Welding robot trajectory planning method, welding system, electronic equipment and medium

Abstract

The present invention provides a welding robot trajectory planning method, welding system, electronic device and medium, including: obtaining point cloud data of a weld; fitting the point cloud data using a B-spline curve to obtain a first weld trajectory; optimizing the curvature of the first weld trajectory to obtain a weld trajectory curve; determining the robot's posture information according to the weld trajectory curve, and controlling the robot based on the posture information. The present invention can generate a high-order spatially complex welding trajectory with smooth curvature and more practical.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial robot positioning, and in particular to a welding robot trajectory planning method, a welding system, an electronic device and a medium. Background Art

[0002] With the development of science and technology, machine vision plays an increasingly important role in manufacturing. Machine vision is used to automatically find welds on welded parts and generate welding trajectories of welds. However, most existing welding robots do not have the function of automatically identifying welds and generating welding trajectories based on vision guidance. Even if a few welding robots support this function, they also require the welding trajectory path to be coplanar, or require the welding trajectory path to be a simple spatial curve. For welding applications where the welding trajectory path is a complex spatial curve, the robot welding process is not mature enough. It can be seen that the welding robot based on vision guidance does not have the function of fine-tuning the generated welding trajectory, cannot make the welding trajectory more in line with the actual weld path, and cannot generate high-order spatial complex curves with smooth curvature.

[0003] In summary, there is an urgent need for a welding robot trajectory planning method that can generate a smooth curvature curve. Summary of the invention

[0004] The present invention provides a welding robot trajectory planning method, a welding system, an electronic device and a medium to solve the above problems.

[0005] The present invention provides a welding robot trajectory planning method, comprising:

[0006] Get the point cloud data of the weld;

[0007] Fitting the point cloud data using a B-spline curve to obtain a first weld trajectory;

[0008] Performing curvature optimization on the first weld trajectory to obtain a weld trajectory curve;

[0009] The position and posture information of the robot is determined according to the weld trajectory curve, and the robot is controlled based on the position and posture information.

[0010] According to a welding robot trajectory planning method provided by the present invention, after fitting the point cloud data using a B-spline curve to obtain a first weld trajectory, the method further includes:

[0011] Adjusting the first weld trajectory according to an actual weld trajectory to obtain a second weld trajectory;

[0012] Accordingly, the curvature optimization of the first weld trajectory to obtain a weld trajectory curve includes:

[0013] The curvature of the second weld trajectory is optimized to obtain a weld trajectory curve.

[0014] According to a welding robot trajectory planning method provided by the present invention, the adjusting the first weld trajectory according to the actual weld trajectory to obtain the second weld trajectory comprises:

[0015] Adjusting the control points of the first weld trajectory according to the actual weld trajectory to obtain adjusted control points, and obtaining the second weld trajectory based on the adjusted control points;

[0016] Accordingly, the curvature optimization of the second weld trajectory to obtain a weld trajectory curve includes:

[0017] Determine the objective function f according to the adjusted control points, the node vectors of the B-spline curve and the second weld trajectory min :

[0018]

[0019] Where σ is the weight coefficient of curve smoothness, w k is the weight value of the curve error, q k is the adjusted control point, s(u k ) is the node vector u k The corresponding function value is is the second-order differential of the second weld trajectory;

[0020] The objective function f is solved by using nonlinear least squares algorithm. min Perform optimization and solve to obtain optimized control points;

[0021] A weld trajectory curve is determined according to the optimized control points and the node vectors.

[0022] According to a welding robot trajectory planning method provided by the present invention, determining the robot's posture information according to the weld trajectory curve includes:

[0023] Performing a space curve arc length integration on the weld trajectory curve to obtain a weld length of the weld trajectory curve;

[0024] An S-shaped trajectory is planned for the weld trajectory curve according to the weld length, and the position, velocity and acceleration information of the robot in Cartesian space are obtained as posture information.

[0025] According to a welding robot trajectory planning method provided by the present invention, performing S-shaped trajectory planning on the weld trajectory curve according to the weld length, and obtaining the position, velocity and acceleration information of the robot in Cartesian space as posture information includes:

[0026] According to the current node value u i Calculate the next node value u i+1 :

[0027]

[0028] In the formula, is the first-order derivative of the ith node of the weld trajectory curve with respect to time, is the second-order derivative of the ith node of the weld trajectory curve with respect to time, ΔT is the interpolation period of robot trajectory planning;

[0029] According to the next node value u i+1 and the position of the robot in Cartesian space is calculated by the weld trajectory curve;

[0030] According to the robot Jacobian matrix, the linear velocity and angular velocity vector of the robot Cartesian space and the linear acceleration and angular acceleration vectors of the robot in Cartesian space Calculate the robot's current joint angular velocity vector And the joint angular acceleration vector at the current moment

[0031]

[0032] In the formula, J + is the pseudo-inverse of the Jacobian matrix, J is the robot Jacobian matrix, is the derivative of the robot Jacobian matrix with respect to time, N = (IJ + ·J), q0 is an arbitrary vector, I is the unit matrix;

[0033] According to the current robot joint position vector l i 、The current joint angular velocity vector The joint angular acceleration vector at the current moment And the robot trajectory planning interpolation period ΔT, calculate the robot's joint angle l at the next moment i+1 :

[0034]

[0035] The present invention also provides a welding system, comprising:

[0036] Visual control module, used to obtain point cloud data of welds;

[0037] A host computer module, used for obtaining the position and posture information of the robot according to the point cloud data and using any of the welding robot trajectory planning methods described above;

[0038] The robot control module is used to control the robot to perform welding according to the posture information.

[0039] According to a welding system provided by the present invention, the system also includes: a welding module, which is used to convey welding wire during the robot welding process and perform collision detection on the welding wire.

[0040] According to a welding system provided by the present invention, the system also includes: a light source control module, which is used to control the brightness of the light source during the robot welding process.

[0041] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned welding robot trajectory planning methods is implemented.

[0042] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any of the above-mentioned welding robot trajectory planning methods is implemented.

[0043] The welding robot trajectory planning method, welding system, electronic device and medium provided by the present invention use high-order spatial B-spline curves to fit a point cloud sequence approximating a spatial weld, automatically generate a spatial curve of the trajectory to be welded, and perform curvature optimization on the trajectory curve to be welded to generate a smoother and continuous high-order complex spatial B-spline curve, thereby making the welding trajectory more consistent with the actual weld path and generating a high-order spatial complex welding trajectory with smooth curvature. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 It is a flow chart of a welding robot trajectory planning method provided by an embodiment of the present invention;

[0046] Figure 2 A schematic structural diagram of a welding system provided in an embodiment of the present invention;

[0047] Figure 3 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Figure 1 is a flow chart of a welding robot trajectory planning method provided by an embodiment of the present invention; Figure 1 As shown, the welding robot trajectory planning method includes:

[0050] S101, obtaining point cloud data of the weld.

[0051] In this step, the weld area is feature extracted to obtain 3D point cloud data of the weld, and isolated point clouds are deleted from the point cloud data. The subsequent weld trajectory is generated based on the deleted point cloud data.

[0052] S102, fitting the point cloud data using a B-spline curve to obtain a first weld trajectory.

[0053] S103, performing curvature optimization on the first weld trajectory to obtain a weld trajectory curve.

[0054] S104, determining the position and posture information of the robot according to the weld trajectory curve, and controlling the robot based on the position and posture information.

[0055] In this step, the arc length of the weld trajectory curve is firstly integrated in space to calculate the total length of the weld trajectory curve.

[0056] Then, according to the total length of the weld trajectory curve, the Cartesian space position, velocity and acceleration information of the end point of the robot welding gun wire at each moment are calculated based on the S-shaped trajectory planning.

[0057] Furthermore, the displacement and instantaneous speed of each joint of the robot at each moment are obtained according to the trajectory of the end point of the welding wire of the welding robot.

[0058] Finally, according to the obtained displacement and instantaneous velocity information of each joint of the robot at each moment, the welding gun end of the robot is controlled to move along the welding trajectory at the target speed and target posture.

[0059] The welding robot trajectory planning method provided by the embodiment of the present invention adopts a high-order spatial B-spline curve to fit a point cloud sequence approximating a spatial weld, automatically generates a spatial curve of the trajectory to be welded, and optimizes the curvature of the trajectory curve to be welded to generate a smoother and continuous high-order complex spatial B-spline curve, thereby making the welding trajectory more consistent with the actual weld path and generating a high-order spatial complex welding trajectory with smooth curvature.

[0060] Furthermore, after fitting the point cloud data using the B-spline curve to obtain the first weld trajectory, the method further includes:

[0061] The first weld trajectory is adjusted according to the actual weld trajectory to obtain a second weld trajectory.

[0062] Specifically, the operator of the welding robot observes whether the first weld trajectory is consistent with the actual weld trajectory. If there is a partial inconsistency, the operator drags the first weld trajectory to make the first weld trajectory more closely fit the actual weld trajectory.

[0063] Accordingly, the curvature optimization of the first weld trajectory to obtain a weld trajectory curve includes:

[0064] The curvature of the second weld trajectory is optimized to obtain a weld trajectory curve.

[0065] Further, the adjusting the first weld trajectory according to the actual weld trajectory to obtain the second weld trajectory includes:

[0066] The control points of the first weld trajectory are adjusted according to the actual weld trajectory to obtain the adjusted control points, and the second weld trajectory is obtained based on the adjusted control points.

[0067] Specifically, the discrete welding point cloud sequence {q0,q1,q2…q n}Automatically perform B-spline interpolation, that is, construct the node vectors {u0,u1,u2…u n+p+1}, set the spline order p = 5, and the first weld trajectory is expressed using B-spline as Where qj is the point cloud data sequence (i.e., the control points of the first weld trajectory), is the spline basis function of the p-degree B-spline curve.

[0068] After obtaining the first weld trajectory, the control points of the first weld trajectory are fine-tuned to make the trajectory curve fit the weld of the weldment more closely, and the control points are recorded and saved as a new control point sequence {q'0,q1',q'2…q' n}, which is the adjusted control point.

[0069] Accordingly, the curvature optimization of the second weld trajectory to obtain a weld trajectory curve includes:

[0070] Determine the objective function f according to the adjusted control points, the node vectors of the B-spline curve and the second weld trajectory min :

[0071]

[0072] Where σ is the weight coefficient of curve smoothness, w k is the weight value of the curve error, q k is the adjusted control point, s(u k ) is the node vector u k The corresponding function value is is the second-order differential of the second weld trajectory. The optimization objective function is to optimize the curvature of the trajectory, thereby ensuring the generation of a high-order B-spline curve with smooth curvature and passing through the interpolation points.

[0073] The objective function f is solved by using nonlinear least squares algorithm. min Perform optimization and solve to obtain optimized control points.

[0074] In this embodiment, the Levenberg-Marquardt algorithm is used to calculate the objective function f min Solve to obtain the control point sequence {P0, P1, P2…P n}.

[0075] The weld trajectory curve is determined according to the optimized control points and the node vectors. That is, according to the optimized control point sequence {P0, P1, P2…P n} and the node vector {u0,u1,u2…u n+p+1}Sequence construction of B-spline curve welding trajectory Where P j is the control point sequence, is the spline basis function of the p-degree B-spline curve.

[0076] Further, determining the posture information of the robot according to the weld trajectory curve includes:

[0077] The arc length of the weld trajectory curve is integrated in space to obtain the weld length s of the weld trajectory curve, that is, In the formula, B x '(u) is the derivative of the spline curve in the X direction with respect to the node, B y '(u) is the derivative of the spline curve in the Y direction with respect to the node, B z '(u) is the derivative of the spline curve in the Z direction with respect to the node.

[0078] An S-shaped trajectory is planned for the weld trajectory curve according to the weld length, and the position, velocity and acceleration information of the robot in Cartesian space are obtained as posture information.

[0079] Further, performing S-shaped trajectory planning on the weld trajectory curve according to the weld length to obtain the position, velocity and acceleration information of the robot in Cartesian space as the posture information includes:

[0080] According to the current node value u i Calculate the next node value u i+1 :

[0081]

[0082] In the formula, is the first-order derivative of the ith node of the weld trajectory curve with respect to time, is the second-order derivative of the ith node of the weld trajectory curve with respect to time, and ΔT is the interpolation period of robot trajectory planning.

[0083] in,

[0084] is the first-order derivative of the B-spline curve with respect to the node vector u,

[0085] is the second-order derivative of the B-spline curve with respect to the node vector u,

[0086] v i is the motion speed of the Cartesian space robot in the i-th cycle,

[0087] a i is the motion acceleration of the Cartesian space robot in the i-th cycle,

[0088] is the first-order derivative of the weld trajectory curve equation at the ith node with respect to time,

[0089] is the second-order derivative of the i-th node of the weld trajectory curve equation with respect to time.

[0090] According to the next node value u i+1 And the weld trajectory curve is calculated to obtain the robot's Cartesian space position Q i+1 =B(u i+1 ).

[0091] According to the robot Jacobian matrix, the linear velocity and angular velocity vector of the robot Cartesian space and the linear acceleration and angular acceleration vectors of the robot in Cartesian space Calculate the robot's current joint angular velocity vector And the joint angular acceleration vector at the current moment

[0092]

[0093] In the formula, J + is the pseudo-inverse of the Jacobian matrix, J is the robot Jacobian matrix, is the derivative of the robot Jacobian matrix with respect to time, N = (IJ + ·J), q0 is an arbitrary vector, and I is the identity matrix.

[0094] According to the current robot joint position vector l i 、The current joint angular velocity vector The joint angular acceleration vector at the current moment And the robot trajectory planning interpolation period ΔT, calculate the robot's joint angle l at the next moment i+1 :

[0095]

[0096] Specifically, the robot control module in the welding system is connected to the driver in the robot via EtherCAT communication. The robot control module sends the joint angle and joint angular velocity information of each joint at each moment to the driver. At the same time, the robot control module is connected to the welding gun in the robot for communication. The robot controls the end of the welding gun to move along the welding motion trajectory at a target speed and target posture based on the acquired angle and instantaneous velocity information of each joint at each moment.

[0097] The welding system provided by the present invention is described below. The welding system described below and the welding robot trajectory planning method described above can be referenced to each other.

[0098] Figure 2 A schematic diagram of the structure of a welding system provided in an embodiment of the present invention is shown in FIG. Figure 2 As shown, a welding system comprises:

[0099] The visual control module 201 is used to obtain the point cloud data of the weld.

[0100] The host computer module 202 is used to obtain the position and posture information of the robot according to the point cloud data and by using the welding robot trajectory planning method as described above.

[0101] The robot control module 203 is used to control the robot to perform welding according to the posture information.

[0102] The welding module 204 is used to convey the welding wire during the robot welding process and perform collision detection on the welding wire.

[0103] The light source control module 205 is used to control the brightness of the light source during the robot welding process. Specifically, the light source control module is used to control the light source to be on or off, or to adjust the brightness or darkness of the light source, and to control the brightness of the light source by changing the magnitude of the current.

[0104] It should be noted that the robot control module is respectively connected with the light source control module, the visual control module, the welding module and the upper computer software module through communication or I / O control.

[0105] The welding system provided by the embodiment of the present invention obtains the posture information of the robot according to the welding robot trajectory planning method, and then controls the robot based on the acquired posture information, thereby improving the welding quality.

[0106] Figure 3 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the electronic device may include: a processor 310 (processor), a communication interface 320 (Communications Interface), a memory 330 (memory) and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the welding robot trajectory planning method, the welding robot trajectory planning method comprising: obtaining point cloud data of the weld; fitting the point cloud data using a B-spline curve to obtain a first weld trajectory; optimizing the curvature of the first weld trajectory to obtain a weld trajectory curve; determining the robot's posture information according to the weld trajectory curve, and controlling the robot based on the posture information.

[0107] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0108] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the welding robot trajectory planning method provided by the above-mentioned method. The welding robot trajectory planning method includes: acquiring point cloud data of the weld; fitting the point cloud data using a B-spline curve to obtain a first weld trajectory; optimizing the curvature of the first weld trajectory to obtain a weld trajectory curve; determining the robot's posture information according to the weld trajectory curve, and controlling the robot based on the posture information.

[0109] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0110] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A welding robot trajectory planning method, characterized in that: include: Get the point cloud data of the weld; Fitting the point cloud data using a B-spline curve to obtain a first weld trajectory; Performing curvature optimization on the first weld trajectory to obtain a weld trajectory curve; Determining the position and posture information of the robot according to the weld trajectory curve, and controlling the robot based on the position and posture information; Wherein, after fitting the point cloud data by using the B-spline curve to obtain the first weld trajectory, the method further includes: Adjusting the first weld trajectory according to an actual weld trajectory to obtain a second weld trajectory; Accordingly, the curvature optimization of the first weld trajectory to obtain a weld trajectory curve includes: performing curvature optimization on the second weld trajectory to obtain a weld trajectory curve; Wherein, adjusting the first weld trajectory according to the actual weld trajectory to obtain the second weld trajectory includes: Adjusting the control points of the first weld trajectory according to the actual weld trajectory to obtain adjusted control points, and obtaining the second weld trajectory based on the adjusted control points; Accordingly, the curvature optimization of the second weld trajectory to obtain a weld trajectory curve includes: Determine the objective function according to the adjusted control points, the node vectors of the B-spline curve and the second weld trajectory : In the formula, is the weight coefficient of curve smoothness, is the weight value of the curve error, is the adjusted control point, is the node vector The corresponding function value is is the second-order differential of the second weld trajectory; The objective function is solved by using nonlinear least squares algorithm. Perform optimization and solve to obtain optimized control points; Determine a weld trajectory curve according to the optimized control points and the node vectors; Wherein, determining the position and posture information of the robot according to the weld trajectory curve includes: Performing a space curve arc length integration on the weld trajectory curve to obtain a weld length of the weld trajectory curve; Performing S-shaped trajectory planning on the weld trajectory curve according to the weld length, and obtaining the position, velocity and acceleration information of the robot in Cartesian space as posture information; Among them, performing S-shaped trajectory planning on the weld trajectory curve according to the weld length, and obtaining the position, velocity and acceleration information of the robot in Cartesian space as the posture information includes: Based on the current node value Calculate the next node value : In the formula, The weld trajectory curve The first-order derivative of a node with respect to time, The weld trajectory curve The second-order derivative of the nodes with respect to time, Plan interpolation cycles for robot trajectories; According to the next node value and the position of the robot in Cartesian space is calculated by the weld trajectory curve; According to the robot Jacobian matrix, the linear velocity and angular velocity vector of the robot Cartesian space and the linear acceleration and angular acceleration vectors of the robot in Cartesian space , calculate the robot's current joint angular velocity vector And the joint angular acceleration vector at the current moment : In the formula, is the pseudo-inverse of the Jacobian matrix, is the robot Jacobian matrix, is the derivative of the robot Jacobian matrix with respect to time, , is the identity matrix; According to the current robot joint position vector 、The current joint angular velocity vector , the joint angular acceleration vector at the current moment And the robot trajectory planning interpolation cycle , calculate the robot's joint angle at the next moment : 。 2. A welding system, characterized in that: include: Visual control module, used to obtain point cloud data of welds; A host computer module, used for obtaining the position and posture information of the robot according to the point cloud data and using the welding robot trajectory planning method as claimed in claim 1; The robot control module is used to control the robot to perform welding according to the posture information.

3. The welding system according to claim 2, characterized in that: The system also includes: The welding module is used to transport the welding wire during the robotic welding process and perform collision detection on the welding wire.

4. The welding system according to claim 2, characterized in that: The system also includes: The light source control module is used to control the brightness of the light source during the robot welding process.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the welding robot trajectory planning method as claimed in claim 1 is implemented.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the welding robot trajectory planning method as claimed in claim 1 is implemented.

Images