Mechanical arm remote control teaching system

Abstract

The invention discloses a mechanical arm remote control teaching system, relates to the technical field of virtual reality, and solves the problems that systematic analysis on path characteristics is lacked, and redundancy, sudden change and the like of a motion track of a mechanical arm are easily caused. A sudden change inflection point is innovatively locked through inflection point angle analysis through a path characteristic verification end; abnormal turning in the path is effectively identified, and a foundation is laid for subsequent optimization; the preliminary optimization end and the secondary optimization end adopt a hierarchical optimization strategy, a preliminary optimization path is generated by connecting abrupt change inflection points, invalid motion of a mechanical arm is reduced, then the shortest interference-free path is screened in an iterative mode, deep optimization of the path is achieved, the efficiency and safety of path planning are remarkably improved, and the optimal path planning efficiency is improved. And the execution end accurately controls the mechanical arm according to the optimized execution path, so that the energy consumption and the time cost of mechanical arm operation are reduced, and the collision risk is effectively avoided through a scientific path optimization mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of virtual reality (VR), and specifically to a robotic arm remote control teaching system. Background Art

[0002] In the fields of industrial automation, hazardous environment operations, etc., the application of robotic arms is becoming increasingly widespread, and the accuracy and efficiency of their path planning and control have become key technical points; traditional robotic arm teaching methods mostly rely on manual on-site operations or preset fixed programs, which have problems such as poor flexibility, low efficiency, and difficulty in adapting to complex dynamic environments.

[0003] With the development of remote control technology, although remote teaching systems can break through spatial limitations, existing solutions still face many challenges: firstly, path planning is mostly based on experience or simple algorithms, lacking systematic analysis of path characteristics, which easily leads to problems such as redundancy and mutation in the robotic arm's motion trajectory, reducing operating efficiency and increasing energy consumption; secondly, in complex environments, it is difficult for path planning to effectively avoid obstacles, which may cause collision risks and threaten equipment safety; thirdly, existing optimization strategies are single and cannot meet the diverse requirements of different working conditions for path optimization.

[0004] Therefore, there is an urgent need for a remote control teaching system that can accurately analyze path characteristics, efficiently optimize the motion trajectory, and ensure the safe and stable operation of the robotic arm. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides a robotic arm remote control teaching system, which solves the problems of lack of systematic analysis of path characteristics, which easily leads to problems such as redundancy and mutation in the robotic arm's motion trajectory.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A robotic arm remote control teaching system, including: A virtual scene construction terminal, which constructs a virtual scene of the environment where the robotic arm works and generates a virtual scene; A virtual path generation terminal, where an operator conducts practical operations in the constructed virtual scene to confirm the virtual path; A path feature verification terminal, which verifies the features of the recorded virtual path, calibrates the path inflection points existing in the virtual path, and locks the mutation inflection points from several calibrated path inflection points. The specific method is as follows: Calibrate the path inflection points in the virtual path in sequence: Denote the different path points associated in the virtual path as the points to be determined, and determine the previous group of path points and the next group of path points adjacent to the points to be determined. Based on the points to be determined and the two adjacent groups of points, confirm the characteristic angle belonging to this point to be determined. If the characteristic angle = 180°, no calibration is performed. If the characteristic angle ≠ 180°, then calibrate this point to be determined as a path inflection point; Identify the mutation inflection points from the calibrated path inflection points: Based on the calibrated path inflection points, denote the previous adjacent path point of the path inflection point as the previous point, denote the next adjacent path point of the path inflection point as the next point, denote the partial line segment between the previous point and the path inflection point as the previous characteristic segment, and extend the previous characteristic segment according to the moving direction from the previous point to the path inflection point to confirm a group of extended segments. Then denote the partial segment between the next point and the path inflection point as the next characteristic segment, and denote the angle between the extended segment and the next characteristic segment as JA i , where i represents different path inflection points. If JA i ≤Y1, no processing is performed. If JA i >Y1, then calibrate the associated path inflection point as a mutation inflection point, where Y1 is a preset value; Initial optimization end: Based on the several mutation inflection points calibrated in the virtual path and the actual spatial positions, connect the successively determined mutation inflection points to generate the first group of optimized paths belonging to the virtual path. The specific method is as follows: Based on the several mutation inflection points calibrated in the virtual path, successively connect the adjacent mutation inflection points to confirm the preferred single path between the adjacent mutation inflection points, and confirm whether there are interfering objects in the virtual scene for the preferred single path: If so, determine the path of travel associated with the adjacent mutation inflection points in the virtual path, and record the determined path of travel as the determined path. If not, record this preferred single path as the determined path; Connect the several groups of determined paths recorded successively to generate the first group of optimized paths belonging to this virtual path; Identify the original path length of the virtual path and denote it as L1, then confirm the path length of the first group of optimized paths and denote it as L2. Use: (L1 - L2) ÷ L1 = YH to confirm the optimization value YH, and display the confirmed optimization value YH through the display end; Secondary optimization end: Perform path optimization processing on the first group of optimized paths after determination. From the several groups of mutation inflection points calibrated in the first group of optimized paths, lock the selected inflection points, and then confirm the paths for the several groups of selected inflection points. Lock the execution path from the several groups of paths confirmed. The specific method is as follows: S1. Take the determined first set of optimized paths as the to-be-determined paths, record several mutation inflection points in the to-be-determined paths as to-be-determined points, record the sorting positions where the to-be-determined points appear in sequence, and label them as k, where k = 1, 2, ……, n. When k = 1, it means this to-be-determined point belongs to the starting point of this to-be-determined path. When k = n, it means this to-be-determined point belongs to the end point of this to-be-determined path; S2. First, take the two sets of to-be-determined points with k = 1 and k = n as the selected inflection points, connect the two sets of selected inflection points, confirm a set of characteristic paths, and identify whether there are interfering objects in the virtual scene for this set of characteristic paths. If there are, do not perform any calibration and proceed with subsequent processing. If not, take this path as the execution path and complete the determination process of the execution path; S3. In the state of determining the first set of characteristic paths, sequentially select a set of mutation inflection points from k ∈ [2, n - 1] and record them as to-be-determined points, and adjust the characteristic paths according to the positions of the to-be-determined points to confirm the second set of characteristic paths. Identify whether there are interfering objects in the virtual scene for the confirmed several sets of characteristic paths. If there are, do not perform any calibration. If not, record the corresponding characteristic paths as the to-be-selected paths. If there is only one set of to-be-selected paths in this processing process, take this to-be-selected path as the execution path. If there are multiple sets of to-be-selected paths, select the shortest path from the multiple sets of to-be-selected paths and take the selected shortest path as the execution path. If there is no set of to-be-selected paths among the multiple sets of characteristic paths, execute the subsequent processing process again; S4. Sequentially add the unselected mutation inflection points to the multiple sets of characteristic paths associated with the previous processing process, and adjust and confirm to obtain the subsequent characteristic paths, and use the same confirmation method as in S3 to lock the execution path or execute the subsequent processing process; S5. Repeat S4 until several mutation inflection points are all locked as selected inflection points, and then confirm the execution path.

[0007] Preferably, the virtual scene construction end performs three-dimensional scanning on the environment around the robotic arm based on the camera and lidar sensor set on the robotic arm, sequentially confirms the position features associated with different pixels in the environment, and generates a virtual scene belonging to the working environment of the corresponding robotic arm according to the sequentially confirmed different pixel position features.

[0008] Preferably, during the generation process of the virtual path: relevant operators wear VR devices to enter the virtual scene, and perform actual operation control on the virtual arm in the virtual scene, record the running trajectory generated by the virtual arm, and generate the virtual path.

[0009] Preferably, the execution end controls the operation of the associated robotic arm according to the determined execution path.

[0010] Preferably, each group of the virtual paths is associated with a group of operating nodes, and the operating nodes of the virtual arms are the same as those of the robotic arm.

[0011] The present invention provides a robotic arm remote control teaching system. Compared with the prior art, it has the following beneficial effects: Through the path feature verification end, the present invention innovatively locks the mutation inflection points through the analysis of the inflection point angles, effectively identifies the abnormal turns in the path, and lays a foundation for subsequent optimization. The preliminary optimization end and the secondary optimization end adopt a hierarchical optimization strategy. First, the preliminary optimization path is generated by connecting the mutation inflection points to reduce the ineffective movement of the robotic arm, and then the shortest non-interfering path is screened iteratively to achieve the in-depth optimization of the path, significantly improving the efficiency and safety of path planning; The execution end accurately controls the robotic arm according to the optimized execution path to ensure its efficient and stable operation in complex scenarios. The entire system not only reduces the energy consumption and time cost of the robotic arm operation, but also effectively avoids the collision risk through a scientific path optimization mechanism, greatly enhancing the reliability and practicality of the system, and is applicable to multi-scenario applications such as industrial manufacturing and operation in dangerous environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a schematic diagram of the principle framework of the present invention; Figure 2 is a schematic diagram for determining the included angle of the front and rear feature segments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the 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 efforts shall fall within the protection scope of the present invention.

[0014] First Embodiment: Please refer to Figure 1 , the present application provides a robotic arm remote control teaching system, including a virtual scene construction end, a virtual path generation end, a path feature verification end, a preliminary optimization end, a secondary optimization end, and an execution end, wherein the virtual scene construction end, the virtual path generation end, the path feature verification end, the preliminary optimization end, the secondary optimization end, and the execution end are electrically connected in sequence from the output node to the input node: Among them, the virtual scene construction end constructs a virtual scene for the environment where the robotic arm works. Based on sensors such as cameras and lidar set on the robotic arm, it conducts three-dimensional scanning of the environment around the robotic arm, sequentially confirms the position features associated with different pixels in the environment, and generates a virtual scene belonging to the corresponding robotic arm working environment according to the sequentially confirmed position features of different pixels. Specifically, in the process of constructing the virtual scene in this part, based on the pixel features captured by the corresponding camera and the position features of the corresponding pixel features determined by the lidar, the spatial features of the specified pixel can be confirmed. Then, based on the different spatial features associated with different pixels, the virtual scene of the robotic arm working environment can be constructed. Since the construction process of this part is relatively common in the prior art, it will not be elaborated here; Among them, the virtual path generation end allows relevant operators to conduct actual operations in the constructed virtual scene through a head-mounted VR device. During the actual operation process, the running trajectory of the corresponding virtual arm in the virtual scene is confirmed and recorded as a virtual path. Different running nodes have different virtual paths. This part of the virtual path is generated by the operator's own operation. The corresponding operator controls the corresponding virtual arm to conduct relevant actual operations according to the constructed virtual scene. During the actual operation process, the virtual paths associated with each different node can be recorded, and then transmitted from the recorded virtual paths to the control terminal of the robotic arm to control the robotic arm to operate in the same frequency, so as to ensure the actual operation process of the corresponding robotic arm and enable the robotic arm to adapt to a variety of different running scenarios; Among them, the path feature verification end verifies the features of the recorded virtual path, calibrates the path inflection points existing in the virtual path, locks the mutation inflection points from the calibrated several path inflection points, and marks the determined mutation inflection points in the virtual path. The locking method of the mutation inflection points is; Calibrate the path inflection points existing in the virtual path in sequence: Denote the different path points associated with the virtual path as the points to be determined, and determine the previous group of path points and the next group of path points adjacent to the points to be determined. Based on the points to be determined and the two adjacent groups of points, confirm the characteristic angle belonging to this point to be determined. If the characteristic angle = 180°, no calibration is performed. If the characteristic angle ≠ 180°, then calibrate this point to be determined as a path inflection point; Combined with Figure 2, confirm the mutation inflection points from several calibrated path inflection points: Based on the calibrated path inflection points, denote the adjacent path point before the path inflection point as the front point, denote the adjacent path point after the path inflection point as the rear point, denote the partial line segment between the front point and the path inflection point as the front feature segment, and extend the front feature segment according to the moving direction from the front point to the path inflection point to confirm a group of extended segments. Then, denote the partial segment between the rear point and the path inflection point as the rear feature segment, and denote the included angle between the extended segment and the rear feature segment as JA. i , where i represents different path inflection points. If JA i ≤Y1, no processing is performed. If JA i >Y1, then the associated path inflection point is calibrated as a mutation inflection point. Y1 is a preset value, and its specific value is determined by the operator according to experience. Generally, Y1 takes a value of 10°. Specifically, after the virtual path is generated, there will be corresponding point position changes. When there is a corner change in adjacent point positions, the characteristic angle generated between the two groups of point positions changes, and the characteristic angle does not belong to 180°. Then it represents that the corresponding point position belongs to the corresponding path inflection point. Then, reconfirm the inflection point angle of the path inflection point in turn. Based on the reconfirmed inflection point angle, reconfirm the mutation inflection point. When the corresponding inflection point angle does not exceed the corresponding 10°, the turning angle of the path is relatively low, so there is no need to specifically calibrate the mutation inflection point. If it exceeds the corresponding 10°, then it is necessary to calibrate the mutation inflection point existing in the path, so as to confirm the path characteristics existing in the virtual path in turn.

[0015] Among them, for the preliminary optimization end, based on several mutation inflection points calibrated in the virtual path, and based on the actual spatial positions of the mutation inflection points, connect the sequentially determined mutation inflection points to generate the first group of optimized paths belonging to the virtual path. The specific generation method is as follows: Based on several mutation inflection points calibrated in the virtual path, connect adjacent mutation inflection points in turn to confirm the preferred single path between adjacent mutation inflection points, and confirm whether there are interfering objects in the virtual scene for the preferred single path (that is, the situation where this path has spatial feature intersections with other objects): If there are, determine the path of travel associated with the adjacent mutation inflection points in the virtual path, and record the determined path of travel as the determined path. If not, record this preferred single path as the determined path. The interfering object is the situation where the determined preferred single path has spatial intersections with the object, that is, the corresponding single path passes through the object in the virtual scene or other situations, then it belongs to the situation of having interfering objects; Connect the several groups of determined paths recorded in turn to generate the first group of optimized paths belonging to this virtual path; Identify the original path length of the virtual path and denote it as L1, then confirm the path length of the first set of optimized paths and denote it as L2. Use: (L1 - L2) ÷ L1 = YH to confirm the optimization value YH, and display the confirmed optimization value YH through the display terminal. Specifically, after the first set of optimized paths are optimized and determined, the travel path length of the robotic arm must be lower than the overall line length of the original virtual path. This part of the optimization process is to prevent the robotic arm from doing useless work during actual operation. By using this method for path optimization, the first set of optimized paths for the corresponding path are determined.

[0016] Second Embodiment: In the specific implementation process of this embodiment, compared with the above embodiment, the main difference is that this embodiment mainly performs secondary optimization on the path after optimization processing to achieve a more optimized path selection process, so that the robotic arm can achieve the optimal travel path confirmation effect and quickly execute the corresponding operation process; Among them, the secondary optimization terminal performs path optimization processing on the determined first set of optimized paths. From the several sets of mutation inflection points marked in the first set of optimized paths, lock and select the inflection points, and then confirm the paths of the several sets of selected inflection points. From the several sets of paths confirmed, lock the execution path; Among them, the specific method for locking the execution path is: S1. Take the determined first set of optimized paths as the pending path, denote the several mutation inflection points existing in the pending path as pending points, and record the sorting positions where the pending points appear in sequence, and mark them as k, where k = 1, 2,..., n. When k = 1, it means that this pending point belongs to the starting point of this pending path. When k = n, it means that this pending point belongs to the end point of this pending path; S2. First, take the two sets of pending points with k = 1 and k = n as the selected inflection points, connect the two sets of selected inflection points, confirm a set of characteristic paths, and identify whether there are interfering objects in the virtual scene for this characteristic path. If there are, do not perform any calibration and proceed with subsequent processing. If not, take this path as the execution path and complete the determination process of the execution path; S3. In the determined state of the first set of feature paths, sequentially select a set of mutation inflection points from k ∈ [2, n - 1] and denote them as the points to be determined. Then, adjust the feature paths based on the positions of the points to be determined to confirm the second set of feature paths (the behavior mode of the corresponding paths after adjustment has changed specifically, and a set of mutation inflection points is added between k = 1 and k = n). Identify whether there are interfering objects in the virtual scene for the confirmed sets of feature paths. If there are, do not perform any calibration. If not, record the corresponding feature paths as candidate paths. If there is only one set of candidate paths in this processing process, use this candidate path as the execution path. If there are multiple sets of candidate paths, select the shortest path from the multiple sets of candidate paths and use the selected shortest path as the execution path. If there is no set of candidate paths among the multiple sets of feature paths, execute the subsequent processing process again; S4. Sequentially add the unselected mutation inflection points to the multiple sets of feature paths associated with the previous processing process, and perform adjustment and confirmation to obtain the subsequent feature paths. Then, use the same confirmation method as in S3 to lock the execution path or execute the subsequent processing process; S5. Repeat the execution of S4 until all the mutation inflection points are locked as selected inflection points and then stop. Confirm the execution path (that is, when all the mutation inflection points are locked as selected inflection points, the execution path determined in the secondary optimization process and the optimization path associated with the first optimization state belong to the same type of path).

[0017] Specifically, sequentially select the associated inflection points from the determined sets of mutation inflection points. Then, according to the gradual selection process, the associated sets of paths can be confirmed in sequence. Then, select the relevant path with the shortest path length from the confirmed sets of paths to use as the corresponding execution path. Subsequently, according to the corresponding selection process, quickly determine the corresponding execution path.

[0018] Among them, the execution end controls the operation of the associated robotic arm according to the determined execution path.

[0019] Some of the data in the above formula are numerically calculated after removing their dimensions, and the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0020] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. 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 method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A robotic arm remote control teaching system, characterized in that, include: The virtual scene construction end constructs a virtual scene for the working environment of the robot arm to generate a virtual scene; At the virtual path generation end, operators conduct actual operations in the constructed virtual scene to confirm the virtual path; The path feature verification end performs feature verification on the recorded virtual path, calibrates the path inflection points existing in the virtual path, and locks the mutation inflection point from the calibrated path inflection points; At the preliminary optimization end, based on a number of mutation inflection points marked in the virtual path and the actual spatial position, the mutation inflection points determined in sequence are connected to generate a first group of optimized paths belonging to the virtual path; On the secondary optimization side, the first group of optimized paths that have been determined are subjected to path optimization processing. From among the several groups of mutation inflection points marked in the first group of optimized paths, selected inflection points are locked, and then the several groups of selected inflection points are subjected to path confirmation. The execution path is locked from among the several confirmed groups of paths.

2. The robotic arm remote control teaching system according to claim 1, wherein The virtual scene construction end performs a three-dimensional scan of the environment around the robotic arm based on the camera and lidar sensor installed on the robotic arm, confirms the position features associated with different pixels in the environment in turn, and generates a virtual scene belonging to the corresponding robotic arm working environment based on the different pixel position features confirmed in turn.

3. The robotic arm remote control teaching system according to claim 1, characterized in that, During the generation process of the virtual path: the relevant operator wears a VR device to enter the virtual scene, and actually controls the virtual arm in the virtual scene, records the running trajectory generated by the virtual arm, and generates a virtual path.

4. The robotic arm remote control teaching system according to claim 1, characterized in that, The specific method of locking the mutation inflection point at the path feature verification end is: The path turning points existing in the virtual path are calibrated in sequence: different path points associated with the virtual path are recorded as pending points, and the previous group of path points and the next group of path points adjacent to the pending point are determined. Based on the pending point and the two adjacent groups of points, the characteristic angle belonging to the pending point is confirmed. If the characteristic angle = 180°, no calibration is performed. If the characteristic angle ≠ 180°, the pending point is calibrated as a path turning point. Identify the mutation inflection point from several calibrated path inflection points: Based on the calibrated path inflection points, denote the adjacent path point before the path inflection point as the front point, denote the adjacent path point after the path inflection point as the rear point, denote the partial line segment between the front point and the path inflection point as the front feature segment, and extend the front feature segment according to the moving direction from the front point to the path inflection point to identify a group of extended segments. Then, denote the partial segment between the rear point and the path inflection point as the rear feature segment, and denote the angle between the extended segment and the rear feature segment as JA i , where i represents different path inflection points. If JA i ≤ Y1, no processing is performed. If JA i > Y1, then the associated path inflection point is calibrated as a mutation inflection point, where Y1 is a preset value.

5. The robotic arm remote control teaching system according to claim 1, characterized in that, The specific method of generating the first set of optimization paths at the preliminary optimization end is: Based on several mutation inflection points marked in the virtual path, adjacent mutation inflection points are connected in sequence to confirm the preferred single path between adjacent mutation inflection points, and confirm whether there is an interference object in the preferred single path in the virtual scene: if there is, the behavior path associated with the adjacent mutation inflection points in the virtual path is determined, and the determined behavior path is recorded as the determined path; if there is no interference object, the preferred single path is recorded as the determined path; Connecting the plurality of groups of determined paths recorded in sequence to generate a first group of optimized paths belonging to the virtual path; Identify the original path length of the virtual path and record it as L1, then confirm the path length of the first group of optimized paths and record it as L2, use: (L1-L2)÷L1=YH to confirm the optimized value YH, and display the confirmed optimized value YH through the display terminal.

6. The robotic arm remote control teaching system according to claim 1, characterized in that, The specific method of locking the execution path at the secondary optimization end is: S1. Take the determined first set of optimized paths as pending paths, record the several mutation inflection points existing in the pending paths as pending points, record the sorting positions where the pending points appear in sequence, and label them as k, where k = 1, 2, ……, n. When k = 1, it means this pending point belongs to the starting point of this pending path; when k = n, it means this pending point belongs to the end point of this pending path. S2. First, take the two sets of pending points with k = 1 and k = n as selected inflection points, connect the two sets of selected inflection points, confirm a set of characteristic paths, and identify whether there are interfering objects in the virtual scene for this set of characteristic paths. If there are, do not perform any calibration and proceed with subsequent processing. If not, take this path as the execution path and complete the determination process of the execution path. S3. In the state of determining the first set of characteristic paths, sequentially select a set of mutation inflection points from k ∈ [2, n - 1] and record them as pending points, and adjust and confirm the characteristic paths according to the positions of the pending points to confirm the second set of characteristic paths. Identify whether there are interfering objects in the virtual scene for the confirmed several sets of characteristic paths. If there are, do not perform any calibration. If not, record the corresponding characteristic paths as candidate paths. If there is only one set of candidate paths in this processing process, take this candidate path as the execution path. If there are multiple sets of candidate paths, select the shortest path from the multiple sets of candidate paths and take the selected shortest path as the execution path. If there is no set of candidate paths among the multiple sets of characteristic paths, execute the subsequent processing process again. S4. Sequentially add the unselected mutation inflection points to the multiple sets of characteristic paths associated with the previous processing process, and adjust and confirm to obtain the subsequent characteristic paths, and use the same confirmation method as in S3 to lock the execution path or execute the subsequent processing process. S5. Repeat the execution of S4 until several mutation inflection points are all locked as selected inflection points, and then confirm the execution path.

7. The robotic arm remote control teaching system according to claim 6, wherein It further includes: An execution end, which controls the operation of the associated robotic arm according to the determined execution path.

8. The robotic arm remote control teaching system according to claim 1, characterized in that Each group of the virtual paths is associated with a group of operation nodes, and the operation nodes of its virtual arm are the same as those of the robotic arm.

Images