Method, device, robot and storage medium for determining target point

Abstract

The present invention relates to the technical field of indoor robots, and discloses a method, device, robot, and storage medium for determining a target point. The method includes: determining environmental state data and robot state data; determining at least one type of target evaluation value for at least one candidate target point according to the environmental state data and the robot state data; wherein the target evaluation value includes an environmental feedback value, an information gain value, and a path cost value; and selecting a mapping target point from the candidate target points according to at least one type of target evaluation value of at least one candidate target point. The present invention can improve the efficiency of autonomous mapping and dynamic adaptability.

Description

Technical Field

[0001] The present invention relates to the technical field of indoor robots, and particularly to a method and device for determining target points, a robot, and a storage medium. Background Art

[0002] An indoor robot is an intelligent robot that can operate autonomously or semi-autonomously in an indoor environment and perform various tasks, and has a wide range of applications in the fields of housework cleaning, transportation services, and security monitoring.

[0003] During the process of autonomous map building, an indoor robot senses and detects the surrounding environment through sensors carried by itself, and then uses algorithms to process and analyze the acquired data to construct an environmental map. In the autonomous map building technology, algorithms are then used to process and analyze the acquired data to construct an environmental map. In the autonomous map building technology, target selection and path planning are the core links to ensure that the robot can effectively complete tasks. The existing autonomous map building methods usually select target points based on grid maps or environmental features, and then perform navigation according to the selected target points combined with path planning strategies. This way of selecting target points depends on the current positioning information of the robot and the existing environmental map, and can work well in static or known environments. However, in a dynamic and complex environment, it lacks flexible adaptability and easily leads to an inefficient or redundant exploration process in autonomous map building. Summary of the Invention

[0004] The present invention provides a method and device for determining target points, a robot, and a storage medium to improve the efficiency and dynamic adaptability of autonomous map building.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining a target point, the method comprising:

[0006] Determine environmental state data and robot state data;

[0007] Determine at least one target point evaluation value of at least one candidate target point according to the environmental state data and the robot state data;

[0008] Wherein, the target point evaluation value includes an environmental feedback value, an information gain value, and a path cost value;

[0009] Select a map building target point from the candidate target points according to at least one target point evaluation value of at least one candidate target point.

[0010] In a second aspect, an embodiment of the present invention further provides a device for determining a target point, the device comprising:

[0011] A data determination module for determining environmental state data and robot state data;

[0012] A target evaluation value determination module, configured to determine at least one target evaluation value of at least one candidate target point according to the environmental state data and the robot state data;

[0013] Wherein, the target evaluation value includes an environmental feedback value, an information gain value, and a path cost value;

[0014] A mapping target point determination module, configured to select a mapping target point from the candidate target points according to at least one target evaluation value of at least one candidate target point.

[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method for determining a target point as described in any one of the embodiments of the present invention.

[0016] In a fourth aspect, an embodiment of the present invention further provides a storage medium storing computer-executable instructions, and the computer-executable instructions are used to execute the method for determining a target point as described in any one of the embodiments of the present invention when executed by a computer processor.

[0017] The technical solution of the embodiment of the present invention obtains environmental state data and robot state data in real time, and determines at least one target evaluation value of candidate target points according to the environmental state data and the robot state data, including: an environmental feedback value, an information gain value, and a path cost value, and then selects a mapping target point from each candidate target point according to at least one target evaluation value of each candidate target point. It solves the problem that the method of selecting target points depending on the current positioning information of the robot and the existing environmental map in the prior art cannot flexibly adapt to a dynamic and complex environment, and easily leads to inefficiency or redundant exploration in the autonomous mapping process. The technical solution of the embodiment of the present invention can improve the efficiency of autonomous mapping and dynamic adaptability.

[0018] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1It is a flowchart of a method for determining a target point provided in Embodiment 1 of the present invention;

[0021] Figure 2 It is a flowchart of a method for determining a target point provided in Embodiment 2 of the present invention;

[0022] Figure 3 It is a schematic structural diagram of a device for determining a target point provided in Embodiment 3 of the present invention;

[0023] Figure 4 It is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present invention. Detailed implementation manners

[0024] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices. In the embodiments of the present application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned, and they should be considered exemplary. The purpose is only to illustrate the feasibility in the implementation of the technical solution of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0026] In the technical solution of the present application, the acquisition, transmission, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations.

[0027] Embodiment 1

[0028] Figure 1The following is a flowchart of a method for determining a target point provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of selecting a target point during the autonomous mapping process of an indoor robot. This method can be executed by a target point determination device, which can be implemented in the form of hardware and / or software, and the target point determination device can be configured in the robot.

[0029] As Figure 1 shown, the method includes:

[0030] S110. Determine environmental state data and robot state data.

[0031] Among them, the environmental state data may include map information, obstacle information, etc. The map information refers to the currently known environmental map information, and the obstacle information refers to the detected static or dynamic obstacle information in the environment. The environmental state data can be collected in real time by the robot through devices such as sensors (such as lidar sensors, depth cameras, and IMUs (Inertial Measurement Units)).

[0032] The robot state data refers to the current position and attitude of the robot, and the robot state data can also be collected through the robot's sensors.

[0033] In this embodiment, by collecting environmental state data and robot state data in real time, the environmental changes around the robot can be perceived in real time, so as to select subsequent target points according to the dynamic changes of the environment.

[0034] S120. Determine at least one target evaluation value of at least one candidate target point according to the environmental state data and the robot state data.

[0035] Among them, the candidate target points can be determined through the known environmental map information. Exemplarily, the boundary points of the known environmental map or the position points with obvious features can be used as candidate target points. In this embodiment, the candidate target points can be represented in the form of a point set, for example, T = {T 1 , T 2 , … T n}.

[0036] Among them, the target evaluation value is used to represent the priority or selection adaptability of the candidate target point, and the target evaluation value may include an environmental feedback value, an information gain value, and a path cost value.

[0037] Among them, the environmental feedback value is used to represent the feedback degree or influence degree of the dynamic environmental change on the candidate target point. The larger the environmental feedback value of the candidate target point, the lower the priority of this candidate target point, and the less suitable it is to be selected for the next path planning; on the contrary, the smaller the environmental feedback value of the candidate target point, the higher the priority of this candidate target point, and the more suitable it is to be selected for the next path planning.

[0038] By determining the environmental feedback value of the candidate target point, the selection of the subsequent mapping target point can reflect the response to the environmental state change in real time, thereby improving the dynamic adaptability of autonomous mapping.

[0039] The information gain value is used to measure the contribution of the robot's exploration of the area where the candidate target point is located to the mapping accuracy. Information gain refers to the new amount of information that can be obtained by exploring the area where the candidate target point is located, so as to improve the map accuracy or update the known map. The larger the information gain value of the candidate target point, the higher the priority of this candidate target point, and the more suitable it is to be selected for the next path planning; on the contrary, the smaller the information gain value of the candidate target point, the lower the priority of this candidate target point, and the less suitable it is to be selected for the next path planning.

[0040] By determining the information gain value of the candidate target point, the contribution of each candidate target point to the mapping accuracy and integrity can be quantitatively evaluated. When selecting the subsequent mapping target point, a candidate target point that is more valuable to the map can be selected for exploration, thereby improving the mapping efficiency and effectively improving the accuracy and integrity of the map.

[0041] The path cost value is used to measure the path cost corresponding to the planned path from the current position of the robot to the candidate target point after the robot selects the candidate target point, and can be determined by factors such as the length of the planned path, the time required for the robot to travel, and the energy consumption required for the robot to travel. The larger the path cost value of the candidate target point, the lower the priority of this candidate target point, and the less suitable it is to be selected for the next path planning; on the contrary, the smaller the path cost value of the candidate target point, the higher the priority of this candidate target point, and the more suitable it is to be selected for the next path planning.

[0042] By determining the path cost value of the candidate target point, the collaborative work of target point selection and path planning is realized, unnecessary path exploration is saved, the resource consumption of robot movement and calculation is saved, and the efficiency of the mapping process is improved.

[0043] In this embodiment, through the evaluation of different dimensions such as environmental feedback, information gain, and path cost of the candidate target point, a multi-dimensional and quantitative evaluation of the candidate target point is realized, the priority of each candidate target point can be comprehensively evaluated, the limitation of the single target point selection method is avoided, the efficiency and accuracy of target point selection are improved, and thus the mapping efficiency and accuracy of the robot are improved.

[0044] S130. Select mapping target points from the candidate target points according to at least one type of target evaluation value of at least one candidate target point.

[0045] Among them, the mapping target point refers to the target point selected from the candidate target points that is most suitable for subsequent exploration and mapping.

[0046] In this embodiment, when selecting mapping target points from the candidate target points, it can be based on one of the environmental feedback value, information gain value, and path cost value, or a combination of two or more.

[0047] In an alternative embodiment, when the target evaluation value is one of the environmental feedback value, information gain value, and path cost value, the candidate target points can be sorted according to the magnitude of the target evaluation value of each candidate target point, and the candidate target point corresponding to the maximum value or the minimum value is selected as the mapping target point.

[0048] Exemplarily, taking the target evaluation value as the environmental feedback value as an example for illustration. Specifically, the smaller the environmental feedback value of the candidate target point, the higher the priority of the candidate target point, and the more suitable it is to be selected for the next path planning. Therefore, the candidate target points can be sorted in ascending order of the environmental feedback value, and the candidate target point with the smallest environmental feedback value is selected as the mapping target point. Correspondingly, if the target evaluation value is the information gain value, the candidate target points are sorted in descending order of the information gain value, and the candidate target point with the largest information gain value is selected as the mapping target point. And if the target evaluation value is the path cost value, the candidate target points can be sorted in ascending order of the path cost value, and the candidate target point with the smallest path cost value is selected as the mapping target point.

[0049] In another alternative embodiment, when the target evaluation value is two of the environmental feedback value, information gain value, and path cost value, the product / quotient / sum or difference of the two different target evaluation values can be calculated, and then the product / quotient / sum or difference is sorted, and the candidate target point corresponding to the maximum value or the minimum value is selected as the mapping target point.

[0050] Exemplarily, taking the environmental feedback value and the information gain value as the target evaluation values as an example, selecting the mapping target point from the candidate target points according to at least one target evaluation value of at least one candidate target point may include: determining the ratio of the information gain value to the environmental feedback value of each candidate target point, and determining the mapping target point according to the ratios of each candidate target point. Since the information gain value is proportional to the priority of the candidate target point, and the environmental feedback value is inversely proportional to the priority of the candidate target point, therefore, in this embodiment, the ratio (i.e., quotient) of the information gain value to the environmental feedback value is taken as the basis for selecting the candidate target point. Sort the ratios in descending order, and select the candidate target point with the largest ratio as the mapping target point.

[0051] Correspondingly, if the target evaluation value is the information gain value and the path cost value, it is possible to determine the ratio of the information gain value to the path cost value of each candidate target point, sort the ratios in descending order, and select the candidate target point with the largest ratio as the mapping target point. And, if the target evaluation value is the environmental feedback value and the path cost value, since both the environmental feedback value and the path cost value are inversely proportional to the priority of the candidate target point, therefore, it is possible to determine the product of the environmental feedback value and the path cost value of each candidate target point, sort the products in ascending order, and select the candidate target point with the smallest product as the mapping target point.

[0052] Exemplarily, when the target evaluation value is the environmental feedback value and the information gain value, it is also possible to determine the difference between the product of the information gain value of each candidate target point and the information gain weight and the environmental feedback value, sort the differences in descending order, and select the candidate target point with the largest difference as the mapping target point. Among them, the information gain weight is used to balance the environmental feedback value and the information gain value.

[0053] Correspondingly, if the target evaluation value is the information gain value and the path cost value, selecting the mapping target point from the candidate target points according to at least one target evaluation value of at least one candidate target point may further include: determining the difference between the product of the information gain value of each candidate target point and the information gain weight and the path cost value, and determining the mapping target point according to the differences of each candidate target point. Specifically, sort the differences in descending order, and select the candidate target point with the largest difference as the mapping target point. At this time, the goal of target point selection is to minimize the path cost and maximize the information gain, so as to optimize the target point selection and path planning at the same time.

[0054] If the target evaluation value is the environmental feedback value and the path cost value, it is possible to determine the sum of the environmental feedback value and the path cost value of each candidate target point, sort the sum values in ascending order, and select the candidate target point with the smallest sum value as the mapping target point.

[0055] In yet another alternative embodiment, when the target evaluation value is a combination of the environmental feedback value, the information gain value, and the path cost value, selecting a mapping target point from the candidate target points according to at least one target evaluation value of at least one candidate target point may further include: performing a weighted sum of the environmental feedback value, the information gain value, and the path cost value of each candidate target point to obtain a sum value, and determining the mapping target point according to the sum value of each candidate target point; wherein, the environmental feedback weight and the path cost weight are negative values, and the sum of the absolute value of the environmental feedback weight, the information gain weight, and the absolute value of the path cost weight is 1.

[0056] Since the information gain value is proportional to the priority of the candidate target point, and the environmental feedback value and the path cost value are inversely proportional to the priority of the candidate target point, therefore, when performing a weighted sum of the three, the weights of the environmental feedback value and the path cost value are both negative values. When determining the mapping target point according to the sum value of each candidate target point, sort the sum values in descending order, and select the candidate target point with the largest sum value as the mapping target point.

[0057] Exemplarily, when the target evaluation value is a combination of the environmental feedback value, the information gain value, and the path cost value, it is also possible to calculate the product of the environmental feedback value and the path cost value of each candidate target point, then calculate the quotient of the information gain value and the product, and sort in descending order according to the quotient, and select the candidate target point with the largest quotient as the mapping target point.

[0058] It should be noted that when there are at least two target evaluation values, when selecting a mapping target point by combining different target evaluation values, it is necessary to first perform a normalization process on different target evaluation values to improve the accuracy of target point selection.

[0059] The technical solution of the embodiment of the present invention, by obtaining environmental state data and robot state data in real time, and determining at least one target evaluation value of the candidate target point according to the environmental state data and the robot state data, including: environmental feedback value, information gain value, and path cost value, and then selecting a mapping target point from each candidate target point according to at least one target evaluation value of each candidate target point. It solves the problem that the method of selecting target points in the prior art relying on the current positioning information of the robot and the existing environmental map cannot flexibly adapt to a dynamic and complex environment, and easily leads to inefficiency or redundant exploration in the autonomous mapping process. The technical solution of the embodiment of the present invention can improve the efficiency and dynamic adaptability of autonomous mapping.

[0060] Embodiment 2

[0061] Figure 2It is a flowchart of a method for determining a target point provided in the second embodiment of the present invention. On the basis of the above embodiments, the present invention further specifies the determination processes of the environmental feedback value, the information gain value, and the path cost value.

[0062] As Figure 2 shown, the method includes:

[0063] S210. Determine the environmental state data and the robot state data.

[0064] S220. Determine the environmental feedback change value within the time interval between the current moment and the initial moment according to the environmental state data and the robot state data.

[0065] Wherein, the environmental feedback change value is determined according to the change in the distance from the candidate target point to the robot at the current moment and the initial moment, the change in the obstacle density matching the candidate target point at the current moment and the initial moment, and the environmental dynamic factor of the candidate target point at the current moment compared to the initial moment.

[0066] Wherein, the environmental feedback change value is the feedback change caused by the environmental state change (such as obstacle movement, target point change, etc.) at the current moment compared to the initial moment. The obstacle density matching the candidate target point can be represented by the number of obstacles within a region centered on the candidate target point with a preset distance. Specifically, taking the acquisition of point cloud data by a lidar as an example, it can be determined whether there are obstacles around the candidate target point by the number of point clouds, and the number of obstacles within a region centered on the candidate target point with a preset distance can be calculated. The environmental dynamic factor of the candidate target point at the current moment compared to the initial moment is used to represent the degree of environmental dynamic change of the candidate target point at the current moment compared to the initial moment. The environmental dynamic factor of the candidate target point at the current moment compared to the initial moment can be represented by the change in obstacles (such as the sum or average value of the displacements of each obstacle) within a region centered on the candidate target point with a preset distance at the current moment compared to the initial moment, or can also be represented by the change in point clouds within a region centered on the candidate target point with a preset distance at the current moment compared to the initial moment.

[0067] Specifically, the environmental feedback change value can be represented by the following formula: , is used to represent the change value of the distance from the candidate target point to the robot at the current moment and the initial moment, is used to represent the change value of the obstacle density matching the candidate target point at the current moment and the initial moment, is used to represent the environmental dynamic factor of the candidate target point at the current moment compared to the initial moment, , and represent weight coefficients, which are used to balance the influence of various factors on the environmental feedback change value.

[0068] S230. Determine the environmental feedback value of the candidate target point according to the initial environmental feedback value of the candidate target point at the initial moment and the environmental feedback change value.

[0069] Among them, the initial environmental feedback value is determined according to the distance from the candidate target point to the robot at the initial moment, the obstacle density matched with the candidate target point at the initial moment, and the environmental dynamic factor matched with the candidate target point at the initial moment.

[0070] Specifically, the initial environmental feedback value can be expressed by the following formula: , where represents the distance from the candidate target point to the robot at the initial moment, represents the obstacle density matched with the candidate target point at the initial moment, represents the environmental dynamic factor matched with the candidate target point at the initial moment.

[0071] The environmental feedback value of the candidate target point can be expressed by the sum of the initial environmental feedback value of the candidate target point at the initial moment and the environmental feedback change value.

[0072] In this embodiment, by real-time sensing the environmental feedback change and performing real-time update of the environmental feedback value, the selection of the target point can respond to the dynamic change of the environment in real time, ensuring the dynamic adaptability of autonomous mapping and avoiding inefficient redundant exploration.

[0073] S240. Determine the current map entropy according to the environmental state data and the robot state data.

[0074] Among them, the current map entropy is used to represent the uncertainty, information chaos degree, or fuzziness of the current map. When the map is represented in different forms, there are different calculation methods for the current map entropy. Taking the map represented in the form of a grid map as an example, the map is divided into small grid cells. For each grid, according to the environmental state data and the robot state data, determine the probability that it is occupied, free, or unknown. For example, through lidar measurement, if an obstacle is detected at a certain grid position, the probability that the grid is occupied will increase. Assume P i represents the probability that the i-th grid is occupied, and 1 - P i is the probability that the grid is free. For the unknown state, an initial probability can be assigned according to certain rules. Finally, the current map entropy can be calculated by the formula: . This embodiment does not limit the specific method for calculating the current map entropy.

[0075] S250. Determine the map conditional entropy that matches the candidate target point.

[0076] The map conditional entropy refers to the conditional entropy of the map if the robot selects the candidate target point.

[0077] Specifically, taking the map represented in the form of a grid map as an example, calculate the joint probability P(M i , T) of each grid i being in different states (occupied / free / unknown) under the condition of selecting the candidate target point, which can be estimated specifically according to the environmental state data and the prior knowledge of the environment; calculate the conditional probability distribution according to the joint probability distribution , where is the probability of the candidate target point appearing; finally, calculate the map conditional entropy that matches the candidate target point through the conditional entropy formula: .

[0078] S260. Take the difference between the current map entropy and the map conditional entropy as the information gain value of the candidate target point.

[0079] The difference between the current map entropy and the map conditional entropy when the robot selects the candidate target point is the information gain value of the candidate target point. The larger the difference, the greater the improvement in the map accuracy and integrity by selecting this candidate target point. Incorporating the information gain into the selection of the target point can ensure that the target area with the greatest improvement in mapping accuracy and integrity is preferentially selected, effectively improving the map accuracy and integrity and significantly enhancing the mapping efficiency.

[0080] S270. Determine a candidate path that matches the candidate target point according to the environmental state data and the robot state data.

[0081] In this embodiment, a conventional path planning method can be used to determine the planned path for the robot to reach the candidate target point as the candidate path that matches the candidate target point.

[0082] In this embodiment, collaborative optimization of path planning and target selection can ensure that when the robot selects a target point, the path planning is optimized simultaneously, avoiding path redundancy and unnecessary detours.

[0083] S280. Determine the path cost value according to at least one path parameter of the candidate path.

[0084] Among them, the path parameters include path length, time consumption, and robot energy consumption. The path length refers to the length of the candidate path, the time consumption refers to the time required for the robot to travel from the current position along the candidate path to the candidate target point, which can be calculated according to the path length and the average speed of the robot, and the robot energy consumption can be calculated according to the time consumption and the average energy consumption during the robot's movement.

[0085] Determine the path cost value according to the path parameter. Specifically, weighted summation can be performed on the path length, time consumption, and robot energy consumption, and this embodiment does not limit this.

[0086] In this embodiment, by calculating the path cost value, collaborative optimization of target point selection and path planning is achieved, unnecessary exploration paths are reduced, resource consumption of robot movement and calculation is saved, and the overall efficiency of robot autonomous mapping is improved.

[0087] S290. Perform weighted summation on the environmental feedback value, information gain value, and path cost value of each candidate target point to obtain a summation value, and determine the mapping target point according to the summation value of each candidate target point.

[0088] Among them, the environmental feedback weight and the path cost weight are negative values, and the sum of the absolute value of the environmental feedback weight, the information gain weight, and the absolute value of the path cost weight is 1.

[0089] The specific process of performing weighted summation according to the environmental feedback value, information gain value, and path cost value and determining the mapping target point based on the summation value has been described in the above embodiments, and this embodiment will not be elaborated here.

[0090] The technical solution of this embodiment, when there are multiple candidate target points, reflects the response of candidate target points to environmental dynamic changes through the calculation of the environmental feedback value, making the selection of target points have dynamic adaptability. Through the calculation of the information gain value, the contribution of each candidate target point to the improvement of mapping accuracy and integrity is evaluated, enabling the selection of target points to combine information gain to ensure that the target area with the greatest improvement in mapping accuracy is preferentially selected, effectively improving the accuracy and integrity of the map. Through the calculation of the path cost value, collaborative work of target point selection and path planning is achieved, unnecessary exploration paths are reduced, resource consumption of robot movement and calculation is saved, and the overall efficiency in the mapping process is improved. Through continuous priority evaluation of multiple candidate target points, selection of mapping target points, path planning, and real-time feedback, the robot can intelligently select among multiple target points, avoid inefficient redundant exploration, and make adjustments according to real-time feedback. At the same time, after exploring the mapping target point, the map data can be continuously updated, and thus the above process can be continuously carried out, finally completing the autonomous mapping task, improving the mapping efficiency while also improving the accuracy and integrity of the map.

[0091] Embodiment III

[0092] Figure 3 This is a schematic structural diagram of a device for determining a target point provided in Embodiment III of the present invention. As Figure 3 shown, the device includes:

[0093] A data determination module 310, configured to determine environmental state data and robot state data;

[0094] A target point evaluation value determination module 320, configured to determine at least one target point evaluation value of at least one candidate target point according to the environmental state data and the robot state data;

[0095] Wherein, the target point evaluation value includes an environmental feedback value, an information gain value, and a path cost value;

[0096] A mapping target point determination module 330, configured to select a mapping target point from the candidate target points according to at least one target point evaluation value of at least one candidate target point.

[0097] The technical solution of the embodiment of the present invention obtains environmental state data and robot state data in real time, and determines at least one target point evaluation value of candidate target points according to the environmental state data and the robot state data, including: an environmental feedback value, an information gain value, and a path cost value, and then selects a mapping target point from each candidate target point according to at least one target point evaluation value of each candidate target point. It solves the problem that the method of selecting target points depending on the current positioning information of the robot and the existing environmental map in the prior art cannot flexibly adapt to a dynamic and complex environment, and easily leads to an inefficient or redundant exploration process in the autonomous mapping process. The technical solution of the embodiment of the present invention can improve the efficiency of autonomous mapping and dynamic adaptability.

[0098] Based on the above embodiment, optionally, the target point evaluation value determination module 320 includes:

[0099] An environmental feedback change value determination unit, configured to determine an environmental feedback change value within a time interval between the current moment and the initial moment according to the environmental state data and the robot state data;

[0100] Wherein, the environmental feedback change value is determined according to the change in the distance from the candidate target point to the robot at the current moment and the initial moment, the change in the obstacle density matching the candidate target point at the current moment and the initial moment, and the environmental dynamic factor of the candidate target point at the current moment compared with the initial moment.

[0101] An environmental feedback value determination unit, configured to determine the environmental feedback value of the candidate target point according to the initial environmental feedback value of the candidate target point at the initial moment and the environmental feedback change value.

[0102] Wherein, the initial environmental feedback value is determined according to the distance from the candidate target point to the robot at the initial moment, the obstacle density matching the candidate target point at the initial moment, and the environmental dynamic factor matching the candidate target point at the initial moment.

[0103] Based on the above embodiments, optionally, the target evaluation value determination module 320 includes:

[0104] A current map entropy determination unit, configured to determine the current map entropy according to the environmental state data and the robot state data;

[0105] A map conditional entropy determination unit, configured to determine the map conditional entropy matching the candidate target point;

[0106] An information gain value determination unit, configured to use the difference between the current map entropy and the map conditional entropy as the information gain value of the candidate target point.

[0107] Based on the above embodiments, optionally, the target evaluation value determination module 320 includes:

[0108] A candidate path determination unit, configured to determine a candidate path matching the candidate target point according to the environmental state data and the robot state data;

[0109] A path cost value determination unit, configured to determine the path cost value according to at least one path parameter of the candidate path;

[0110] Wherein, the path parameters include path length, time consumption, and robot energy consumption.

[0111] Based on the above embodiments, optionally, the map building target point determination module 330 includes:

[0112] A first map building target point determination unit, configured to determine the ratio of the information gain value of each candidate target point to the environmental feedback value, and determine the map building target point according to the ratios of each candidate target point.

[0113] Based on the above embodiments, optionally, the map building target point determination module 330 includes:

[0114] A second map building target point determination unit, configured to determine the difference between the product of the information gain value of each candidate target point and the information gain weight and the path cost value, and determine the map building target point according to the differences of each candidate target point.

[0115] Based on the above embodiments, optionally, the map building target point determination module 330 includes:

[0116] A third map building target point determination unit, configured to perform weighted summation on the environmental feedback value, information gain value, and path cost value of each candidate target point to obtain a summation value, and determine the map building target point according to the summation values of each candidate target point;

[0117] Among them, the environmental feedback weight and the path cost weight are negative values, and the sum of the absolute value of the environmental feedback weight, the information gain weight, and the absolute value of the path cost weight is 1.

[0118] The target point determination device provided by the embodiments of the present invention can execute the target point determination method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0119] Embodiment 4

[0120] Figure 4 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0121] As Figure 4 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0122] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0123] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for determining the target point.

[0124] In some embodiments, the method for determining the target point can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining the target point described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for determining the target point by any other suitable means (e.g., by means of firmware).

[0125] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), system-on-a-chip systems (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0126] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0127] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0128] In order to provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0129] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0130] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0131] It should be understood that various forms of processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0132] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for determining a target point, characterized in that: include: Determine environment state data and robot state data; Determine a target evaluation value of at least one candidate target point according to the environmental state data and the robot state data; The target review value includes at least two of the following: environmental feedback value, information gain value, and path cost value, and the target review value must at least include the environmental feedback value; Wherein, determining the environmental feedback value of at least one candidate target point according to the environmental state data and the robot state data comprises: Determine, according to the environmental state data and the robot state data, an environmental feedback change value within a time interval between a current moment and an initial moment; The environmental feedback change value is determined according to the change of the distance from the candidate target point to the robot at the current moment and the initial moment, the change of the obstacle density matching the candidate target point at the current moment and the initial moment, and the environmental dynamic factor of the candidate target point at the current moment compared with the initial moment; Determining the environmental feedback value of the candidate target point according to the initial environmental feedback value of the candidate target point at the initial moment and the environmental feedback change value; The initial environmental feedback value is determined based on the distance from the candidate target point to the robot at the initial moment, the obstacle density matching the candidate target point at the initial moment, and the environmental dynamic factor matching the candidate target point at the initial moment; A mapping target point is selected from the candidate target points according to at least two target review values ​​of at least one candidate target point.

2. The method for determining a target point according to claim 1, characterized in that: Determining an information gain value of at least one candidate target point according to the environment state data and the robot state data, comprising: Determining a current map entropy according to the environment state data and the robot state data; Determine the map condition entropy matching the candidate target point; The difference between the current map entropy and the map conditional entropy is used as the information gain value of the candidate target point.

3. The method for determining a target point according to claim 1, characterized in that: Determining a path cost value of at least one candidate target point according to the environment state data and the robot state data includes: Determining a candidate path matching a candidate target point according to the environment state data and the robot state data; Determining a path cost value according to at least one path parameter of the candidate path; The path parameters include path length, time consumption and robot energy consumption.

4. The method for determining a target point according to any one of claims 1 to 3, characterized in that: According to at least two target evaluation values ​​of at least one candidate target point, a mapping target point is selected from the candidate target points, including: Determine the ratio of the information gain value to the environmental feedback value of each candidate target point, and determine the mapping target point based on the ratio of each candidate target point.

5. The method for determining a target point according to any one of claims 1 to 3, characterized in that: According to at least two target evaluation values ​​of at least one candidate target point, a mapping target point is selected from the candidate target points, including: Perform weighted summation on the environmental feedback value, information gain value, and path cost value of each candidate target point to obtain a sum value, and determine the mapping target point based on the sum value of each candidate target point; Among them, the environmental feedback weight and the path cost weight are negative values, and the sum of the absolute value of the environmental feedback weight, the information gain weight, and the absolute value of the path cost weight is 1.

6. A device for determining a target point, characterized in that: include: A data determination module, used for determining environment state data and robot state data; A target review value determination module, used to determine the target review value of at least one candidate target point according to the environmental state data and the robot state data; The target review value includes at least two of the following: environmental feedback value, information gain value, and path cost value, and the target review value must at least include the environmental feedback value; The target review value determination module includes: An environment feedback change value determination unit, used to determine the environment feedback change value within the time interval between the current moment and the initial moment according to the environment state data and the robot state data; The environmental feedback change value is determined according to the change of the distance from the candidate target point to the robot at the current moment and the initial moment, the change of the obstacle density matching the candidate target point at the current moment and the initial moment, and the environmental dynamic factor of the candidate target point at the current moment compared with the initial moment; An environment feedback value determination unit, used to determine the environment feedback value of the candidate target point according to the initial environment feedback value of the candidate target point at the initial moment and the environment feedback change value; The initial environmental feedback value is determined based on the distance from the candidate target point to the robot at the initial moment, the obstacle density matching the candidate target point at the initial moment, and the environmental dynamic factor matching the candidate target point at the initial moment; The mapping target point determination module is used to select a mapping target point from the candidate target points according to at least two target evaluation values ​​of at least one candidate target point.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for determining a target point as described in any one of claims 1 to 5 is implemented.

8. A storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to perform the target point determination method according to any one of claims 1 to 5.

Images