Special-shaped part laser automatic cleaning track planning method and system

Abstract

The invention provides an automatic laser cleaning track planning method and system for special-shaped parts, and relates to the field of robot control, and the method comprises the following steps: carrying out visual scanning on the special-shaped parts; according to the point cloud coordinates on the surface of the part three-dimensional model, cleaning track planning is carried out with the purpose of reducing the operation time, energy consumption, impact and acceleration of a mechanical arm; interference detection is carried out on the determined track points on the cleaning track, and interference is eliminated; through a mechanical arm kinematics model, track point coordinates on the cleaning track are converted into rotation angles of all joints of the mechanical arm; aiming at reducing the difference between the tail end of the mechanical arm and the track point on the cleaning track, optimizing the rotation angle of each joint of the mechanical arm by using a Jacobian matrix in combination with iterative solution; and controlling the mechanical arm to move according to the mapping relation between the track point on the cleaning track and the rotating angle of each joint of the mechanical arm, and automatically cleaning the special-shaped part by using laser.

Description

Technical Field

[0001] The present invention relates to the technical field of trajectory control, and in particular to a trajectory planning method and system for automatic laser cleaning of special-shaped parts. Background Art

[0002] Laser cleaning can precisely clean specific areas of the surface of parts through a focused laser beam, avoiding damage to parts that do not need to be cleaned. At the same time, laser cleaning is fast and suitable for rapid cleaning of parts in large-scale production, significantly shortening the cleaning time.

[0003] At present, automatic laser cleaning mainly relies on operators to control the robot to perform indiscriminate scanning from left to right and from top to bottom. Only simple plane scanning cleaning trajectory planning can be performed. The utilization rate of the robot is low, and only vertical downward scanning is performed, completely abandoning the angle rotation function of the robot.

[0004] Furthermore, for workpieces with complex surfaces, the operator's manual programming becomes much more tedious, and there are large errors in the programming operation, which affects the accuracy of the laser automatic cleaning trajectory and the accuracy of the laser automatic cleaning. Summary of the invention

[0005] In order to solve the technical problems that currently the operator mainly controls the robot to perform indiscriminate scanning from left to right and from top to bottom, and can only perform simple plane scanning cleaning trajectory planning, the utilization rate of the robot is low, the operator's manual programming is greatly complicated for workpieces with complex surfaces, and there are large errors in programming operations, which affects the accuracy of the laser automatic cleaning trajectory and the accuracy of the laser automatic cleaning, the present invention provides a method and system for laser automatic cleaning trajectory planning of special-shaped parts.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect:

[0008] An embodiment of the present invention provides a trajectory planning method for automatic laser cleaning of special-shaped parts, comprising:

[0009] S1: Visually scan the special-shaped parts to generate a three-dimensional model of the parts;

[0010] S2: According to the point cloud coordinates on the surface of the three-dimensional model of the component, the cleaning trajectory is planned by combining flower pollination with a genetic optimization algorithm with the goal of reducing the operating time, energy consumption, impact and acceleration of the robot arm;

[0011] S3: performing interference detection on the track points on the determined cleaning track and eliminating interference;

[0012] S4: construct the kinematic model of the robot arm;

[0013] S5: converting the coordinates of the track points on the cleaning track into the rotation angles of the joints of the robot arm through the kinematic model of the robot arm;

[0014] S6: with the goal of reducing the difference between the end of the robot arm and the trajectory point on the cleaning trajectory, the rotation angle of each joint of the robot arm is optimized by using the Jacobian matrix combined with iterative solution;

[0015] S7: According to the mapping relationship between the trajectory points on the cleaning trajectory and the rotation angles of the joints of the robot arm, the robot arm is controlled to move, and the laser is used to automatically clean the special-shaped parts.

[0016] Second aspect:

[0017] An embodiment of the present invention provides a trajectory planning system for laser automatic cleaning of special-shaped parts, comprising:

[0018] processor;

[0019] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for automatic laser cleaning trajectory planning of special-shaped parts as described in the first aspect is implemented.

[0020] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0021] In the present invention, the special-shaped parts are visually scanned to generate a three-dimensional model of the parts, with the goal of reducing the operating time, energy consumption, impact and acceleration of the robot arm. Automatic cleaning trajectory planning is carried out through flower pollination combined with a genetic optimization algorithm to improve the accuracy of the automatic cleaning trajectory. Then, according to the mapping relationship between the trajectory points on the cleaning trajectory and the rotation angles of each joint of the robot arm, the movement of the robot arm is controlled, and laser is used to automatically clean the special-shaped parts, thereby improving the utilization rate of the robot arm and improving the efficiency and accuracy of laser automatic cleaning. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A schematic flow chart of a trajectory planning method for automatic laser cleaning of special-shaped parts provided by an embodiment of the present invention;

[0024] Figure 2 A schematic structural diagram of a trajectory planning system for automatic laser cleaning of special-shaped parts provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0026] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0027] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0028] Reference Manual Attached Figure 1 , showing a flow chart of a trajectory planning method for automatic laser cleaning of special-shaped parts provided in an embodiment of the present invention.

[0029] The embodiment of the present invention provides a method for planning a trajectory of laser automatic cleaning of special-shaped parts, which includes the following steps:

[0030] S1: Visually scan special-shaped parts and generate 3D models of the parts.

[0031] In a possible implementation, S1 specifically includes: visually scanning the special-shaped parts by using a high-precision camera or reverse modeling equipment to generate a three-dimensional model of the parts.

[0032] In the present invention, the three-dimensional model of parts is generated by a high-precision camera or reverse modeling equipment, which can not only provide high-quality model data and support the precise planning of subsequent laser cleaning trajectories, but also significantly improve work efficiency and reduce trial and error costs. It is an important prerequisite for achieving automated and precise cleaning.

[0033] S2: Based on the point cloud coordinates on the surface of the 3D model of the component, the cleaning trajectory is planned through flower pollination combined with a genetic optimization algorithm with the goal of reducing the robot's operating time, energy consumption, impact, and acceleration.

[0034] Among them, the flower pollination combined with genetic optimization algorithm combines the flower pollination algorithm (FPA) and the genetic algorithm (GA). The flower pollination algorithm is an optimization algorithm based on the pollination behavior of flowers in nature. It simulates the process of plants spreading pollen through media such as wind and insects during the pollination process to achieve population reproduction. The genetic algorithm is a random search algorithm based on the principles of natural selection and genetics. It simulates the process of biological evolution and continuously optimizes the population through genetic operations (selection, crossover, mutation) to find the approximate optimal solution to the problem. The genetic algorithm is good at global search, but lacks local search capabilities. After the introduction of the flower pollination algorithm, the algorithm can flexibly adjust the search strategy according to the complexity of the problem and the optimization stage.

[0035] In a possible implementation, S2 specifically includes sub-steps S201 to S203:

[0036] S201: Construct an optimization objective function with the goal of reducing the operation time, energy consumption, impact and acceleration of the robot arm.

[0037] Optionally, the optimization objective function is specifically:

[0038]

[0039] Among them, min means minimization, F represents the optimization objective function, c1 represents the running time of the robot, c2 represents the energy consumption of the robot, c3 represents the impact of the joint of the robot, c4 represents the acceleration of the joint of the robot, λ1 represents the weight coefficient of the running time of the robot, λ2 represents the weight coefficient of the energy consumption of the robot, λ3 represents the weight coefficient of the impact of the joint of the robot, λ4 represents the weight coefficient of the acceleration of the joint of the robot, ξ1 represents the normalized coefficient of the running time of the robot, ξ2 represents the normalized coefficient of the energy consumption of the robot, ξ3 represents the normalized coefficient of the impact of the joint of the robot, and ξ4 represents the normalized coefficient of the acceleration of the joint of the robot.

[0040] Among them, technical personnel in this field can set the weight coefficient λ1 of the robot's operating time, the weight coefficient λ2 of the robot's energy consumption, the weight coefficient λ3 of the impact of the robot's joints, and the weight coefficient λ4 of the acceleration of the robot's joints according to actual conditions, and the present invention does not limit this.

[0041] In this invention, an optimization objective function based on running time, energy consumption, impact and acceleration is constructed to make the robot arm laser cleaning trajectory planning more scientific, flexible and efficient. This method can not only significantly improve the cleaning quality and system reliability, but also reduce operating costs and environmental impact, which meets the core needs of modern intelligent manufacturing.

[0042] Optionally, the running time of the robot arm is specifically:

[0043]

[0044] Wherein, Tk represents the running time on the kth cleaning trajectory.

[0045] Optionally, the energy consumption of the robotic arm is specifically:

[0046]

[0047] Among them, E ki represents the energy consumption of the i-th joint on the k-th cleaning trajectory, I i represents the moment of inertia of the i-th joint, ω ki represents the angular velocity of the i-th joint on the k-th cleaning trajectory, P k+1,i represents the rotation angle of the joint of the i-th joint on the k+1-th cleaning trajectory, P ki represents the rotation angle of the joint of the i-th joint on the k-th cleaning trajectory, T ki represents the running time of the i-th joint on the k-th cleaning trajectory, and n represents the total number of trajectory points.

[0048] Optionally, the impact of the robot arm joint is specifically:

[0049]

[0050] Among them, γ ki represents the angular impact of the i-th joint on the k-th cleaning trajectory, α ki represents the angular acceleration of the i-th joint on the k-th cleaning trajectory, α k-1,i Represents the angular acceleration of the i-th joint on the k-1-th cleaning trajectory.

[0051] Optionally, the acceleration of the robot arm joint is specifically:

[0052]

[0053] S202: Setting constraints in the cleaning trajectory planning process.

[0054] Optionally, the constraint condition is specifically:

[0055]

[0056] Among them, λ1 represents the weight coefficient of the robot's running time, λ2 represents the weight coefficient of the robot's energy consumption, λ3 represents the weight coefficient of the impact of the robot's joints, λ4 represents the weight coefficient of the acceleration of the robot's joints, ω kirepresents the angular velocity of the i-th joint on the k-th cleaning trajectory, τ1 represents the speed safety factor, and W i represents the maximum velocity of the i-th joint, J i represents the moment of inertia of the i-th joint, α ki represents the angular acceleration of the i-th joint on the k-th cleaning trajectory, τ2 represents the driving torque safety factor, F i represents the maximum driving torque of the i-th joint.

[0057] It should be noted that limiting the angular velocity of the joints prevents the robot from running too fast, which may cause trajectory instability or damage to the robot hardware. Furthermore, limiting the joint drive torque can prevent hardware overload due to excessive acceleration.

[0058] In the present invention, by setting reasonable constraints, efficiency, safety and hardware protection can be effectively balanced in the trajectory optimization process, ensuring that the trajectory planning result not only has the best performance, but also can be executed stably and safely in actual operation. This method meets the needs of industrial applications and provides important support for the efficient and reliable laser cleaning of robotic arms.

[0059] S203: Under the constraints of the constraints, with the goal of minimizing the optimization objective function, the cleaning trajectory is planned through flower pollination combined with a genetic optimization algorithm.

[0060] Specifically, the optimization objective function can be used as the fitness function of flower pollination combined with genetic optimization algorithm.

[0061] Initialize the population, which contains multiple individuals. Each individual represents a feasible cleaning trajectory plan. Each individual has multiple components, and each component represents the coordinates of a trajectory point.

[0062] An elite selection strategy is adopted to remove the 30% of individuals with the lowest fitness values ​​to form the first population.

[0063] In the present invention, an elite selection strategy is adopted to remove the 30% of individuals with the lowest fitness values, which can significantly improve the quality of the population. By retaining individuals with higher fitness, it is ensured that the population converges to the optimal solution and accelerates the optimization process. At the same time, individuals with lower fitness are eliminated to reduce the interference of invalid solutions on optimization and reduce the computational cost. In addition, this strategy can also balance the diversity and convergence speed of the population, provide a better genetic basis for subsequent crossover and mutation operations, thereby improving the optimization efficiency and the global search capability of the solution.

[0064] Perform a crossover operation on the individuals in the first population to form a second population:

[0065] Y1=rand×X1+(1-rand)×X2

[0066] Y2=rand×X2+(1-rand)×X1

[0067] Among them, Y1 and Y2 represent new individuals, X1 represents the first parent, X2 represents the second parent, and rand represents a random number between 0 and 1.

[0068] In the present invention, a crossover operation is performed on the individuals in the first population, and two new individuals are generated by combining the genes of the two parents according to random weights, which helps to preserve excellent genes while exploring new solution spaces. This can enhance the diversity of the population, prevent the algorithm from falling into the local optimum, and accelerate the search process for the global optimal solution, providing better candidate solutions for the subsequent optimization stage.

[0069] Perform mutation operations on individuals in the second population to form a third population:

[0070]

[0071] Among them, Y3 represents the new individual, X3 represents the parent, and X max represents the individual with the largest fitness value, X min represents the individual with the smallest fitness value, and rand represents a random number between 0 and 1.

[0072] In the present invention, mutation operations are performed on individuals in the second population, which can introduce diversity while retaining high-quality solutions, and prevent the population from converging to the local optimum too early. In addition, this mutation method guides the mutation direction by comparing the largest and smallest individuals, which helps to explore the solution space more efficiently, improve the global search capability, and provide a better gene pool for subsequent optimization.

[0073] The individuals in the third population are updated according to the flower pollination optimization algorithm to form the fourth population. A random number is randomly generated to determine whether the conversion probability is greater than the random number. If so, cross-pollination is performed. Otherwise, self-pollination is performed.

[0074] When cross-pollination occurs, the individual positions are updated according to the Levy flight mechanism:

[0075]

[0076] in, represents the position of the i-th individual at the t+1th iteration, represents the position of the i-th individual at the t-th iteration, θ t represents the step size influencing factor at the tth iteration, L represents the step size, represents the global optimal solution at the tth iteration.

[0077]

[0078] Among them, Γ represents the standard Gamma function, λ represents the exponential parameter, and s represents the scale parameter.

[0079] In the present invention, during the cross-pollination process, the Lévy flight mechanism is used to update the individual position, and the individual is brought closer to the global optimal solution by introducing the step length influencing factor and the step length, while the step length generated by the Lévy distribution provides randomness and long-distance jumping ability. The advantage of this is that the global search capability of the algorithm is enhanced, especially the ability to effectively explore the potential optimal area in the solution space and avoid falling into the local optimum. In addition, the long and short step random characteristics of the Lévy flight balance the search range and the refined search, and improve the optimization efficiency and robustness of the algorithm.

[0080] Optionally, the step length influencing factor is specifically:

[0081]

[0082] Among them, θ t It represents the step size influencing factor at the tth iteration, q represents the scaling factor, and T represents the maximum number of iterations.

[0083] In the present invention, the step size influencing factor can be used to gradually reduce the step size as the number of iterations increases. The larger step size in the early stage helps the algorithm to quickly explore the solution space and improve the global search capability; the smaller step size in the later stage enables the algorithm to perform fine optimization in the local area of ​​the solution space, improving the accuracy and convergence performance of the solution.

[0084] When self-pollination occurs, the individual positions are updated according to the golden sine mechanism:

[0085]

[0086] x1=-π+2π(1-τ)

[0087] x2=-π+2πτ

[0088] in, represents the position of the jth randomly selected individual at the tth iteration, represents the position of the randomly selected kth individual at the tth iteration, r1 and r2 represent random numbers between 0 and 2π, x1 and x2 represent the self-pollination coefficients, and τ represents the golden section number.

[0089] In the present invention, during the self-pollination process, the golden sine mechanism is used to update the individual position, so that the update of the individual position is both exploratory and stable. The advantage of this is that it utilizes the balance characteristics of the sine function and the golden section number to generate a smoother and more refined update path, enhance the local search ability, and avoid the algorithm from falling into the local optimal solution. In addition, the differences between randomly selected individuals further promote the diversity of the population, which helps to improve the optimization efficiency and the quality of the solution.

[0090] The third and fourth populations are merged to form the fifth population.

[0091] Determine whether the current number of iterations has reached the maximum number of iterations; if so, output the cleaning trajectory plan represented by the individual with the highest fitness in the fifth population; otherwise, return to continue iterating.

[0092] In the present invention, flower pollination is combined with a genetic optimization algorithm to plan the cleaning trajectory, which can combine the advantages of the two algorithms, with the goal of minimizing the optimization objective function while satisfying the constraints. The genetic algorithm provides a global search capability, using selection, crossover and mutation to improve the quality of the population and enhance the diversity of solutions; the flower pollination algorithm achieves a dynamic balance between global search and local optimization through Levy flight and the golden sine mechanism, improving search accuracy and efficiency. The advantage of this is that the generated trajectory plan not only meets physical constraints, but also achieves an effective trade-off between multiple objectives such as running time, energy consumption, impact and smoothness, significantly improving the efficiency, stability and cleaning quality of the cleaning task.

[0093] S3: Perform interference detection on the track points on the determined cleaning track and eliminate interference.

[0094] In a possible implementation, S3 specifically includes sub-steps S301 to S307:

[0095] S301: Obtaining trajectory points on the cleaning trajectory and corresponding normal vectors.

[0096] S302: For each trajectory and the corresponding normal vector, construct a detection ray:

[0097] r(t)=v i +da i

[0098] Among them, r(t) represents the ray, d represents the distance along the normal vector, and v i represents the i-th trajectory point, a i Represents the normal vector corresponding to the i-th trajectory point.

[0099] S303: Determine the intersection of the detection ray and the point cloud grid and solve the equation:

[0100] v i+da i =(1-b1-b2)p0+b1p1+b2p2

[0101] Among them, p0, p1, and p2 represent the three vertices of the point cloud mesh, and b1 and b2 represent the coefficients to be solved.

[0102] S304: Using Cramer's rule, solve the intersection point solution equation and calculate d, b1 and b2:

[0103]

[0104] P1=p1-p0

[0105] P2=p2-p0

[0106] S=v i -p0

[0107] S1=a i ×P2

[0108] S2=S×P1.

[0109] S305: Determine whether the solved b1 and b2 meet the following conditions. If so, the ray intersects with the point cloud mesh; otherwise, the ray does not intersect with the point cloud mesh:

[0110] 0≤b1≤1

[0111] 0≤b2≤1

[0112] 0≤b1+b2≤1

[0113] S306: When the ray intersects the point cloud grid, the trajectory point is determined to be an interference point.

[0114] S307: According to the interference point, the cleaning trajectory is adjusted to eliminate the interference.

[0115] Specifically, the cleaning trajectory can be adjusted by interpolating using neighboring non-interfering points.

[0116] In the present invention, by constructing a detection ray, solving the intersection equation of the ray and the point cloud grid, and judging the intersection condition, it is determined whether there is interference, and the trajectory point is dynamically adjusted when interference occurs. The advantage of this is that it ensures that the laser cleaning path does not collide with the surface of the component, improving the safety and reliability of the cleaning process; at the same time, the trajectory optimization avoids cleaning deviations caused by interference, ensures cleaning quality, and meets the cleaning needs of parts with complex shapes.

[0117] S4: Construct the kinematic model of the robotic arm.

[0118] In a possible implementation, S4 specifically includes: using Denavit-Hartenberg parameters to describe the geometric and kinematic relationships of the joints of the robotic arm and constructing a kinematic model of the robotic arm.

[0119] Among them, Denavit-Hartenberg (DH) parameters are a standardized robot modeling method used to describe the geometric relationship and kinematic characteristics between the joints and links of the robot. It defines the relative position and direction of each joint and link, constructs a homogeneous transformation matrix, and thus realizes the kinematic modeling and analysis of the robot.

[0120] S5: Through the robot arm kinematic model, the coordinates of the trajectory points on the cleaning trajectory are converted into the rotation angles of each joint of the robot arm.

[0121] Specifically, according to the DH parameter table of the robot arm, the coordinates of the track points on the cleaning track can be initially converted into the rotation angles of each joint of the robot arm, and then further optimized using iterative solution.

[0122] S6: With the goal of reducing the difference between the end of the robot arm and the trajectory points on the cleaning trajectory, the Jacobian matrix combined with iterative solution is used to optimize the rotation angles of each joint of the robot arm.

[0123] In a possible implementation, S6 specifically includes sub-steps S601 to S607:

[0124] S601: Obtain the current joint rotation angle value, convergence condition and maximum number of iterations.

[0125] S602: Calculate the current pose matrix and Jacobian matrix.

[0126] Among them, the pose matrix is ​​used to represent the current position and direction of the end of the robotic arm, and the Jacobian matrix is ​​used to define the relationship between the joint velocity and the end velocity.

[0127] Optionally, when the Jacobian matrix is ​​singular, the generalized inverse matrix is ​​used instead of the Jacobian matrix for calculation.

[0128] In the present invention, when the Jacobian matrix is ​​a singular matrix, the use of a generalized inverse matrix instead can effectively avoid calculation failure and ensure the continuity and stability of the inverse kinematics iteration process. The singularity of the Jacobian matrix usually occurs in certain special positions (such as when the robot reaches the motion boundary or certain postures), and direct inversion may cause the algorithm to be interrupted. The introduction of the generalized inverse matrix can provide a reasonable approximate solution near the singular point, maintain the update of the joint angle, and maintain the approximation accuracy of the target point. This method enhances the robustness of the algorithm and makes it more adaptable in complex path planning.

[0129] S603: Based on the current posture matrix, calculate the difference motion matrix:

[0130]

[0131] Where ΔT represents the differential motion matrix, T c Represents the pose matrix of the end of the robot arm, T e represents the pose matrix of the target point, and I represents the identity matrix.

[0132] There is the following relationship between the elements of the difference motion matrix and the elements of the difference motion vector:

[0133]

[0134] Among them, dx represents the linear displacement component in the x direction in Cartesian space, dy represents the linear displacement component in the y direction in Cartesian space, dz represents the linear displacement component in the z direction in Cartesian space, δx represents the angular displacement component in the x direction in Cartesian space, δy represents the angular displacement component in the y direction in Cartesian space, and δz represents the angular displacement component in the z direction in Cartesian space.

[0135] S604: Calculate the difference motion vector based on the difference motion matrix:

[0136] D=[d x d y d z δ x δ y δ z ] T

[0137] Wherein, D represents the difference motion vector, and T represents the matrix transpose operation.

[0138] S605: Calculate the increment of the joint angle based on the difference motion vector:

[0139] Δθ=J -1 D

[0140] Among them, Δθ represents the joint rotation angle increment, J represents the Jacobian matrix, -1 represents the inverse matrix operation, and D represents the difference motion vector calculated based on the difference motion matrix.

[0141] S606: Based on the increment of the joint angle, the joint rotation angle value is updated by adopting an iterative solution method:

[0142] θ c (k+1)=θ c (k)+α(k)Δθ

[0143] Among them, θ c (k+1) represents the joint rotation angle value at the k+1th iteration, θc (k) represents the joint rotation angle value at the kth iteration, α(k) represents the adaptive learning rate at the kth iteration, and Δθ represents the joint rotation angle increment.

[0144] The adaptive learning rate is specifically:

[0145]

[0146] Among them, α0 represents the initial learning rate, α K represents the maximum learning rate, and K represents the maximum number of iterations.

[0147] In the present invention, an adaptive learning rate is introduced to achieve a dynamic balance between speed and accuracy during the optimization process. A large initial learning rate helps to quickly approach the target. As the number of iterations increases, the learning rate decays exponentially, effectively reducing oscillations and fine-tuning joint angles to ensure convergence stability. This method can avoid convergence failures caused by too large a step size or slow convergence speeds caused by too small a step size, while adapting to the needs of different optimization stages, making the robotic arm joint optimization process more efficient and accurate.

[0148] S607: Determine whether the maximum number of iterations has been reached. If so, output the rotation angle values ​​of each joint of the current robot arm. Otherwise, return to S601 and continue iterating.

[0149] In the present invention, the rotation angle of each joint of the robot arm is optimized by combining the Jacobian matrix with iterative solution, which can effectively reduce the difference between the end of the robot arm and the target point on the cleaning trajectory. This method calculates the difference motion matrix and the difference motion vector, uses the joint angle increment to gradually approach the target point, and introduces an adaptive learning rate to control the iteration step size to improve the convergence speed and stability.

[0150] S7: According to the mapping relationship between the trajectory points on the cleaning trajectory and the rotation angles of the joints of the robotic arm, the robotic arm is controlled to move, and the laser is used to automatically clean the special-shaped parts.

[0151] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0152] In the present invention, visual scanning is performed on special-shaped parts to generate a three-dimensional model of the parts, with the goal of reducing the operating time, energy consumption, impact and acceleration of the robot arm. Automatic cleaning trajectory planning is performed through flower pollination combined with a genetic optimization algorithm to improve the accuracy of the automatic cleaning trajectory. Then, the movement of the robot arm is controlled according to the mapping relationship between the trajectory points on the cleaning trajectory and the rotation angles of each joint of the robot arm, and laser is used to automatically clean the special-shaped parts, thereby improving the utilization rate of the robot arm and improving the efficiency and accuracy of laser automatic cleaning.

[0153] Reference Manual Attached Figure 2 , showing a schematic structural diagram of a trajectory planning system for automatic laser cleaning of special-shaped parts provided in an embodiment of the present invention.

[0154] The present invention also provides a trajectory planning system 20 for laser automatic cleaning of special-shaped parts, comprising:

[0155] Processor 201;

[0156] The memory 202 stores computer-readable instructions, and when the computer-readable instructions are executed by the processor 201, the method for automatic laser cleaning trajectory planning of special-shaped parts as described in the method embodiment is implemented.

[0157] The trajectory planning system 20 for automatic laser cleaning of special-shaped parts provided by the present invention can execute the above-mentioned trajectory planning method for automatic laser cleaning of special-shaped parts and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0158] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0159] In the present invention, the special-shaped parts are visually scanned to generate a three-dimensional model of the parts, with the goal of reducing the operating time, energy consumption, impact and acceleration of the robot arm. Automatic cleaning trajectory planning is carried out through flower pollination combined with a genetic optimization algorithm to improve the accuracy of the automatic cleaning trajectory. Then, according to the mapping relationship between the trajectory points on the cleaning trajectory and the rotation angles of each joint of the robot arm, the movement of the robot arm is controlled, and laser is used to automatically clean the special-shaped parts, thereby improving the utilization rate of the robot arm and improving the efficiency and accuracy of laser automatic cleaning.

[0160] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0161] There are a few points to note:

[0162] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0163] (2) For the sake of clarity, the thickness of a film or region in the drawings used to describe the embodiments of the present invention is enlarged or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a film, a region or a substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0164] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0165] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A trajectory planning method for automatic laser cleaning of special-shaped parts, characterized in that: include: S1: Visually scan the special-shaped parts to generate a three-dimensional model of the parts; S2: According to the point cloud coordinates on the surface of the three-dimensional model of the component, the cleaning trajectory is planned by combining flower pollination with a genetic optimization algorithm with the goal of reducing the operating time, energy consumption, impact and acceleration of the robot arm; S3: performing interference detection on the track points on the determined cleaning track and eliminating interference; S4: construct the kinematic model of the robot arm; S5: converting the coordinates of the track points on the cleaning track into the rotation angles of the joints of the robot arm through the kinematic model of the robot arm; S6: with the goal of reducing the difference between the end of the robot arm and the trajectory point on the cleaning trajectory, the rotation angle of each joint of the robot arm is optimized by using the Jacobian matrix combined with iterative solution; S7: According to the mapping relationship between the trajectory points on the cleaning trajectory and the rotation angles of the joints of the robot arm, the robot arm is controlled to move, and the laser is used to automatically clean the special-shaped parts.

2. The trajectory planning method for automatic laser cleaning of special-shaped parts according to claim 1 is characterized in that: The S1 is specifically: The special-shaped parts are visually scanned by a high-precision camera or reverse modeling equipment to generate a three-dimensional model of the parts.

3. The trajectory planning method for automatic laser cleaning of special-shaped parts according to claim 1 is characterized in that: The S2 specifically includes: S201: Construct an optimization objective function with the goal of reducing the operation time, energy consumption, impact and acceleration of the robot arm; S202: Setting constraints in the cleaning trajectory planning process; S203: Under the constraints of the constraints, with the goal of minimizing the optimization objective function, cleaning trajectory planning is performed through flower pollination combined with a genetic optimization algorithm.

4. The trajectory planning method for automatic laser cleaning of special-shaped parts according to claim 3 is characterized in that: The optimization objective function is specifically: Among them, min means minimization, F represents the optimization objective function, c1 represents the running time of the robot, c2 represents the energy consumption of the robot, c3 represents the impact of the joint of the robot, c4 represents the acceleration of the joint of the robot, λ1 represents the weight coefficient of the running time of the robot, λ2 represents the weight coefficient of the energy consumption of the robot, λ3 represents the weight coefficient of the impact of the joint of the robot, λ4 represents the weight coefficient of the acceleration of the joint of the robot, ξ1 represents the normalized coefficient of the running time of the robot, ξ2 represents the normalized coefficient of the energy consumption of the robot, ξ3 represents the normalized coefficient of the impact of the joint of the robot, and ξ4 represents the normalized coefficient of the acceleration of the joint of the robot.

5. The trajectory planning method for automatic laser cleaning of special-shaped parts according to claim 4 is characterized in that: The constraints are specifically: Among them, λ1 represents the weight coefficient of the robot's running time, λ2 represents the weight coefficient of the robot's energy consumption, λ3 represents the weight coefficient of the impact of the robot's joints, λ4 represents the weight coefficient of the acceleration of the robot's joints, ω ki represents the angular velocity of the i-th joint on the k-th cleaning trajectory, τ1 represents the speed safety factor, and W i represents the maximum velocity of the i-th joint, J i represents the moment of inertia of the i-th joint, α ki represents the angular acceleration of the i-th joint on the k-th cleaning trajectory, τ2 represents the driving torque safety factor, F i represents the maximum driving torque of the i-th joint.

6. The trajectory planning method for automatic laser cleaning of special-shaped parts according to claim 1 is characterized in that: The S3 specifically includes: S301: Obtaining trajectory points on the cleaning trajectory and corresponding normal vectors; S302: For each trajectory and the corresponding normal vector, construct a detection ray: r(t)=v i +ta i Among them, r(t) represents the ray, t represents the distance along the normal vector, and v i represents the i-th trajectory point, a i Represents the normal vector corresponding to the i-th trajectory point; S303: Determine the intersection of the detection ray and the point cloud grid and solve the equation: <h2 style=";text-align:left;direction:ltr">v<h2 style=";text-align:left;direction:ltr"> i <h2 style=";text-align:left;direction:ltr"> +ta<h2 style=";text-align:left;direction:ltr"> i <h2 style=";text-align:left;direction:ltr"> (1-b1-b2)p0+b1p1+b2p2 Among them, p0, p1, and p2 represent the three vertices of the point cloud mesh, and b1 and b2 represent the coefficients to be solved; S304: Using Cramer's rule, solve the intersection point solution equation to calculate t, b1 and b2: S305: Determine whether the solved b1 and b2 meet the following conditions. If so, the ray intersects with the point cloud mesh; otherwise, the ray does not intersect with the point cloud mesh: 0≤b1≤1 0≤b2≤1 0≤b1+b2≤1 S306: When the ray intersects the point cloud grid, the trajectory point is determined to be an interference point; S307: According to the interference point, adjust the cleaning trajectory to eliminate the interference.

7. The trajectory planning method for automatic laser cleaning of special-shaped parts according to claim 1 is characterized in that: The S4 is specifically: Denavit-Hartenberg parameters are used to describe the geometric and kinematic relationships of the joints of the robotic arm and to construct a kinematic model of the robotic arm.

8. The trajectory planning method for automatic laser cleaning of special-shaped parts according to claim 1 is characterized in that: The S6 specifically includes: S601: Obtain the current joint rotation angle value, convergence condition and maximum number of iterations; S602: Calculate the current pose matrix and Jacobian matrix; S603: Calculate a difference motion matrix based on the current posture matrix; S604: Calculate a difference motion vector based on the difference motion matrix; S605: Calculating the increment of the joint angle based on the difference motion vector; S606: Based on the increment of the joint angle, update the joint rotation angle value by adopting an iterative solution method; S607: Determine whether the convergence condition or the maximum number of iterations is reached; if so, output the rotation angle value of each joint of the current robot arm; otherwise, return to S601 and continue iterating.

9. The trajectory planning method for automatic laser cleaning of special-shaped parts according to claim 8 is characterized in that: When the Jacobian matrix is ​​a singular matrix, a generalized inverse matrix is ​​used to replace the Jacobian matrix for calculation.

10. A trajectory planning system for laser automatic cleaning of special-shaped parts, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for automatic laser cleaning trajectory planning of special-shaped parts as described in any one of claims 1 to 9 is implemented.

Images