Redundant motion planning method of wheel arm based on artificial intelligence

Abstract

The present invention discloses a wheel arm redundant motion planning method based on artificial intelligence, which belongs to the technical field of motion planning; data integration calculation and analysis are performed on each overall implementation of a robot wheel arm redundant motion planning scheme according to a processed and acquired local planning monitoring processing set, and a single overall planning state of the robot wheel arm redundant motion planning scheme is digitally represented and classified from an overall dimension; single overall planning state data corresponding to different implementations of the robot wheel arm redundant motion planning scheme are integrated and analyzed to determine the planning implementation reliability state corresponding to the robot wheel arm redundant motion planning scheme, and dynamically optimize and manage the robot wheel arm redundant motion planning scheme adaptively according to the planning implementation reliability state; the present invention is used to solve the technical problems of poor autonomous supervision and analysis effect and poor adaptive planning optimization management effect of the robot wheel arm redundant motion planning scheme implementation in the existing scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of motion planning, and particularly to a redundant motion planning method for a wheel-arm based on artificial intelligence. Background Art

[0002] The redundant motion of a robot's wheel-arm generally refers to the use of redundant degrees of freedom in a robot system, especially in composite robots that combine a mobile platform (such as a wheeled base) and a robotic arm, to optimize the motion path, improve flexibility, and obstacle avoidance capabilities; this design allows the robot to complete tasks in multiple ways, thus providing more operation options and higher efficiency.

[0003] When implementing existing redundant motion planning schemes for a robot's wheel-arm, it is not possible to conduct regulatory analysis and evaluation from different aspects on the implementation effects of different planning of existing redundant motion planning schemes for a robot's wheel-arm, and determine the corresponding planning implementation status of existing redundant motion planning schemes for a robot's wheel-arm based on the evaluation results and implement targeted optimization management. There are problems with poor autonomous regulatory analysis effects and poor adaptive planning optimization management effects in the implementation of redundant motion planning schemes for a robot's wheel-arm. Summary of the Invention

[0004] The purpose of the present invention is to provide a redundant motion planning method for a wheel-arm based on artificial intelligence, which is used to solve the technical problems of poor autonomous regulatory analysis effects and poor adaptive planning optimization management effects in the implementation of redundant motion planning schemes for a robot's wheel-arm in existing schemes.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A redundant motion planning method for a wheel-arm based on artificial intelligence includes:

[0007] Monitoring and statistics of different aspects of planning processing for each implementation of a redundant motion planning scheme for a robot's wheel-arm, performing data processing and analysis combination of local planning on the monitoring and statistical data of different aspects of planning processing, and obtaining a local planning monitoring processing set;

[0008] Among them, when performing local monitoring, statistics, processing, and analysis on the effectiveness of pre-planning for each implementation of a redundant motion planning scheme for a robot's wheel-arm, all planned angles JGi corresponding to different joints of the robot's wheel-arm at different planning timestamps are obtained, and the all planned angles corresponding to different joints are sequentially analyzed through the planned angle recognition function for data analysis, and the angle planning effective identifier JGBij corresponding to different planned angles is output; where i is different joints of the robot's wheel-arm, i = 1, 2, 3,..., n; n is a positive integer; j is the number of planned actions corresponding to different planned angles, j = 1, 2, 3,..., m; m is a positive integer;

[0009] The angle planning valid flag contains a value of 0 or 1, indicating whether the corresponding planned angle is valid or invalid;

[0010] Sort and combine all the angle planning valid flags obtained by corresponding processing of different joints of the robot arm to obtain the angle planning processing sequences corresponding to different joints of the robot arm;

[0011] According to the locally planned monitoring processing set obtained by processing, perform data integration calculation and analysis on each overall implementation of the redundant motion planning scheme of the robot arm to obtain the single - time overall planning status data;

[0012] Integrate and analyze the single - time overall planning status data corresponding to different implementations of the redundant motion planning scheme of the robot arm, determine the reliable status of the planned implementation corresponding to the redundant motion planning scheme of the robot arm, and perform dynamic optimization management on the redundant motion planning scheme of the robot arm adaptively according to the reliable status of the planned implementation.

[0013] Preferably, the expression of the planned angle recognition function is ; in the formula, JG min ij, JG max ij are the minimum operating angle and the maximum operating angle corresponding to different joints respectively.

[0014] Preferably, traverse and analyze the angle planning processing sequences corresponding to different joints of the robot arm in turn. If all the elements in the angle planning processing sequence are 0, set the angle planning valid value associated with the arm joint to 0;

[0015] If there are non - zero elements in the angle planning processing sequence, set the angle planning valid value associated with the arm joint to N; N is the total number of non - zero elements in the angle planning processing sequence;

[0016] Sort and combine the angle planning valid values associated with all arm joints to obtain the angle planning valid recognition sequence.

[0017] Preferably, when performing local monitoring statistics and processing analysis on the mid - term planning effectiveness of each implementation of the redundant motion planning scheme of the robot arm, monitor and obtain all the obstacles identified during the implementation of the redundant motion planning of the robot arm, as well as the corresponding obstacle types, recognition discovery timestamps, recognition processing end timestamps, and obstacle recognition interval distances of all obstacles;

[0018] Traverse and match different obstacle types with the pre - constructed obstacle type impact table to obtain the corresponding obstacle type impact flags, and calculate the obstacle processing duration corresponding to different obstacles according to the recognition discovery timestamp and the recognition processing end timestamp;

[0019] Sort and combine the obstacle type influence identifier, obstacle handling duration, and obstacle recognition interval distance obtained by corresponding processing of obstacles to obtain a single obstacle recognition and processing sequence;

[0020] Sort and combine the single obstacle recognition and processing sequences corresponding to different obstacles in the order of discovery time to obtain an obstacle recognition and processing sequence set.

[0021] Preferably, pass the single obstacle recognition and processing sequences in the obstacle recognition and processing sequence set through the formula Calculate and obtain the local recognition reliability SKk corresponding to different obstacles; in the formula, k is different recognized obstacles, k = 1, 2, 3, ……, p; p is a positive integer; GYk, TCk, LSk are respectively the obstacle type influence identifier, obstacle handling duration, and obstacle recognition interval distance corresponding to different recognized obstacles; TC0k, LSk0 are respectively the obstacle handling standard duration and obstacle recognition standard interval distance corresponding to different recognized obstacles; [ ] is the rounding function, indicating obtaining the largest integer not exceeding the real number;

[0022] Sort and combine the local recognition reliabilities obtained by corresponding processing of different recognized obstacles to obtain an obstacle planning effective processing sequence;

[0023] The angle planning effective recognition sequence and the obstacle planning effective processing sequence constitute a local planning monitoring and processing set.

[0024] Preferably, when performing data integration calculation on the overall implementation of the redundant motion planning scheme of the robot arm according to the angle planning effective recognition sequence and the obstacle planning effective processing sequence in the local planning monitoring and processing set, pass all the data in the angle planning effective recognition sequence and the obstacle planning effective processing sequence through the formula Calculate and obtain the single overall planning status value GZ of the redundant motion planning scheme of the robot arm; in the formula, Nij is the different angle planning effective values associated with different robot arm joints; NJ1 is the total number of angle planning effective values with non-zero values associated with all robot arm joints; a, b are different data item calculation weights, 0 < a ≤ b, a + b = 1; A is the single overall planning standard value.

[0025] Preferably, if the single overall planning status value is 0, generate a single overall planning status normal label and prompt;

[0026] If the single overall planning status value is not 0, generate a single overall planning status abnormal label and prompt;

[0027] The single overall planning status value and the obtained single overall planning status normal label or single overall planning status abnormal label constitute the single overall planning status data.

[0028] Preferably, traverse and count all single - time overall planning status data, and obtain the overall influence value YL of the status exception corresponding to the redundant motion planning scheme of the robot arm through the formula where NY is the total number of single - time overall planning status exception labels obtained by statistics; NZ is the total number of all single - time overall planning status data; B% is the overall standard influence rate of the status exception.

[0029] Preferably, the total number NJ1 of valid angle planning values with non - zero values associated with all arm joints and the total number NJ2 of local recognition reliability with non - zero values are respectively obtained through the formula to obtain the local influence value JZg of the status exception corresponding to different local planning; where g = 1, 2; JZg is JZ1 and JZ2, which are the first local influence value of the status exception and the second local influence value of the status exception respectively; NJg is NJ1 and NJ2; NJZg is NJZ1 and NJZ2, which are the total number of all planned angles of different joints corresponding to all redundant motion planning schemes of the robot arm and the total number of all obstacles obtained by recognition of different implementation processes corresponding to all redundant motion planning schemes of the robot arm respectively; Cg% is C1% and C2%, which are the first local standard influence rate of the status exception and the second local standard influence rate of the status exception respectively;

[0030] Sort and combine the obtained overall influence value of the status exception, the first local influence value of the status exception, and the second local influence value of the status exception to obtain an integrated sequence of the status exception influence.

[0031] Preferably, traverse and analyze the integrated sequence of the status exception influence;

[0032] If all elements in the integrated sequence of the status exception influence are less than or equal to 0, it is prompted that the planning implementation status is reliable, and the subsequent implementation of the existing redundant motion planning scheme of the robot arm is maintained;

[0033] If there are elements greater than 0 in the integrated sequence of the status exception influence, it is prompted that the planning implementation status is unreliable, and the subsequent implementation of the existing redundant motion planning scheme of the robot arm is dynamically adjusted.

[0034] Compared with the existing scheme, the beneficial effects achieved by the present invention are as follows:

[0035] By monitoring and counting the implementation of each redundant motion planning scheme of the robot arm through different aspects of planning processing, and performing data processing, analysis and combination on the monitoring and statistical data of different aspects of planning processing, a local planning monitoring and processing set is obtained, which improves the different local autonomous supervision and analysis effects of the implementation of the redundant motion planning scheme of the robot arm.

[0036] The present invention performs data integration calculation and analysis on the overall implementation of the robot arm redundant motion planning scheme each time according to the locally planned monitoring and processing set obtained by processing, realizes the expansion and mining utilization of the locally planned implementation processing data in different aspects in the early stage, and digitally represents and classifies the single overall planning state of the robot arm redundant motion planning scheme from the overall dimension, improving the overall autonomous supervision and analysis effect of the implementation of the robot arm redundant motion planning scheme.

[0037] The present invention integrates and analyzes the single overall planning state data corresponding to different implementations of the robot arm redundant motion planning scheme, determines the reliable state of the planned implementation corresponding to the robot arm redundant motion planning scheme, and adaptively performs dynamic optimization management on the robot arm redundant motion planning scheme according to the reliable state of the planned implementation, improving the adaptive planning optimization management effect of the robot arm redundant motion planning scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention will be further described below with reference to the accompanying drawings.

[0039] Figure 1 It is a flowchart of the method for redundant motion planning of the robot arm based on artificial intelligence according to the present invention.

[0040] Figure 2 It is a schematic structural diagram of the redundant motion of the robot arm in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0041] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] As Figure 1 - Figure 2 shown, the present invention is a method for redundant motion planning of the robot arm based on artificial intelligence, including:

[0043] Monitoring and statistics of different aspects of planning processing for each implementation of the robot arm redundant motion planning scheme, performing data processing and analysis combination of local planning on the monitoring and statistical data of different aspects of planning processing, and obtaining a locally planned monitoring and processing set; including:

[0044] When conducting local monitoring statistics and processing analysis on the effectiveness of the preliminary planning for each implementation of the redundant motion planning scheme of the robot arm, all the planned angles JGi corresponding to different joints of the robot arm at different planning timestamps are obtained. The unit of the planning timestamp is accurate to seconds, and all the planned angles corresponding to different joints are sequentially analyzed through the planned angle recognition function for data analysis, and the angle planning validity flag JGBij corresponding to different planned angles is output;

[0045] It should be noted that all the planned angles corresponding to different joints of the robot arm are automatically generated according to the existing redundant motion planning scheme of the robot arm and the application requirements of the actual application scenario;

[0046] Among them, i represents different joints of the robot arm, i = 1, 2, 3, ……, n; n is a positive integer; j represents the number of the planned action corresponding to different planned angles, j = 1, 2, 3, ……, m; m is a positive integer;

[0047] The expression of the planned angle recognition function is ; In the formula, JG min ij, JG max ij are respectively the minimum operating angle and the maximum operating angle corresponding to different joints, which are determined according to the operating design requirement data corresponding to different joints;

[0048] The angle planning validity flag contains a value of 0 or 1, indicating that the corresponding planned angle is valid or invalid;

[0049] All the angle planning validity flags obtained by processing different joints of the robot arm are sorted and combined respectively to obtain the angle planning processing sequence corresponding to different joints of the robot arm;

[0050] In the embodiment of the present invention, by monitoring statistics and processing combination of the effectiveness of the preliminary planning for each implementation of the redundant motion planning scheme of the robot arm, the angle planning processing sequence corresponding to different joints of the robot arm is obtained, which can not only realize the digital representation of the local angle planning state of different arm joints, but also provide reliable local angle planning supervision data support for the subsequent analysis of the effective state of angle planning;

[0051] Traverse and analyze the angle planning processing sequences corresponding to different joints of the robot arm in sequence. If all the elements in the angle planning processing sequence are 0, the angle planning valid value associated with the corresponding arm joint is set to 0;

[0052] If there are non-zero elements in the angle planning processing sequence, the angle planning valid value associated with the corresponding arm joint is set to N; N is the total number of non-zero elements in the angle planning processing sequence;

[0053] Sort and combine the valid values of the angle planning associated with all wheel arm joints to obtain a valid recognition sequence of angle planning;

[0054] In the embodiment of the present invention, by traversing and analyzing different angle planning processing sequences obtained through preprocessing, and processing, sorting, and combining the results of the traversal analysis to obtain a valid recognition sequence of angle planning, it can provide reliable data support for the analysis of the valid angle planning for the data analysis of the overall implementation status of each subsequent robot wheel arm redundant motion planning scheme.

[0055] When conducting local monitoring statistics and processing analysis on the effectiveness of the mid-term planning for each implementation of the robot wheel arm redundant motion planning scheme, monitor and obtain all obstacles identified during the implementation of the robot wheel arm redundant motion planning, as well as the corresponding obstacle types, recognition discovery timestamps, recognition processing end timestamps, and obstacle recognition interval distances for all obstacles;

[0056] Among them, the identification and acquisition of all obstacles can be determined according to existing obstacle identification technical solutions, such as image recognition solutions, lidar recognition solutions, ultrasonic recognition solutions, and multi-sensor fusion recognition solutions. The specific implementation steps are not elaborated here;

[0057] Obstacle types include but are not limited to static obstacle types, dynamic obstacle types, narrow space obstacle types, and soft obstacle types;

[0058] Specifically, the static obstacle type is the most common obstacle type, including walls, other machine devices, or fixed objects in the working environment, etc. The positions of such obstacles are relatively fixed and can be avoided through pre-planning;

[0059] Dynamic obstacle type: Such as moving people, animals, or other robots, etc.; since their positions change over time, real-time perception and collision avoidance strategies need to be combined to effectively avoid collisions;

[0060] Narrow space obstacle type: Some operating scenarios may require the robotic arm to operate in a very limited space, such as internal inspection of pipelines or precision assembly processes; in this case, even the design of redundant degrees of freedom may face challenges;

[0061] Soft obstacle type: Flexible objects such as cables and wires, although they will not cause direct damage to the mechanical structure, are prone to winding around the joints, affecting the motion trajectory and even causing failures;

[0062] Traverse and match different obstacle types with the pre-built obstacle type impact table to obtain the corresponding obstacle type impact identifiers, and calculate the obstacle handling durations corresponding to different obstacles based on the recognition discovery timestamps and recognition processing end timestamps;

[0063] Among them, the obstacle type influence table pre-stores several sample obstacle types and their corresponding sample obstacle type influence identifiers. Different sample obstacle types are pre-associated with a corresponding sample obstacle type influence identifier. The sample obstacle type influence identifier is used to digitally represent the obstacle influence corresponding to the sample obstacle type to which it belongs. The specific value of the sample obstacle type influence identifier can be determined by the total number of historical occurrences and the processing duration corresponding to the sample obstacle type;

[0064] Sort and combine the obstacle type influence identifier, obstacle processing duration, and obstacle recognition interval distance obtained from the corresponding processing of the obstacle to obtain a single obstacle recognition processing sequence;

[0065] Sort and combine the single obstacle recognition processing sequences corresponding to different obstacles in the order of discovery time to obtain an obstacle recognition processing sequence set;

[0066] In the embodiments of the present invention, by monitoring, counting, and processing the effectiveness of the mid-term planning for each implementation of the robot arm redundant motion planning scheme, an obstacle recognition processing sequence set for the corresponding planning processing of all obstacles is obtained, which can provide reliable processing data support for the subsequent analysis of the reliable state of local recognition corresponding to different obstacles.

[0067] Pass the single obstacle recognition processing sequences in the obstacle recognition processing sequence set through the formula Calculate and obtain the local recognition reliability SKk corresponding to different obstacles; in the formula, k is different recognized obstacles, k = 1, 2, 3,..., p; p is a positive integer; GYk, TCk, and LSk are respectively the obstacle type influence identifier, obstacle processing duration, and obstacle recognition interval distance corresponding to different recognized obstacles; TC0k and LSk0 are respectively the standard obstacle processing duration and the standard obstacle recognition interval distance corresponding to different recognized obstacles, which are determined according to the design requirement data corresponding to the robot arm redundant motion or the previous obstacle test data; [ ] is the rounding function, indicating obtaining the largest integer not exceeding the real number;

[0068] Sort and combine the local recognition reliabilities obtained from the corresponding processing of different recognized obstacles to obtain an obstacle planning effective processing sequence;

[0069] In the embodiments of the present invention, through data calculation and sorting combination of the reliable state of local recognition for the planning processing data corresponding to different obstacles, an obstacle planning effective processing sequence corresponding to all obstacles is obtained, realizing the digital processing of the reliable state of local recognition corresponding to different obstacles, and at the same time, it can also provide reliable local recognition reliable supervision data support for the subsequent data analysis of the overall implementation state of each robot arm redundant motion planning scheme;

[0070] The angle planning effective recognition sequence and the obstacle planning effective processing sequence constitute a local planning monitoring processing set;

[0071] In the embodiment of the present invention, by monitoring and counting the implementation of the redundant motion planning scheme of the robot wheel arm for different aspects of planning processing each time, and performing data processing and analysis combination on the monitoring and statistical data of different aspects of planning processing, a local planning monitoring processing set is obtained, which improves the different local autonomous supervision and analysis effects of the implementation of the redundant motion planning scheme of the robot wheel arm.

[0072] According to the obtained local planning monitoring processing set, data integration calculation and analysis are performed on the overall implementation of the redundant motion planning scheme of the robot wheel arm each time to obtain the single - time overall planning state data, including:

[0073] When performing data integration calculation on the overall implementation of the redundant motion planning scheme of the robot wheel arm according to the angle planning effective recognition sequence and the obstacle planning effective processing sequence in the local planning monitoring processing set, all data in the angle planning effective recognition sequence and the obstacle planning effective processing sequence are calculated through the formula to obtain the single - time overall planning state value GZ of the redundant motion planning scheme of the robot wheel arm; in the formula, Nij is the different angle planning effective values associated with different wheel arm joints; NJ1 is the total number of angle planning effective values with non - zero values associated with all wheel arm joints; a and b are the calculation weights of different data items, 0 < a ≤ b, a + b = 1, and the specific values of a and b are not limited and can be customized according to the actual application requirements of the actual application scenario; A is the single - time overall planning standard value, which can be determined according to the design requirement data corresponding to the redundant motion of the robot wheel arm or can be determined according to the previous motion test data.

[0074] In the embodiment of the present invention, by integrating and calculating the local planning implementation processing data of different aspects in the early stage, the single - time overall planning state value of the redundant motion planning scheme of the robot wheel arm is obtained, realizing the digital representation of the single - time overall planning state.

[0075] If the single - time overall planning state value is 0, a single - time overall planning state normal label is generated and a prompt is given.

[0076] If the single - time overall planning state value is not 0, a single - time overall planning state abnormal label is generated and a prompt is given.

[0077] The single - time overall planning state value and the obtained single - time overall planning state normal label or single - time overall planning state abnormal label constitute the single - time overall planning state data.

[0078] In the embodiments of the present invention, data integration calculation and analysis are performed on the overall implementation of the robot arm redundant motion planning scheme each time according to the locally planned monitoring processing set obtained by processing, realizing the expansion and mining utilization of the locally planned implementation processing data in different aspects in the early stage, and digitally representing and classifying the single overall planning state of the robot arm redundant motion planning scheme from the overall dimension, improving the overall autonomous supervision and analysis effect of the implementation of the robot arm redundant motion planning scheme;

[0079] Integrate and analyze the single overall planning state data corresponding to different implementations of the robot arm redundant motion planning scheme, determine the reliable state of the planned implementation corresponding to the robot arm redundant motion planning scheme, and dynamically optimize and manage the robot arm redundant motion planning scheme adaptively according to the reliable state of the planned implementation; including:

[0080] Traverse and count all the single overall planning state data, and calculate the total number NY of abnormal labels of the single overall planning state through the formula Calculate the overall influence value YL of the state anomaly corresponding to the robot arm redundant motion planning scheme; NZ is the total number of all single overall planning state data; B% is the overall standard influence rate of the state anomaly, which can be determined according to the design requirement data corresponding to the robot arm redundant motion or the previous motion test data;

[0081] It should be noted that the overall influence value of the state anomaly is used to calculate the data of the overall influence degree of the state anomaly from the overall dimension of all implementation results of the robot arm redundant motion planning scheme;

[0082] And, the total number NJ1 of valid angle planning values with non-zero numerical values associated with all arm joints and the total number NJ2 of local recognition reliability with non-zero numerical values are respectively calculated through the formula Calculate the local influence value JZg of the state anomaly corresponding to different local plans; where g = 1, 2; JZg is JZ1, JZ2, which are the first local influence value of the state anomaly and the second local influence value of the state anomaly respectively; NJg is NJ1, NJ2; NJZg is NJZ1, NJZ2, which are the total number of all planned angles of different joints corresponding to all robot arm redundant motion planning schemes and the total number of all obstacles recognized in different implementation processes corresponding to all robot arm redundant motion planning schemes respectively; Cg% is C1%, C2%, which are the first local standard influence rate of the state anomaly and the second local standard influence rate of the state anomaly respectively, and both can be determined according to the design requirement data corresponding to the robot arm redundant motion or the previous motion test data;

[0083] It should be noted that the first state anomaly partial influence value and the second state anomaly partial influence value are respectively used to calculate the data of the degree of local influence of state anomalies for different local dimensions of all implementation results of the redundant motion planning scheme of the robot wheel arm;

[0084] Sort and combine the obtained overall influence value of state anomaly, the first state anomaly partial influence value, and the second state anomaly partial influence value to obtain an integrated sequence of state anomaly influences;

[0085] In the embodiments of the present invention, by calculating and combining the data of the degree of corresponding state anomaly influence for the overall dimension and different local dimensions of all implementation results of the redundant motion planning scheme of the robot wheel arm, reliable multi-dimensional data support can be provided for the analysis of the reliable state of the planning implementation corresponding to the redundant motion planning scheme of the robot wheel arm.

[0086] Traverse and analyze the integrated sequence of state anomaly influences;

[0087] If all elements in the integrated sequence of state anomaly influences are less than or equal to 0, it is prompted that the planning implementation state is reliable, and the subsequent implementation of the existing redundant motion planning scheme of the robot wheel arm is maintained;

[0088] If there are elements greater than 0 in the integrated sequence of state anomaly influences, it is prompted that the planning implementation state is unreliable, and the subsequent implementation of the existing redundant motion planning scheme of the robot wheel arm is dynamically adjusted;

[0089] Among them, dynamically adjusting the subsequent implementation of the existing redundant motion planning scheme of the robot wheel arm can specifically implement the optimization adjustment of the planning design of the corresponding local dimension and the optimization adjustment of the planning design of the corresponding overall dimension according to the elements greater than 0.

[0090] In the embodiments of the present invention, the single-time overall planning state data corresponding to different implementations of the redundant motion planning scheme of the robot wheel arm is integrated and analyzed to determine the reliable state of the planning implementation corresponding to the redundant motion planning scheme of the robot wheel arm, and the redundant motion planning scheme of the robot wheel arm is dynamically optimized and managed adaptively according to the reliable state of the planning implementation, improving the adaptive planning optimization management effect of the redundant motion planning scheme of the robot wheel arm.

[0091] In addition, the formulas involved above are all numerical calculations after removing the dimension, and are obtained by collecting a large amount of data and simulating through simulation software to obtain a formula closest to the real situation.

[0092] In several embodiments provided by the present invention, it should be understood that the disclosed method can be implemented in other ways. For example, the described embodiments of the invention are merely illustrative. For example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0093] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules. They may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0094] In addition, the functional modules in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically alone, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware, or in the form of hardware plus software functional modules.

[0095] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A wheel arm redundant motion planning method based on artificial intelligence, characterized in that: include: The effectiveness of the preliminary planning is monitored and analyzed locally for each implementation of the redundant motion planning scheme of the robot wheel arm, and all the planning angles JGi corresponding to different planning timestamps of different joints of the robot wheel arm are obtained, and all the planning angles corresponding to different joints are analyzed in turn through the planning angle identification function, and the effective identification of the angle planning JGBij corresponding to different planning angles is output; where i is the different joints of the robot wheel arm, i=1, 2, 3, ..., n; j is the number of the planning action corresponding to different planning angles, j=1, 2, 3, ..., m; The planning angle identification function is ; In the formula, JG min ij, JG max ij are the minimum operating angle and maximum operating angle corresponding to different joints; All the acquired angle planning valid identifiers are sorted and combined respectively to obtain the angle planning processing sequence corresponding to different joints; The angle planning processing sequences corresponding to different joints are traversed and analyzed in turn. If all elements in the angle planning processing sequence are 0, the effective value of the angle planning associated with the joint is set to 0; If there are non-zero elements in the angle planning processing sequence, the angle planning valid value associated with the joint is set to N; N is the total number of non-zero elements in the angle planning processing sequence; all the angle planning valid values ​​associated with the joint are sorted and combined to obtain the angle planning valid identification sequence; Conduct local monitoring statistics and process analysis on the effectiveness of mid-term planning for each implementation of the redundant motion planning scheme for the robot's wheel arms, monitor and obtain all obstacles identified during the implementation of the redundant motion planning scheme for the robot's wheel arms, and obtain the obstacle type, identification discovery timestamp, identification processing end timestamp, and obstacle identification interval distance corresponding to all obstacles; Traverse and match different obstacle types with the pre-built obstacle type impact table to obtain the corresponding obstacle type impact identifier, and calculate the obstacle processing time corresponding to different obstacles based on the identification discovery timestamp and the identification processing end timestamp; The obstacle type impact identification, obstacle processing time and obstacle identification interval distance are sorted and combined to obtain a single obstacle identification processing sequence; The individual obstacle recognition processing sequences corresponding to different obstacles are sorted and combined in the order of discovery time to obtain an obstacle recognition processing sequence set; The individual obstacle recognition processing sequences in the obstacle recognition processing sequence set are sequentially transformed into Calculate and obtain the local recognition reliability SKk corresponding to different obstacles; where k is the obstacle of different recognition, k=1, 2, 3, ..., p; GYk, TCk, LSk are the obstacle type impact identification, obstacle processing time, and obstacle recognition interval distance corresponding to different recognition obstacles; TC0k and LS0k are the obstacle processing standard time and obstacle recognition standard interval distance corresponding to different recognition obstacles; [] is the rounding function, which means obtaining the maximum integer that does not exceed the real number; The local recognition reliability obtained by processing different recognized obstacles is sorted and combined to obtain an effective processing sequence for obstacle planning; The effective recognition sequence of angle planning and the effective processing sequence of obstacle planning constitute the local planning monitoring processing set; According to the local planning monitoring processing set, the data integration calculation and analysis of each overall implementation of the robot arm redundant motion planning scheme are performed to obtain the single overall planning state data; The single overall planning status data corresponding to different implementations of the robot's wheel arm redundant motion planning schemes are integrated and analyzed to determine the planning implementation reliability status corresponding to the robot's wheel arm redundant motion planning scheme, and the robot's wheel arm redundant motion planning scheme is dynamically optimized and managed adaptively based on the planning implementation reliability status.

2. The wheel arm redundant motion planning method based on artificial intelligence according to claim 1 is characterized in that: When performing data integration calculation for the overall implementation of the robot arm redundant motion planning scheme based on the angle planning effective recognition sequence and obstacle planning effective processing sequence in the local planning monitoring processing, all the data in the angle planning effective recognition sequence and obstacle planning effective processing sequence are calculated by the formula Calculate and obtain the single overall planning state value GZ of the redundant motion planning scheme of the robot wheel arm; where Nij is the effective value of different angle planning associated with different joints; NJ1 is the total number of effective values ​​of angle planning associated with all joints whose values ​​are not 0; a and b are the calculation weights of different data items, 0<a≤b, a+b=1; A is the standard value of single overall planning.

3. The wheel arm redundant motion planning method based on artificial intelligence according to claim 2 is characterized in that: If the single overall planning status value is 0, a single overall planning status normal label is generated and prompted; If the single overall planning status value is not 0, a single overall planning status abnormal label is generated and prompted; The single overall planning state value and the single overall planning state normal label or the single overall planning state abnormal label obtained through analysis constitute the single overall planning state data.

4. The wheel arm redundant motion planning method based on artificial intelligence according to claim 3 is characterized in that: All single overall planning status data are traversed and counted, and the total number of abnormal labels of the single overall planning status NY is calculated through the formula Calculate and obtain the overall impact value YL of the abnormal state corresponding to the redundant motion planning scheme of the robot's wheel arm; NZ is the total number of all single overall planning state data; B% is the overall standard impact rate of the abnormal state.

5. The wheel arm redundant motion planning method based on artificial intelligence according to claim 4 is characterized in that: The total number of angle planning valid values ​​NJ1 and the total number of local recognition reliability values ​​NJ2 when the values ​​associated with all joints are not 0 are calculated by the formula Calculate and obtain the state abnormal local influence value JZg corresponding to different local plans; where g=1,2; JZ1 and JZ2 are the local influence values ​​of the first state abnormality and the local influence values ​​of the second state abnormality, respectively; NJZ1 and NJZ2 are the total number of all planning angles corresponding to different joints of all robot wheel arm redundant motion planning schemes and the total number of all obstacles identified and obtained by different implementation processes of all robot wheel arm redundant motion planning schemes, respectively; C1% and C2% are the local standard influence rate of the first state abnormality and the local standard influence rate of the second state abnormality, respectively; The overall impact value of the state anomaly, the local impact value of the first state anomaly, and the local impact value of the second state anomaly obtained by processing are sorted and combined to obtain a state anomaly impact integration sequence.

6. The wheel arm redundant motion planning method based on artificial intelligence according to claim 5 is characterized in that: Conduct traversal analysis on the integration sequence affected by abnormal status; If the elements in the integration sequence affected by the abnormal state are all less than or equal to 0, it is indicated that the planning implementation state is reliable, and the subsequent implementation of the existing robot wheel arm redundant motion planning scheme is maintained; If the abnormal state affects the existence of elements greater than 0 in the integrated sequence, it indicates that the planning implementation state is unreliable, and the subsequent implementation of the existing robot wheel arm redundant motion planning scheme is dynamically adjusted.

Images