprocating exploration path, the non-reciprocating exploration path, and the second reciprocating exploration path.

[0091] S104: Acquire environmental exploration data;

[0092] Environmental exploration data refers to environmental data collected by the robot based on the exploration path data in unknown areas;

[0093] S105: Perform map construction processing on the environmental exploration data to obtain target exploration map data.

[0094] The target exploration map data is used to represent unknown areas.

[0095] In some optional embodiments of this application, a method for autonomous robot exploration is proposed. Figure 3 A flowchart of a robot autonomous exploration method provided in this application is shown below. Figure 3 As shown, the method includes:

[0096] S301: Identify and process the environmental exploration data to obtain first environmental exploration data and second environmental exploration data;

[0097] The first environmental exploration data is used to represent the environmental data of the first unknown area collected by the robot during operation, and the second environmental exploration data is used to represent the environmental data of the second unknown area collected by the robot during operation;

[0098] S302: Perform keyframe-based map construction processing on the first environment exploration data and the second environment exploration data respectively to obtain the first exploration map data and the second exploration map data;

[0099] In some optional embodiments of this application, a method for autonomous robot exploration is proposed, including:

[0100] The first environment exploration data is processed by keyframe extraction to obtain first environment keyframe data, which is used to represent the keyframe data for constructing a map of the first unknown area; the first environment keyframe data is processed by map construction based on a mapping algorithm to obtain first environment map data, which is used to represent the environment of the first unknown area; the first environment map data and the initial map data are processed by map update based on keyframe matching to obtain first exploration map data, which is used to represent the robot map data including the first unknown area.

[0101] S303: Perform keyframe-based map matching processing on the first exploration map data, the second exploration map data, and the initial map data to obtain the process exploration map data;

[0102] S304: Perform global optimization processing on the process exploration map data to obtain the target exploration map data.

[0103] In an optional embodiment of this application, the keyframe data in the collected environmental data is processed for map construction using the SLAM algorithm. The newly created map data is then matched with the initial map data to expand the initial map data. The map data constructed at different exploration stages is also matched. During the map expansion process, repeated data collection improves the collection of environmental information and increases the accuracy of map construction. Furthermore, during the autonomous exploration process of the robot to achieve map construction, the constructed exploration map is globally optimized at a preset optimization distance to improve the accuracy of the newly created map.

[0104] In some alternative embodiments of this application, a robotic autonomous exploration device is proposed. Figure 4 A schematic diagram of a robot autonomous exploration device provided in this application, such as... Figure 4 As shown, the device includes:

[0105] The data acquisition module 41 is used to acquire data to be processed, wherein the data to be processed includes start point data and end point data, the start point data is data used to represent the robot's start point, and the end point data is data used to represent the robot's end point;

[0106] The exploration point module 42 is used to perform exploration point generation processing on the starting point data and the ending point data to obtain exploration point data, wherein the exploration point data is data used to represent exploration points in unknown areas of the robot;

[0107] The exploration path module 43 is used to perform exploration path generation processing on the exploration point data to obtain exploration path data, wherein the exploration path data is data used to represent the path of the robot running in an unknown area;

[0108] The exploration data acquisition module 44 is used to acquire environmental exploration data, wherein the environmental exploration data is used to represent the environmental data of the unknown area collected by the robot according to the exploration path data;

[0109] The map building module 45 performs map building processing on the environmental exploration data to obtain target exploration map data, wherein the target exploration map data is map data used to represent unknown areas.

[0110] In some alternative embodiments of this application, a robotic autonomous exploration device is proposed. Figure 5 A schematic diagram of another robotic autonomous exploration device provided in this application, such as... Figure 5 As shown, the device includes:

[0111] The identification module 51 is used to identify the data to be processed and obtain initial map data, wherein the initial map data is map data used to represent the initial area of ​​the robot;

[0112] The first exploration point module 52 is used to perform exploration point generation processing on the initial map data and the starting point data to obtain the first exploration point data;

[0113] The second exploration point module 53 is used to perform exploration point generation processing on the first exploration point data and the termination point data to obtain the second exploration point data;

[0114] The exploration point generation module 54 is used to obtain exploration point data based on the first exploration point data and the second exploration point data.

[0115] The specific methods of execution of each unit in the above embodiments have been described in detail in the embodiments of the method, and will not be elaborated here.

[0116] In summary, this application involves: acquiring data to be processed, including start point data and end point data, wherein the start point data represents the robot's start point and the end point data represents the robot's end point; performing exploration point generation processing on the start point data and the end point data to obtain exploration point data, wherein the exploration point data represents exploration points within an unknown area of ​​the robot; performing exploration path generation processing on the exploration point data to obtain exploration path data, wherein the exploration path data represents the robot's running path within the unknown area; acquiring environmental exploration data, wherein the environmental exploration data represents environmental data collected by the robot in the unknown area based on the exploration path data; and performing map construction processing on the environmental exploration data to obtain target exploration map data, wherein the target exploration map data represents map data representing the unknown area. By generating exploration points for the robot in unknown areas based on its start and end points, determining exploration paths based on these points, and collecting environmental data along the exploration paths, the robot constructs a map from the collected environmental exploration data to obtain a target exploration map. This enables the robot to autonomously explore and map unknown areas, thus improving its level of autonomy.

[0117] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0118] Obviously, those skilled in the art should understand that the various units or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps into a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0119] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for autonomous exploration by a robot, characterized in that, include: Acquire data to be processed, wherein the data to be processed includes start point data and end point data, the start point data being data used to represent the robot's start point, and the end point data being data used to represent the robot's end point; The starting point data and the ending point data are processed to generate exploration points, which are used to represent exploration points in unknown areas of the robot. The exploration point data is processed to generate exploration paths, thereby obtaining exploration path data, wherein the exploration path data is used to represent the path of the robot running in an unknown area; The exploration point data is identified to obtain first exploration point data and second exploration point data; a first exploration path generation process is performed on the starting point data and the first exploration point data to obtain first exploration path data; a second exploration path generation process is performed on the second exploration point data and the ending point data to obtain second exploration path data; a third exploration path generation process is performed on the first exploration point data and the second exploration point data to obtain third exploration path data; and the exploration path data is obtained based on the first exploration path data, the second exploration path data, and the third exploration path data. The third exploration path generation process includes: the adjacent process exploration of any process exploration point includes a first adjacent process exploration point and a second adjacent process exploration point. The first adjacent process exploration point is the preceding adjacent exploration point of the process exploration point, and the second adjacent process exploration point is the following adjacent exploration point of the process exploration point. The robot's exploration point operation sequence during the autonomous exploration process is the first adjacent process exploration point, the process exploration point, and the second adjacent process exploration point. A first reciprocating exploration path based on a preset reciprocating path distance is generated based on the process exploration point and the first adjacent process exploration point. A non-reciprocating exploration path is generated based on the process exploration point and the second adjacent process exploration point. Based on the path direction determined by the process exploration point and the second adjacent process exploration point, a second reciprocating exploration path based on a preset path distance is generated at the second adjacent process exploration point. The third exploration path data is obtained based on the first reciprocating exploration path, the non-reciprocating exploration path, and the second reciprocating exploration path. Acquire environmental exploration data, wherein the environmental exploration data is used to represent environmental data of unknown areas collected by the robot based on the exploration path data; The environmental exploration data is processed to construct a map, resulting in target exploration map data, which is used to represent unknown areas.

2. The method according to claim 1, characterized in that, The exploration point data is obtained by performing exploration point generation processing on the starting point data and the ending point data, including: The data to be processed is identified to obtain initial map data, wherein the initial map data is map data used to represent the robot's initial area; The initial map data and the starting point data are processed to generate exploration points, resulting in the first exploration point data; The first exploration point data and the termination point data are processed to generate exploration points, resulting in the second exploration point data. The exploration point data is obtained based on the first exploration point data and the second exploration point data.

3. The method according to claim 2, characterized in that, The initial map data and the starting point data are processed to generate exploration points, resulting in the first exploration point data, which includes: The initial map data is subjected to boundary region identification processing to obtain boundary region data, wherein the boundary region data is used to represent the boundary between the initial map and the unknown region; The boundary region data is subjected to target point filtering processing to obtain process target point data, wherein the process target point data is data used to represent points on the boundary region; The starting point data and the process target point data are processed based on path distance to generate exploration points, thereby obtaining the first exploration point data.

4. The method according to claim 1, characterized in that, Map construction processing is performed on the environmental exploration data to obtain target exploration map data, including: The environmental exploration data is identified and processed to obtain first environmental exploration data and second environmental exploration data, wherein the first environmental exploration data is used to represent environmental data of a first unknown area collected by the robot during operation, and the second environmental exploration data is used to represent environmental data of a second unknown area collected by the robot during operation; The first environmental exploration data and the second environmental exploration data are respectively processed based on keyframes to obtain the first exploration map data and the second exploration map data; The first exploration map data and the second exploration map data are subjected to keyframe-based map matching processing with the initial map data to obtain the process exploration map data; The process exploration map data is globally optimized to obtain the target exploration map data.

5. The method according to claim 4, characterized in that, The first environment exploration data is processed using keyframe-based map building to obtain the first exploration map data, which includes: The first environment exploration data is processed by keyframe extraction to obtain first environment keyframe data, wherein the first environment keyframe data is keyframe data used to represent the construction of a first unknown area map; The first environment keyframe data is processed by a map building algorithm to obtain the first environment map data, wherein the first environment map data is map data used to represent the environment of the first unknown area. The first environmental map data and the initial map data are subjected to map update processing based on keyframe matching to obtain the first exploration map data, wherein the first exploration map data is robot map data used to represent a first unknown area.

6. A robotic autonomous exploration device, characterized in that, include: The data acquisition module is used to acquire data to be processed, wherein the data to be processed includes start point data and end point data, the start point data is data used to represent the robot's start point, and the end point data is data used to represent the robot's end point; The exploration point module is used to perform exploration point generation processing on the starting point data and the ending point data to obtain exploration point data, wherein the exploration point data is data used to represent exploration points in unknown areas of the robot; The exploration path module is used to process the exploration point data to generate exploration paths, thereby obtaining exploration path data, wherein the exploration path data is data used to represent the robot's running path in an unknown area; The exploration point data is identified to obtain first exploration point data and second exploration point data; a first exploration path generation process is performed on the starting point data and the first exploration point data to obtain first exploration path data; a second exploration path generation process is performed on the second exploration point data and the ending point data to obtain second exploration path data; a third exploration path generation process is performed on the first exploration point data and the second exploration point data to obtain third exploration path data; and the exploration path data is obtained based on the first exploration path data, the second exploration path data, and the third exploration path data. The third exploration path generation process includes: the adjacent process exploration of any process exploration point includes a first adjacent process exploration point and a second adjacent process exploration point. The first adjacent process exploration point is the preceding adjacent exploration point of the process exploration point, and the second adjacent process exploration point is the following adjacent exploration point of the process exploration point. The robot's exploration point operation sequence during the autonomous exploration process is the first adjacent process exploration point, the process exploration point, and the second adjacent process exploration point. A first reciprocating exploration path based on a preset reciprocating path distance is generated based on the process exploration point and the first adjacent process exploration point. A non-reciprocating exploration path is generated based on the process exploration point and the second adjacent process exploration point. Based on the path direction determined by the process exploration point and the second adjacent process exploration point, a second reciprocating exploration path based on a preset path distance is generated at the second adjacent process exploration point. The third exploration path data is obtained based on the first reciprocating exploration path, the non-reciprocating exploration path, and the second reciprocating exploration path. An exploration data acquisition module is used to acquire environmental exploration data, wherein the environmental exploration data is used to represent environmental data of unknown areas collected by the robot based on the exploration path data; The map building module performs map building processing on the environmental exploration data to obtain target exploration map data, wherein the target exploration map data is map data used to represent unknown areas.

7. The apparatus according to claim 6, characterized in that, The exploration point module includes: The identification module is used to identify the data to be processed and obtain initial map data, wherein the initial map data is map data used to represent the initial area of ​​the robot; The first exploration point module is used to perform exploration point generation processing on the initial map data and the starting point data to obtain the first exploration point data; The second exploration point module is used to perform exploration point generation processing on the first exploration point data and the termination point data to obtain the second exploration point data. An exploration point generation module is used to obtain the exploration point data based on the first exploration point data and the second exploration point data.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the autonomous exploration method of the robot according to any one of claims 1-5.

9. 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, the computer program being executed by the at least one processor to cause the at least one processor to perform the robot autonomous exploration method according to any one of claims 1-5.

Images