A method for obstacle avoidance motion path planning for a robotic arm used for welding in ship compartments

Abstract

This invention discloses a method for obstacle avoidance motion path planning for a robotic arm used for welding in ship cabins, including setting a starting point and a target point for two random trees; generating random trees through bidirectional growth; and generating sampling points x. rand And perform target bias; find the nearest node x near ; Calculate the nearest node x near The resultant force F of the gravitational and repulsive forces t From the nearest node x near Expand in this direction with a fixed step size s to generate a new node x. new Collision detection; repeated iterations to generate an initial path. By incorporating a target bias strategy and improving the artificial potential field into the bidirectional RRT* algorithm to plan the end effector trajectory of the welding machine, this algorithm combines attractive and repulsive forces during path planning, effectively avoiding obstacles, making the search process more focused on the target area, enhancing path connectivity and planning quality, solving the problems of uneven sampling, excessive redundant points, excessive iterations, and excessively long paths in the RRT* algorithm, improving the algorithm's search efficiency, and making the obstacle avoidance movement of the welding robot arm more efficient and safe.

Description

Technical Field

[0001] This invention relates to a method for planning the obstacle avoidance motion path of a robotic arm used for welding in ship cabins, belonging to the field of path planning technology. Background Technology

[0002] In the shipbuilding industry, numerous confined spaces require welding operations. Traditional manual welding methods have many drawbacks and cannot meet process requirements. With the development of the robotics industry, robotic arms are now commonly used to assist production in shipbuilding. Robotic arms require motion planning when performing tasks, and path planning is a crucial component of this process. In ship welding operations, welding robotic arms must possess flexible task execution capabilities and autonomous, efficient path planning functions to avoid obstacles and accurately reach designated positions. This enables them to quickly select a collision-free path from the starting position to the target position in complex obstacle environments.

[0003] The Rapidly-exploring Random Tree (RRT) algorithm is a widely used method in robotic arm path planning. Based on a random sampling strategy, this algorithm searches a vast space to find feasible solutions, thereby increasing the probability of finding the global optimum. However, due to its reliance on randomness, the RRT algorithm is prone to uneven distribution of sampled points in the search space. This unevenness can easily cause discontinuities or unsmoothness in the planned path, thus affecting the path quality. Lower-quality paths can lead to unnecessary vibrations during robotic arm movement, which not only affects operational accuracy but also poses potential risks to the robotic arm and its environment.

[0004] Patent CN 116852367 A discloses a path planning method for obstacle avoidance of a six-axis robotic arm based on an improved RRT* algorithm. This method addresses the problems of large search space, long search time, computational complexity, and uneven path smoothness in existing algorithms by introducing a target bias and dual-tree expansion strategy. It expands simultaneously from the starting point and the target point, combining strategies for shortening the path and removing redundant nodes, and then optimizes the path using B-spline fitting. This method effectively reduces search time and complexity, achieves path shortening and smoothing, and ensures efficient and safe obstacle avoidance at the robotic arm's end effector. However, the algorithm suffers from numerous redundant points, high iteration counts, and long paths. Furthermore, this method only uses B-splines to fit and smooth the path, neglecting to prune the initially generated path to further shorten it. Summary of the Invention

[0005] Purpose of the invention: To address the shortcomings of existing technologies, this invention provides a method for planning the obstacle avoidance motion path of a robotic arm used for welding in ship compartments. This invention incorporates a target bias strategy and an improved artificial potential field mechanism to enhance path search efficiency and optimize path quality.

[0006] Technical solution: A method for planning the obstacle avoidance motion path of a robotic arm for welding in ship compartments, comprising the following steps:

[0007] Step 1: Set the starting point and target point of two random trees: Determine the starting point x of random tree T1 based on the starting point of the robotic arm. start1 And the target point x of random tree T2 goal2 The starting point x of the random tree T2 is determined based on the welding endpoint of the robotic arm. start2 And the target point x of random tree T1 goal1 ;

[0008] Step 2: Generate a random tree through bidirectional growth: two starting points x start1 and x start2 and their respective target points x goal1 and x goal2 Perform bidirectional growth to generate two random trees, T1 and T2, respectively;

[0009] Bidirectional growth refers to the process of exploring and expanding outwards from both the starting point and the target point until the two trees meet, at which point the planning algorithm converges, thus improving the efficiency of finding a path.

[0010] Step 3: Generate sampling point x rand And target bias is applied: random points are generated in the workspace, and according to a preset probability P, the random points are biased toward the target point x. goal1 Or target point x goal2 Bias is applied to obtain the sampling point x under the preset probability P. rand ;

[0011] Step 4: Find the nearest node x near For any random tree T1 or T2, find the distance x from each sampling point in step three. rand The nearest node x near That is, with the sampling point x rand The node with the smallest distance x near .

[0012] Step 5: Use an improved artificial potential field function for each nearest node x. near Calculate the resultant force F of the attractive and repulsive forces acting on it. t ;

[0013] Step 6: Calculate the resultant force F. t Direction, from the nearest node x nearExpand in this direction with a fixed step size s to generate a new node x. new ;

[0014] Step 7: For the newly generated node x new Perform collision detection, that is, determine the new node x. new Check if the connection path to its parent node interferes with an obstacle. If a collision occurs, abandon the current expansion and return to step three to resample and expand; if no collision occurs, optimize the new node x. new With the nearest node x near Determine the path length between them, then proceed to step eight;

[0015] Step 8: Set the maximum number of iterations n max Repeat steps three through seven, checking in each iteration whether the two random trees T1 and T2 have successfully grown and completed the path connection between them. If the maximum number of iterations n is reached... max Within, the paths of two random trees T1 and T2 are successfully connected, meaning that the two random trees originate from their respective starting points x. start1 and x start2 Towards their respective target points x goa l1 and x goal2 When paths meet and connect during the growth process, an initial path is generated, and sampling stops; if no path is found within the maximum number of iterations n... max If two trees are internally joined, return to step three.

[0016] The preferred option, step three, specifically includes:

[0017] Because the RRT* algorithm suffers from high randomness and long search time in path search in complex 3D environments, a dual-target bias strategy is adopted as shown in equation (1) for random sampling:

[0018]

[0019] In the formula, rand is a random number between 0 and l, p is the set target bias threshold, and size(map) is the size of the map;

[0020] When the value of rand is greater than the set target bias threshold, the random point is used as the sampling point x. rand Otherwise, set the target point x goal1 and x goal2 As sampling points x of their respective random trees rand .

[0021] The preferred option, step five, specifically includes:

[0022] Target point x goal For the nearest node x near Apply attraction F aiMeanwhile, sampling point x rand Also for the nearest node x near Apply attraction F aj In the nearest node x near The surrounding obstacles exert a repulsive force F on it. ri Overall attractiveness F ai and repulsive force F aj Determine the final direction F of node expansion. t :

[0023] Artificial potential fields include the gravitational field function U att As shown in equation (2), the repulsive field function U rep As shown in equation (3), the resultant potential field function is shown in equation (4):

[0024]

[0025] U = U att +U rep (4)

[0026] Among them, K a K is the gravitational factor. r d is the repulsive force factor; d is the distance between the robotic arm and the obstacle; d0 is the range of the repulsive potential field of the obstacle; P r P represents the position coordinates of the robotic arm's end effector. g d is the coordinate of the target point; a is the improvement factor, d(P) r -P g () represents the relative distance between the end effector of the robotic arm and the target point;

[0027] Each nearest node x near The resultant force F of the attractive and repulsive forces acting on it t For: F t =F aj +F ri .

[0028] Preferred option: In step seven, the new node x is optimized. new With the nearest node x near The specific path lengths between them are:

[0029] New node x new Using any nearest node x near Join as the parent node and the nearest node x near In the corresponding random tree T1 or T2; then with the new node x new Centered on x, search for nodes in random tree T1 or T2 within a radius r, selecting nodes that allow the node originating from the starting point x to be selected. start1 and x start2 To the new node x new The node x with the shortest path minand the new node x new The parent node is updated to x min To optimize the path.

[0030] The preferred options also include optimization of the initial path length and the number of turns, specifically:

[0031] In step eight of the traversal, the initial path includes the starting point x. start1 Target point x goal1 Or starting point x start2 Target point x goal2 For intermediate nodes other than those in the path, remove some intermediate nodes and check if the initial path after removing intermediate nodes does not collide with obstacles. If there is no collision, update the initial path. If a collision occurs, restore the intermediate nodes and select other intermediate nodes to remove until the initial path does not collide with obstacles, thus optimizing the length and number of turns of the initial path.

[0032] The preferred options also include optimizing the initial path linearity, specifically:

[0033] For all but the starting point x start1 Target point x goal1 Or starting point x start2 Target point x goal2 Connect two non-adjacent intermediate nodes to form a path. Check if the path does not collide with any obstacles. If there is no collision, remove the node between the two non-adjacent intermediate nodes and update the initial path. If a collision occurs, cancel the path connection between the two non-adjacent intermediate nodes and reselect non-adjacent intermediate nodes to form a path connection until the connected path does not collide with any obstacles, thus completing the optimization of the linearity of the initial path.

[0034] The preferred option also includes optimizing the initial path smoothness, specifically:

[0035] Preliminary path smoothness pre-optimization:

[0036] From the target point x of the initial path goal1 Beginning, and except for the starting point x start1 Connect all intermediate nodes except the target point x one by one. goal1 If the path connecting to the intermediate node does not collide with an obstacle, then remove the target point x. goal1 Check all nodes between the intermediate node and update the path if the target point x goal1 If a collision occurs between the target point x and the path connecting to this intermediate node, then x... goal1 Connect the path to the previous non-collision intermediate node, and repeat the connection steps with the intermediate node that did collide as the new target point until the connection path does not collide with any obstacles. This completes the initial smoothness optimization of the path. This optimization method is similar to starting from the target point x of the initial path.goal2 Beginning, and except for the starting point x start2 The initial path optimization method is the same as that used to connect all intermediate nodes one by one.

[0037] Then, B-spline curves are used to fit the path smoothness after the initial path smoothness pre-optimization, specifically:

[0038]

[0039] In the formula, P i F is the control point of the curve. i,k (t) is a k-order B-spline basis function.

[0040] Beneficial Effects: This invention plans the end effector trajectory of a welding robot by incorporating a target bias strategy and an improved artificial potential field into the bidirectional RRT* algorithm. This algorithm combines attractive and repulsive forces during path planning, effectively avoiding obstacles while focusing the search process more intently on the target area, thus enhancing path connectivity and planning quality. The improved path planning algorithm solves the problems of uneven sampling, excessive redundant points, excessive iterations, and excessively long paths in the RRT* algorithm, improving the algorithm's search efficiency and making obstacle avoidance movement of the welding robot more efficient and safer. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0042] Figure 1 This is a flowchart of the method of the present invention;

[0043] Figure 2 This is a diagram illustrating the generation process of two random trees using the bidirectional RRT* algorithm.

[0044] Figure 3 This is a preliminary path optimization process diagram for this embodiment;

[0045] Figure 4 This is a schematic diagram of B-spline curve path optimization.

[0046] Figure 5 The figure shows the simulation results of this invention;

[0047] Figure 6 This is a simulation experiment diagram of the robotic arm of the present invention operating inside a ship's cabin. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] In the description of this invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0050] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0051] like Figure 1 As shown, a method for planning the obstacle avoidance motion path of a robotic arm for welding in a ship compartment includes the following steps:

[0052] Step 1: Set the starting point and target point of two random trees: Determine the starting point x of random tree T1 based on the starting point of the robotic arm. start1 And the target point x of random tree T2 goal2 The starting point x of the random tree T2 is determined based on the welding endpoint of the robotic arm. start2 And the target point x of random tree T1 goal1 ;

[0053] Step 2: Generate a random tree through bidirectional growth: two starting points x start1 and x start2 and their respective target points x goal1 and x goal2 Perform bidirectional growth to generate two random trees, T1 and T2, respectively;

[0054] Bidirectional growth refers to the process of exploring and expanding outwards from both the starting point and the target point until the two trees meet, at which point the planning algorithm converges, thus improving the efficiency of finding a path.

[0055] Step 3: Generate sampling point x rand And target bias is applied: random points are generated in the workspace, and according to a preset probability P, the random points are biased toward the target point x. goal1 Or target point x goal2 Bias is applied to obtain the sampling point x under the preset probability P. rand Specifically:

[0056] Because the RRT* algorithm suffers from high randomness and long search time in path search in complex 3D environments, a dual-target bias strategy is adopted as shown in equation (1) for random sampling:

[0057]

[0058] In the formula, rand is a random number between 0 and l, p is the set target bias threshold, and size(map) is the size of the map;

[0059] When the value of rand is greater than the set target bias threshold, the random point is used as the sampling point x. rand Otherwise, set the target point x goal1 and x goal2 As sampling points x of their respective random trees rand .

[0060] Step 4: Find the nearest node x near For any random tree T1 or T2, find the distance x from each sampling point in step three. rand The nearest node x near That is, with the sampling point x rand The node with the smallest distance x near .

[0061] Step 5: Use an improved artificial potential field function for each nearest node x. near Calculate the resultant force F of the attractive and repulsive forces acting on it. t :

[0062] Target point x goal For the nearest node x near Apply attraction F ai Meanwhile, sampling point x rand Also for the nearest node x near Apply attraction F aj In the nearest node x near The surrounding obstacles exert a repulsive force F on it. ri Overall attractiveness F ai and repulsive force F aj Determine the final direction F of node expansion. t :

[0063] Artificial potential fields include the gravitational field function U att As shown in equation (2), the repulsive field function U rep As shown in equation (3), the resultant potential field function is shown in equation (4):

[0064]

[0065] U = U att +U rep (4)

[0066] Among them, K a K is the gravitational factor. r d is the repulsive force factor; d is the distance between the robotic arm and the obstacle; d0 is the range of the repulsive potential field of the obstacle; P r P represents the position coordinates of the robotic arm's end effector. g d is the coordinate of the target point; a is the improvement factor, d(P) r -P g () represents the relative distance between the end effector of the robotic arm and the target point;

[0067] Each nearest node x near The resultant force F of the attractive and repulsive forces acting on it t For: F t =F aj +F ri .

[0068] Step 6: Calculate the resultant force F. t Direction, from the nearest node x near Expand in this direction with a fixed step size s to generate a new node x. new ;

[0069] Step 7: For the newly generated node x new Perform collision detection, that is, determine the new node x. new Check if the connection path to its parent node interferes with an obstacle. If a collision occurs, abandon the current expansion and return to step three to resample and expand; if no collision occurs, optimize the new node x. new With the nearest node x near Determine the path length between them, then proceed to step eight;

[0070] In step seven, the new node x is optimized. new With the nearest node x near The specific path lengths between them are:

[0071] New node x new Using any nearest node x near Join as the parent node and the nearest node x near In the corresponding random tree T1 or T2; then with the new node xnew Centered on x, search for nodes in random tree T1 or T2 within a radius r, selecting nodes that allow the node originating from the starting point x to be selected. start1 and x start2 To the new node x new The node x with the shortest path min and the new node x new The parent node is updated to x min To optimize the path.

[0072] Step 8: Set the maximum number of iterations n max Repeat steps three through seven, checking in each iteration whether the two random trees T1 and T2 have successfully grown and completed the path connection between them. If the maximum number of iterations n is reached... max Within, the paths of two random trees T1 and T2 are successfully connected, meaning that the two random trees originate from their respective starting points x. start1 and x start2 Towards their respective target points x goa l1 and x goal2 When paths meet and connect during the growth process, an initial path is generated, and sampling stops; if no path is found within the maximum number of iterations n... max If two trees are internally joined, return to step three.

[0073] like Figure 2 The diagram illustrates the generation process of two random trees using the bidirectional RRT* algorithm. Figure 3 The diagram shows the initial path optimization process in this embodiment: assuming there are 5 nodes: starting point x start1 intermediate node x middle1 intermediate node x middle2 intermediate node x middle3 Target point x goal1 ,

[0074] It also includes optimizations to the initial path length and number of turns, specifically:

[0075] In step eight of the traversal, the initial path includes the starting point x. start1 Target point x goal1 Or starting point x start2 Target point x goal2 For intermediate nodes other than those mentioned above, remove some intermediate nodes and check if the initial path after removing intermediate nodes has no collision with obstacles. If there is no collision, update the initial path; if a collision occurs, restore the intermediate nodes and select other intermediate nodes to remove until the initial path has no collision with obstacles, thus optimizing the initial path length and number of turns. That is: directly connect x middle1 With x middle3 If the path still has no collisions, then remove x. middle2Update the path; if a collision occurs, remove other intermediate nodes until the initial path does not collide with obstacles.

[0076] This also includes optimization of the initial path linearity, specifically:

[0077] For all but the starting point x start1 Target point x goal1 Or starting point x start2 Target point x goal2 For any non-adjacent intermediate nodes, a path is connected. The path is checked for collision-free behavior. If no collision occurs, the node between the two non-adjacent intermediate nodes is removed, and the initial path is updated. If a collision occurs, the path connection between the two non-adjacent intermediate nodes is canceled, and a new non-adjacent intermediate node is selected for connection. This process continues until the connected path does not collide with any obstacle, thus optimizing the linearity of the initial path. In other words, for each x in the path... middle1 With x middle4 Perform a connection if x middle1 To x middle4 If the path does not collide with any obstacle, then delete x. middle2 x middle3 If a collision occurs, the path connection between the two non-adjacent intermediate nodes is canceled, and a new non-adjacent intermediate node is selected to connect the paths until the connected path does not collide with the obstacle.

[0078] It also includes optimization of the initial path smoothness, specifically:

[0079] Preliminary path smoothness pre-optimization:

[0080] From the target point x of the initial path goal1 Beginning, and except for the starting point x start1 Connect all intermediate nodes except the target point x one by one. goal1 If the path connecting to the intermediate node does not collide with an obstacle, then remove the target point x. goal1 Check all nodes between the intermediate node and update the path if the target point x goal1 If a collision occurs between the target point x and the path connecting to this intermediate node, then x... goal1 Connect the path to the previous non-collision intermediate node, and repeat the connection steps with the intermediate node that did collide as the new target point until the connection path does not collide with any obstacles. This completes the initial smoothness optimization of the path. This optimization method is similar to starting from the target point x of the initial path. goal2 Beginning, and except for the starting point x start2 The initial path optimization method for connecting intermediate nodes one by one is the same as that for x; that is: goal1 With x middle2 If the path connecting the two points does not collide with any obstacles, then continue towards the preceding node x.middle1 Initiate a connection; if a collision occurs with an obstacle, then connect with x. middle3 Connect, and x middle2 Repeat the above steps as a new target point until the connecting path does not collide with any obstacles.

[0081] like Figure 4 As shown, B-spline curves are then used to fit the path smoothness after the initial path smoothness pre-optimization, specifically:

[0082]

[0083] In the formula, P i F is the control point of the curve. i,k (t) is a k-order B-spline basis function.

[0084] like Figure 5 and Figure 6 As shown in the simulation results diagram, according to this obstacle avoidance planning method, the end effector of the welding robot avoids the sphere and square obstacles and successfully reaches the target point, and the selected path is optimal.

[0085] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0086] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for planning the obstacle avoidance motion path of a robotic arm used for welding in ship cabins, characterized in that: Includes the following steps: Step 1: Set the starting point and target point of two random trees: Determine the starting point x of random tree T1 based on the starting point of the robotic arm. start1 And the target point x of random tree T2 goal2 The starting point x of the random tree T2 is determined based on the welding endpoint of the robotic arm. star2 And the target point x of random tree T1 goal1 ; Step 2: Generate a random tree through bidirectional growth: two starting points x start1 and x star2 and their respective target points x goal1 and x goal2 Perform bidirectional growth to generate two random trees, T1 and T2, respectively; Step 3: Generate sampling point x rand And target bias is applied: random points are generated in the workspace, and according to a preset probability P, the random points are biased toward the target point x. goal1 Or target point x goal2 Bias is applied to obtain the sampling point x under the preset probability P. rand ; Step three specifically involves: Because the RRT* algorithm suffers from high randomness and long search time in path search in complex 3D environments, a dual-target bias strategy is adopted as shown in equation (1) for random sampling: （1） In the formula, rand is a random number between 0 and l, p is the set target bias threshold, and size(map) is the size of the map; When the value of rand is greater than the set target bias threshold, the random sampling point is used as the sampling point x. rand ;otherwise , target point x goal1 and x goal2 As sampling points x of their respective random trees rand ; Step 4: Find the nearest node x near For any random tree T1 or T2, find the distance x from each sampling point in step three. rand The nearest node x near That is, with the sampling point x rand The node with the smallest distance x near ; Step 5: Use an improved artificial potential field function for each nearest node x. near Calculate the resultant force F of the attractive and repulsive forces acting on it. t ; Step five specifically involves: Target point x goal For the nearest node x near Apply attraction F ai Meanwhile, sampling point x rand Also for the nearest node x near Apply attraction F aj At the nearest node x near The surrounding obstacles exert a repulsive force F on it. ri Overall attractiveness F ai and repulsive force F aj Determine the final direction F of node expansion. t : Artificial potential fields include the gravitational field function U att As shown in equation (2), the repulsive field function U rep As shown in equation (3), the resultant potential field function is shown in equation (4): (2) (3) (4) Among them, K a K is the gravitational factor. r d is the repulsive force factor; d is the distance between the robotic arm and the obstacle; d0 is the range of the repulsive potential field of the obstacle; P r P represents the position coordinates of the robotic arm's end effector. g d is the coordinate of the target point; a is the improvement factor, d(P) r -P g () represents the relative distance between the end effector of the robotic arm and the target point; Each nearest node x near The resultant force F of the attractive and repulsive forces acting on it t for: ; Step 6: Calculate the resultant force F. t Direction, from the nearest node x near Expand in this direction with a fixed step size s to generate a new node x. new ; Step 7: For the newly generated node x new Perform collision detection, that is, determine the new node x. new Check if the connection path to its parent node interferes with an obstacle. If a collision occurs, abandon the current expansion and return to step three to resample and expand; if no collision occurs, optimize the new node x. new With the nearest node x near Determine the path length between them, then proceed to step eight; Step 8: Set the maximum number of iterations n max Repeat steps three through seven, checking in each iteration whether the two random trees T1 and T2 have successfully grown and completed the path connection between them. If the maximum number of iterations n is reached... max Within, the paths of two random trees T1 and T2 are successfully connected, meaning that the two random trees originate from their respective starting points x. start1 and x star2 Towards their respective target points x goal1 and x goal2 When paths meet and connect during the growth process, an initial path is generated, and sampling stops; if no path is found within the maximum number of iterations n... max If two trees are internally joined, return to step three.

2. The obstacle avoidance motion path planning method for a ship cabin welding robotic arm according to claim 1, characterized in that: In step seven, the new node x is optimized. new With the nearest node x near The specific path lengths between them are: New node x new Using any nearest node x near Join as the parent node and the nearest node x near In the corresponding random tree T1 or T2; then with the new node x new Centered on x, search for nodes in random tree T1 or T2 within a radius r, selecting nodes that allow the node originating from the starting point x to be selected. start1 and x star2 To the new node x new The node x with the shortest path min and the new node x new The parent node is updated to x min To optimize the path.

3. The obstacle avoidance motion path planning method for a ship cabin welding robotic arm according to claim 1, characterized in that: It also includes optimizations to the initial path length and number of turns, specifically: In step eight of the traversal, the initial path includes the starting point x. start1 Target point x goal1 For intermediate nodes other than those mentioned above, remove some intermediate nodes and check if the initial path after removing intermediate nodes has no collision with obstacles. If there is no collision, update the initial path; if a collision occurs, restore the intermediate nodes and select other intermediate nodes to remove until the initial path has no collision with obstacles. This completes the optimization of the initial path length and number of turns. Another starting point x star2 Target point x goal2 The initial path uses the same optimization method.

4. The obstacle avoidance motion path planning method for a ship cabin welding robotic arm according to claim 1, characterized in that: This also includes optimization of the initial path linearity, specifically: For all but the starting point x start1 Target point x goal1 For any non-adjacent intermediate nodes, a path is connected. The path is checked for collision-free behavior. If no collision occurs, the node between the two non-adjacent intermediate nodes is removed, and the initial path is updated. If a collision occurs, the path connection between the two non-adjacent intermediate nodes is canceled, and a new non-adjacent intermediate node is selected for connection. This process continues until the connected path does not collide with any obstacle, thus optimizing the linearity of the initial path. (Another starting point x...) star2 Target point x goal2 The initial path uses the same optimization method.

5. The obstacle avoidance motion path planning method for a ship cabin welding robotic arm according to claim 1, characterized in that: It also includes optimization of the initial path smoothness, specifically: Preliminary path smoothness pre-optimization: From the target point x of the initial path goal1 Beginning, and except for the starting point x start1 Connect all intermediate nodes except the target point x one by one. goal1 If the path connecting to the intermediate node does not collide with an obstacle, then remove the target point x. goal1 Check all nodes between the intermediate node and update the path if the target point x goal1 If a collision occurs between the target point x and the path connecting to this intermediate node, then x... goal1 Connect the path to the previous non-collision intermediate node, and repeat the connection steps with the intermediate node that did collide as the new target point until the connection path does not collide with any obstacles. This completes the initial smoothness optimization of the path. This optimization method is similar to starting from the target point x of the initial path. goal2 Beginning, and except for the starting point x star2 The initial path optimization method is the same as that used to connect all intermediate nodes one by one. Then, B-spline curves are used to fit the path smoothness after the initial path smoothness pre-optimization, specifically: ； In the formula: P i F is the control point of the curve. i,k (t) is a k-order B-spline basis function.

Images