Track planning method for mechanical arm to pass through space passing points based on improved dynamic motion primitives

Abstract

The invention provides a trajectory planning method for a mechanical arm to pass through a space passing point based on an improved dynamic motion primitive, and belongs to the technical field of robots. Firstly, the mechanical arm obtains a teaching trajectory, an improved dynamic motion primitive algorithm is used for learning the preprocessed teaching trajectory, and the teaching trajectory is obtained; the DMP can generate a motion mode similar to the teaching track; through a depth camera installed around the mechanical arm or at a fixed position, information, shapes and motion states of passing points are obtained in real time, the detected information of the passing points serves as input, and attraction steering force and regression steering force are quantified; the DMP is dynamically updated for real-time adjustment, based on the Lyapunov stability theory, the stability of the improved DMP algorithm is proved, and it is ensured that the motion trail of the mechanical arm in the dynamic environment is converged to a target point; and finally, carrying out an experiment to verify the dynamic passing point crossing capability of the mechanical arm. Under the condition that the starting point and the end point are not changed, an additional learning process is not needed, and the practicability and the efficiency of the system are improved.

Description

Technical Field

[0001] The present invention belongs to the field of robot technology, and in particular, relates to a trajectory planning method for a robot arm to pass through a space waypoint based on an improved dynamic motion primitive. Background Art

[0002] When the robot arm completes the on-orbit operation task in space, it faces the challenges of narrow working space and frequent dynamic changes in the environment. The robot arm needs to operate accurately in a limited space, and may need to pass through specific waypoints during the operation to ensure the smooth progress of the task. However, the current trajectory planning mostly adopts manual programming, which is not only inefficient, but also cumbersome to change the program, and it is difficult to adapt to the task requirements in complex dynamic environments. In order to improve the adaptability and operation efficiency of the robot arm in complex environments, learning from demonstration (Learn from Demonstration, LfD) as an emerging technology can transfer the skills of human operators to the robot arm and realize the generalization of skills, thus providing a new idea for the trajectory planning of the robot arm. Among them, dynamic movement primitives (DMP) is a commonly used teaching learning method, which is widely used in trajectory planning and task execution of the robot arm. DMP decomposes complex motion trajectories into a series of simple motion patterns, enabling the robot arm to perform complex humanoid movements in a flexible and creative way. However, the traditional DMP method is insufficient in the following aspects:

[0003] Inability to effectively navigate dynamic waypoints: When performing motion at waypoints, traditional DMP methods have difficulty ensuring that the robot arm can accurately navigate these points.

[0004] Insufficient ability to adjust trajectory shape: Traditional DMP methods have difficulties in adjusting trajectory shape and cannot flexibly adapt to complex task requirements.

[0005] Excessive loss of free space: When passing through waypoints, traditional methods often sacrifice too much free space, resulting in a limited range of motion for the robot arm and reduced operating efficiency.

[0006] Poor adaptability: In a dynamic environment, traditional DMP methods have difficulty adapting to changes in the environment and task requirements, and require re-demonstration or parameter adjustment.

[0007] In view of the above problems, in order to adapt to the needs of on-orbit operation tasks of the robotic arm, improve the ability of DMP to cross waypoints in the generalization process, realize the modification of trajectory shape, and reduce the free space loss, it is particularly important to propose a new trajectory planning method. Summary of the invention

[0008] In order to solve the problem that the existing DMP method cannot pass through dynamic waypoints in complex dynamic environments, the present invention proposes a trajectory planning method for a robotic arm to pass through space waypoints based on improved dynamic motion primitives (DMP) and steering force fields. By introducing steering force field constraints, the trajectory adjustment capability of DMP is enhanced, and the dynamic waypoints can be passed in the generalization process, thereby reducing the free space loss.

[0009] The present invention is achieved through the following technical solutions:

[0010] A trajectory planning method for a robotic arm crossing space waypoints based on improved dynamic motion primitives:

[0011] The method specifically comprises the following steps:

[0012] Step 1, enabling the robot arm to obtain the teaching trajectory and perform preprocessing;

[0013] Step 2, using an improved dynamic motion primitive (DMP) algorithm to learn the preprocessed teaching trajectory, so that the DMP can generate a motion pattern similar to the teaching trajectory;

[0014] Step 3: Using a depth camera installed around the robot arm or at a fixed position, the waypoint information and motion status are acquired in real time, and the detected waypoint information is used as input to quantify the attraction steering force and the regression steering force;

[0015] Step 4: Dynamically update the DMP for real-time adjustment, and based on the Lyapunov stability theory, prove the stability of the improved DMP algorithm to ensure that the motion trajectory of the robot in a dynamic environment converges to the target point;

[0016] Step 5: Conduct experiments to verify the robot's ability to traverse dynamic waypoints.

[0017] Furthermore, in step 1,

[0018] The teaching trajectory is the motion path of the robot arm when completing a specific task, which is manually demonstrated or given in advance by a human operator;

[0019] The acquired teaching trajectory is preprocessed, and the preprocessing includes noise removal, smoothing and normalization; the preprocessed trajectory data will be used as the basic data for DMP learning.

[0020] Furthermore, in step 2,

[0021] The specific implementation process of the improved dynamic motion primitive algorithm is as follows: on the basis of the traditional DMP, a steering force field coupling term is introduced;

[0022] The traditional dynamic motion primitive (DMP) equation is:

[0023]

[0024] In the formula, τ is the time scale factor, the system duration can be adjusted by τ, x is the current position, x init is the initial position, g is the target position, v and are velocity and acceleration respectively, and the diagonal d×d matrix A=diag[α1,α2,…,α d ],B=diag[β1,β2,…,β d ] are elastic term and damping term respectively, λ is a predefined positive constant, and f(s) is a forcing term composed of N weighted radial basis functions, which can be expressed as:

[0025]

[0026] in is the radial basis function, ω i Represents the weight of the radial basis function. When the initial state or target state of the trajectory changes, ω i It has the ability to generalize and can generate similar trajectories;

[0027] The method of adding coupling terms on the basis of DMP, the improved DMP control equation is:

[0028]

[0029] Among them, the additional items is the waypoint coupling term.

[0030] Further, in step 3, the steering attraction is first quantified;

[0031] Suppose a passing point P. In order to make the planned trajectory pass through point P, point P is set as an "attractive point". The attractive point generates attraction, which causes the trajectory to turn in its direction. The direction of attraction is perpendicular to the current speed v and is directed toward point P. After the direction of attraction is determined, its magnitude will determine whether the proposed method can make the trajectory pass through point P.

[0032] In the process of dynamically approaching point P, the distance d between the end effector position X and point P, and the angle θ between the current velocity direction v and XP are included in the steering force measurement index; at this time, the steering attraction f a1 It is expressed as:

[0033]

[0034] Where v is the velocity, d = |XP| represents the distance between the end effector position X and point P, Indicates the angle between the current velocity direction v and XP, is a function of d, is a function of θ;

[0035] Separate analysis and in represents a function related to d, d min is the minimum value from point P to the teaching trajectory. After passing point P, Set to:

[0036] Before passing point P

[0037] After point P

[0038] Where μ1 is the constant, d min is the minimum value from point P to the teaching trajectory;

[0039] represents a function related to θ, θ∈(0,π), Set to

[0040]

[0041] where η1 is the constant.

[0042] From the above, we can get the turning attraction f a1 :

[0043]

[0044] Where R is the rotation or The rotation matrix of .

[0045] Furthermore, in step 3

[0046] Quantifying the regression attraction f a2 To balance the attraction generated by the passing point P, during the dynamic approach process, the current speed v is compared with the original trajectory speed v d The angle φ and the Euclidean distance δ between the current trajectory and the original trajectory are included as influencing factors in f a2 item,

[0047]

[0048] in δ=|X-X0|

[0049] The resultant total turning force field: In a dynamic environment where point P moves at a variable speed, the relative speed v r The definition is as follows:

[0050] v r =vv p

[0051] where v p represents the velocity vector of point P; at this time, the coupling term of the system can be expressed as:

[0052]

[0053] Furthermore, in step 4,

[0054] Real-time update of steering force field coupling terms: During the movement of the robot arm, the steering force field coupling terms are calculated in real time And add it to the control equation of DMP; the steering force field coupling term is adjusted in real time according to the dynamic changes of the waypoint to ensure that the robot arm can effectively pass through the waypoint.

[0055] Furthermore, in step 4,

[0056] It is proved that the expression of the coupling term satisfies the Lyapunov stability criterion and all starting points converge to the target;

[0057] When t→∞, the phase variable x approaches 0; therefore, the simplified DMP equation It can be expressed as:

[0058]

[0059] point is the stationary point of the equation; construct a Lyapunov function V and prove Therefore, it is shown that all points will converge to this stationary point; using the energy function of the damped spring mass system

[0060]

[0061]

[0062] Since R is a matrix rotated by π / 2, we can get v T Rv=0, It is proved that DMP converges to

[0063] A trajectory planning system for a robotic arm traversing space waypoints based on improved dynamic motion primitives:

[0064] The trajectory planning system includes a preprocessing module, a DMP learning module, a steering force quantification module and a verification module:

[0065] The preprocessing module enables the robot arm to obtain the teaching trajectory and perform preprocessing;

[0066] The DMP learning module uses an improved dynamic motion primitive (DMP) algorithm to learn the preprocessed teaching trajectory, so that the DMP can generate a motion pattern similar to the teaching trajectory;

[0067] The steering force quantification module obtains waypoint information and motion status in real time through a depth camera installed around the robot arm or at a fixed position, and uses the detected waypoint information as input to quantify the attraction steering force and the regression steering force;

[0068] The verification module dynamically updates the DMP for real-time adjustment, and based on the Lyapunov stability theory, proves the stability of the improved DMP algorithm to ensure that the motion trajectory of the robot in a dynamic environment converges to the target point; finally, experiments are conducted to verify the ability of the robot to cross dynamic waypoints.

[0069] An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0070] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the steps of the above method are implemented.

[0071] Beneficial effects of the present invention

[0072] Compared with the prior art, the present invention has the following effects:

[0073] Improved generalization ability: By introducing steering attraction and regression attraction, the generalization ability of DMP in dynamic environments is significantly improved, allowing the robot arm to flexibly pass through dynamic waypoints without changing the starting and ending points.

[0074] Reduced free space loss: By dynamically adjusting the trajectory shape, the loss of free space is significantly reduced, and the range of motion and operating efficiency of the robot arm are improved.

[0075] Enhanced adaptability: Lyapunov stability analysis ensures that the robot arm's motion trajectory in a dynamic environment is stable and reliable, and can adapt to changes in the environment and task requirements.

[0076] No additional learning required: Without changing the starting point and the end point, navigation to dynamic waypoints can be achieved by adjusting the parameters, without the need for additional learning, which improves the practicality and efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 is the two-dimensional steering attraction f a1 The impact on the trajectory, where (a)f a1 Factors affecting (b)f a1Generalized trajectory of static waypoints under action.

[0078] Figure 2 is the two-dimensional steering attraction f a1 , two-dimensional regression attraction f a2 The impact on the trajectory, where (a)f a2 Factors affecting (b)f a1 、f a2 Generalized trajectory of static waypoints under action.

[0079] Figure 3 f a1 、f a2 Generalized trajectory of dynamic waypoints under action, including (a) initial state, (b) approaching the waypoint, (c) passing the waypoint, and (d) ending state.

[0080] Figure 4 The influence of three-dimensional attraction on the trajectory, including (a) the influencing factors of three-dimensional attraction and (b) the generalized trajectory of static waypoints under the action of three-dimensional attraction.

[0081] Figure 5 This is an example diagram of setting up the experimental system of the present invention.

[0082] Figure 6 Snapshots of the experiments in the examples. DETAILED DESCRIPTION

[0083] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0084] The experimental methods used in the following examples are conventional methods unless otherwise specified. The materials, reagents, methods and instruments used are conventional materials, reagents, methods and instruments in the art unless otherwise specified, and can be obtained through commercial channels by those skilled in the art.

[0085] Combination Figures 1 to 6 The present invention provides a trajectory planning method for a robotic arm crossing a space waypoint based on a dynamic motion primitive (DMP) and a steering force field, including an improved dynamic motion primitive (DMP) algorithm, quantified attractive steering force and regressive steering force, Lyapunov stability analysis, and experimental verification of crossing waypoints.

[0086] System settings such as Figure 5Figure 1 shows a 7-DOF Franka Emika Panda robotic arm, a table with waypoints and depth cameras, and the waypoints are driven by servo motors. The camera is used to detect the location of obstacles, and the robotic arm is controlled using the ROS framework on Ubuntu 20.04 to move over the entire tabletop while passing through the waypoints.

[0087] Step 1, enabling the robot arm to obtain the teaching trajectory and perform preprocessing;

[0088] The teaching trajectory is the motion path of the robot arm when completing a specific task, which is usually demonstrated manually or given in advance by a human operator. For example, the drag-and-drop teaching method can be used to allow the operator to manually guide the robot arm to complete a complete task operation, record its position, speed and time information, and pre-process the obtained teaching trajectory, including noise removal, smoothing and normalization. The pre-processed trajectory data will serve as the basic data for DMP learning.

[0089] The teaching trajectory of this example is given in advance, and the teaching trajectory equation is: x=0.5sin(-t), y=0.5cos(t), z=0.3, where t∈(0,π), x, y, z are the Cartesian coordinates of the end of the robot arm in the base coordinate system.

[0090] Step 2, DMP parameter learning: Apply the improved DMP algorithm to learn the preprocessed teaching trajectory. The radial basis function weights in the DMP are adjusted through optimization algorithms (such as local weighted regression, LWR) so that the DMP can generate motion patterns similar to the teaching trajectory. After learning is completed, the DMP will have the ability to generate similar trajectories when the target state changes.

[0091] The specific implementation process of the improved dynamic motion primitive (DMP) algorithm is as follows: on the basis of traditional DMP, a steering force field coupling term is introduced, including the attraction of different waypoints and the regression force generated by the teaching trajectory, to achieve crossing dynamic waypoints. Traditional dynamic motion primitive (DMP) equation:

[0092]

[0093] In the formula, τ is the time scale factor, the system duration can be adjusted by τ, x is the current position, x init is the initial position, g is the target position, v and are velocity and acceleration respectively, and the diagonal d×d matrix A=diag[α1,α2,…,α d ],B=diag[β1,β2,…,β d ] are elastic term and damping term respectively, λ is a predefined positive constant, and f(s) is a forcing term composed of N weighted radial basis functions, which can be expressed as:

[0094]

[0095] where ω i represents the weights of the radial basis functions. An optimization algorithm such as Locally Weighted Regression (LWR) can be used to select appropriate model parameters for these basis functions so that the forcing function matches the desired trajectory. When the initial state or target state of the trajectory changes, ω i It has the ability to generalize and can generate similar trajectories. In addition, f depends on the phase variable s, which is a reparameterization of time t and is controlled by the so-called canonical system. The transient behavior of s is defined as:

[0096]

[0097] Where λ is a predefined positive constant. Radial basis function It can be defined as follows:

[0098]

[0099] where exp(·) is an exponential function. The width of the Gaussian function h is i It can be calculated by the following formula:

[0100] h i =(c i+1 -c i ) -2 ,h N =h N-1

[0101] The center c of the Gaussian function i It can be calculated as follows:

[0102]

[0103] The method of adding waypoint coupling terms on the basis of DMP has the following control equation:

[0104]

[0105] Among them, the additional items is the waypoint coupling term.

[0106] Step 3, obtaining the waypoint information, and quantifying the attraction steering force and the regression steering force;

[0107] Waypoint detection and identification: Use a depth camera installed around the robot arm or in a fixed position to obtain waypoint information in the working environment in real time. Use image processing or point cloud analysis algorithms to identify the shape, position, and motion state of the waypoints. For example, video analysis algorithms such as optical flow can be used to extract the speed and direction of the waypoints. In this example, the speeds of the two waypoints are 4 mm / s respectively.

[0108] Data import and processing: Import the detected waypoint information (including position, speed, etc.) into the computer system. Further process the waypoint information, such as coordinate conversion, data filtering, etc., to ensure the accuracy and real-time nature of the data, and use the data as input for calculating the steering force.

[0109] The specific implementation process of the quantified steering force is: by analyzing the position and motion state of the waypoint, the quantified steering attraction is realized to cross the dynamic waypoint. The direction and magnitude of the attraction are dynamically adjusted according to the distance and angle between the waypoint and the original trajectory to ensure that the dynamic waypoint is crossed.

[0110] In order to make the planned trajectory pass through point P, point P is set as the "attractor point". The attraction point generates attraction, which causes the trajectory to turn in its direction. The attraction direction is perpendicular to the current speed v and is toward point P, such as Figure 1 (a). After the attraction direction is determined, its magnitude will determine whether the proposed method can make the trajectory pass through point P. In the process of dynamically approaching point P, the distance d between the end effector position X of the robot and point P, and the angle θ between the current velocity direction v and XP are important factors. Therefore, it is considered to include them in the steering force magnitude measurement index. At this time, the steering attraction f a1 It is expressed as:

[0111]

[0112] Where v is the velocity, d = |XP| represents the distance between the end effector position X and point P, Indicates the angle between the current velocity direction v and XP, is a function of d, is a function of θ.

[0113] Separate analysis and in It represents a function related to d. In order to prevent the attraction from excessively affecting the original trajectory and reduce the loss of free space, it is hoped that when d is large or small are both small, when d=d min When the value is near Larger, d min is the minimum value from point P to the teaching trajectory. After passing point P, Set to:

[0114] Before passing point P

[0115] After point P

[0116] Where μ1 is the constant, d min It is the minimum value from point P to the teaching trajectory.

[0117] Represents a function related to θ, θ∈(0,π), and it is hoped that when θ is large, The influence is greater when θ is smaller. Small impact, Set to

[0118]

[0119] where η1 is the constant.

[0120] From the above, we can get the turning attraction f a1 :

[0121]

[0122] Where R is the rotation or The rotation matrix of .

[0123] The planned trajectory at this time is as follows Figure 1 As shown in (b), it can be found that under the attraction f a1 Under the action of , the generalized trajectory passes through the waypoint P and has little impact on the original teaching trajectory.

[0124] A high-quality planned trajectory should skillfully pass through the waypoints and be as close to the original trajectory as possible, which can improve the similarity with the original trajectory and reduce the loss of free space. Therefore, adding the original trajectory attraction f a2 To balance the attraction generated by the passing point P. In the dynamic approach process, the current speed v is compared with the original trajectory speed v d The angle φ and the Euclidean distance δ between the current trajectory and the original trajectory are included as influencing factors in f a2 Items, such as Figure 2 (a):

[0125]

[0126] in δ=|X-X0|

[0127] Add attraction a2 The planning trajectory obtained is Figure 3 (b), the dotted line indicates that f a1 、f a2 The obtained planned trajectory. It can be found that the loss of free space is reduced and the similarity between the planned trajectory and the original trajectory is improved.

[0128] Synthetic total steering force field: In a dynamic environment where point P moves at a variable speed, two factors need to be focused on: one is the relative speed v between the end effector of the robot and point P r , the second is the distance d, δ, the angle θ, Both are real-time distance and real-time angle. r It can be defined as follows:

[0129] v r =vv p

[0130] where v p Represents the velocity vector of point P. At this time, the coupling term of the system can be expressed as:

[0131]

[0132] Dynamic programming simulation process Figure 3 The results show that this method not only solves the problem of passing through point P in a dynamic environment, but also generates a motion trajectory that meets the teaching intention.

[0133] In three-dimensional space, when determining the magnitude of the steering force, d, θ, δ, It is difficult to generalize equal distances and angles from two-dimensional space to three-dimensional space. Figure 4 As shown in (a), the key point is to determine the direction of attraction, that is, to give an expression for R. Define f to be in the plane formed by point P and vector v, with the direction being around the axis of rotation Rotation or Towards point P. So the expression for R is:

[0134]

[0135] in n x 、n y 、n z is the component of vector n in the xyz direction.

[0136] The planned trajectory at this time is as follows Figure 4 As shown in (b), the results show that the motion planning method designed by the present invention is also applicable in three-dimensional space.

[0137] Step 4, update the DMP and construct the Lyapunov equation,

[0138] Real-time update of steering force field coupling terms: During the movement of the robot arm, the steering force field coupling terms are calculated in real time And add it to the control equation of DMP. The steering force field coupling term is adjusted in real time according to the dynamic changes of the waypoint to ensure that the robot arm can effectively pass through the waypoint.

[0139] Based on the Lyapunov stability theory, the stability of the improved DMP algorithm is proved to ensure that the motion trajectory of the robot in a dynamic environment converges to the target point.

[0140] The specific implementation process of the Lyapunov stability analysis is: prove that the expression of the coupling term satisfies the Lyapunov stability criterion and that all starting points converge to the target. When t→∞, the phase variable x tends to 0. Therefore, the simplified DMP equation It can be expressed as:

[0141]

[0142] point is the stationary point of the equation. Construct a Lyapunov function V and prove that Therefore, it is shown that all points will converge to this stationary point. Using the energy function of the damped spring mass system

[0143]

[0144] Since R is a matrix rotated by π / 2, we can get v T Rv=0, It is proved that DMP converges to

[0145] Step 5: Conduct experimental verification to verify the ability of the robot arm to traverse dynamic waypoints;

[0146] The specific implementation process of the experimental verification is as follows: the effectiveness of the method of the present invention is verified through a series of numerical simulations and Franka robot arm experiments. The specific experimental settings and experimental results will be reflected in the specific implementation methods. The experimental results show that this method can provide reliable trajectory planning for the robot arm in a complex dynamic environment and significantly improve the generalization operation capability of the robot arm.

[0147] The center of the Franka robot base is taken as the coordinate origin. Figure 6 As shown in the figure, the snapshots of the experimental process show the trajectory of the Franka robot end effector. Each row of figures represents an experimental process consisting of 3 snapshots. The initial position and the target position are: x init=[-0.5, 0.0, 0.3] and g = [0.0, 0.5, 0.5]. To verify the effectiveness of the method, the waypoints are placed at [0.4, 0.2, 0.4] and [0.18, 0.4, 0.45], and the speeds are [0.0, 2.5, 0.0] mm / s and [0.0, 2.5, 0.0] mm / s respectively. The results show that the trajectory planned by this scheme can effectively pass through the waypoints.

[0148] A trajectory planning system for a robotic arm traversing space waypoints based on improved dynamic motion primitives:

[0149] The trajectory planning system includes a preprocessing module, a DMP learning module, a steering force quantification module and a verification module:

[0150] The preprocessing module enables the robot arm to obtain the teaching trajectory and perform preprocessing;

[0151] The DMP learning module uses an improved dynamic motion primitive (DMP) algorithm to learn the preprocessed teaching trajectory, so that the DMP can generate a motion pattern similar to the teaching trajectory;

[0152] The steering force quantification module obtains waypoint information, shape and motion status in real time through a depth camera installed around the robot arm or at a fixed position, and uses the detected waypoint information as input to quantify the attraction steering force and the regression steering force;

[0153] The verification module dynamically updates the DMP for real-time adjustment, and based on the Lyapunov stability theory, proves the stability of the improved DMP algorithm to ensure that the motion trajectory of the robot in a dynamic environment converges to the target point; finally, experiments are conducted to verify the ability of the robot to cross dynamic waypoints.

[0154] An electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0155] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the steps of the above method are implemented.

[0156] The memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory, ROM, a programmable read-only memory, PROM, an erasable programmable read-only memory, EPROM, an electrically erasable programmable read-only memory, EEPROM, or a flash memory. The volatile memory may be a random access memory, RAM, which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory static RAM, SRAM, dynamic random access memory dynamic RAM, DRAM, synchronous dynamic random access memory synchronous DRAM, SDRAM, double data rate synchronous dynamic random access memory double data rate SDRAM, DDR SDRAM, enhanced synchronous dynamic random access memory enhanced SDRAM, ESDRAM, synchronous link dynamic random access memory synchlink DRAM, SLDRAM, and direct memory bus random access memory direct rambus RAM, DR RAM. It should be noted that memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0157] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center through a wired method such as coaxial cable, optical fiber, digital subscriber line digital subscriber line, DSL or wireless such as infrared, wireless, microwave, etc. to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium such as a floppy disk, a hard disk, a tape, an optical medium such as a high-density digital video disc digital video disc, DVD, or a semiconductor medium such as a solid state hard disk solid state disc, SSD, etc.

[0158] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0159] It should be noted that the processor in the embodiment of the present application can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor can be combined to perform. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0160] The above is a detailed introduction to the trajectory planning method for a robotic arm crossing a space waypoint based on an improved dynamic motion primitive proposed in the present invention, and the principles and implementation methods of the present invention are explained. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A trajectory planning method for a robot arm passing through a space waypoint based on an improved dynamic motion primitive, characterized in that: The method specifically comprises the following steps: Step 1, enabling the robot arm to obtain the teaching trajectory and perform preprocessing; Step 2, using an improved dynamic motion primitive (DMP) algorithm to learn the preprocessed teaching trajectory, so that the DMP can generate a motion pattern similar to the teaching trajectory; Step 3: Using a depth camera installed around the robot arm or at a fixed position, the waypoint information and motion status are acquired in real time, and the detected waypoint information is used as input to quantify the attraction steering force and the regression steering force; Step 4: Dynamically update the DMP for real-time adjustment, and based on the Lyapunov stability theory, prove the stability of the improved DMP algorithm to ensure that the motion trajectory of the robot in a dynamic environment converges to the target point; Step 5: Conduct experiments to verify the robot's ability to traverse dynamic waypoints.

2. The planning method according to claim 1, characterized in that: In step 1, The teaching trajectory is the motion path of the robot arm when completing a specific task, which is manually demonstrated or given in advance by a human operator; The acquired teaching trajectory is preprocessed, and the preprocessing includes noise removal, smoothing and normalization; the preprocessed trajectory data will be used as the basic data for DMP learning.

3. The planning method according to claim 2, characterized in that: In step 2, The specific implementation process of the improved dynamic motion primitive algorithm is as follows: on the basis of the traditional DMP, a steering force field coupling term is introduced; The traditional dynamic motion primitive (DMP) equation is: In the formula, τ is the time scale factor, the system duration can be adjusted by τ, x is the current position, x init is the initial position, g is the target position, v and are velocity and acceleration respectively, and the diagonal d×d matrix A=diag[α1,α2,…,α d ],B=diag[β1,β2,…,β d ] are elastic term and damping term respectively, λ is a predefined positive constant, and f(s) is a forcing term composed of N weighted radial basis functions, which can be expressed as: in is the radial basis function, ω i Represents the weight of the radial basis function. When the initial state or target state of the trajectory changes, ω i It has the ability to generalize and can generate similar trajectories; The method of adding coupling terms on the basis of DMP, the improved DMP control equation is: Among them, the additional items is the waypoint coupling term.

4. The planning method according to claim 3, characterized in that: In step 3, the steering attractiveness is first quantified; Suppose there is a passing point P. In order to make the planned trajectory pass through point P, point P is set as an "attractive point". The attractive point generates attraction, which causes the trajectory to turn in its direction. The direction of attraction is perpendicular to the current speed v and is directed toward point P. After the direction of attraction is determined, its magnitude will determine whether the proposed method can make the trajectory pass through point P. In the process of dynamically approaching point P, the distance d between the end effector position X and point P, and the angle θ between the current velocity direction v and XP are included in the steering force measurement index; at this time, the steering attraction f a1 It is expressed as: Where v is the velocity, d = |XP| represents the distance between the end effector position X and point P, Indicates the angle between the current velocity direction v and XP, is a function of d, is a function of θ; Separate analysis and in represents a function related to d, d min is the minimum value from point P to the teaching trajectory. After passing point P, Set to: Before passing point P After point P Where μ1 is the constant, d min is the minimum value from point P to the teaching trajectory; represents a function related to θ, θ∈(0,π), Set to where η1 is the constant. From the above, we can get the turning attraction f a1 : Where R is the rotation or The rotation matrix of .

5. The planning method according to claim 4, characterized in that: In step 3 Quantifying the regression attraction f a2 To balance the attraction generated by the passing point P, during the dynamic approach process, the current speed v is compared with the original trajectory speed v d Angle The Euclidean distance δ between the current trajectory and the original trajectory is included as an influencing factor in f a2 item, in δ=|X-X0| The resultant total turning force field: In a dynamic environment where point P moves at a variable speed, the relative speed v r The definition is as follows: v r =vv p where v p represents the velocity vector of point P; at this time, the coupling term of the system can be expressed as:

6. The planning method according to claim 4, characterized in that: In step 4, Real-time update of steering force field coupling terms: During the movement of the robot arm, the steering force field coupling terms are calculated in real time And add it to the control equation of DMP; the steering force field coupling term is adjusted in real time according to the dynamic changes of the waypoint to ensure that the robot arm can effectively pass through the waypoint.

7. The planning method according to claim 6, characterized in that: In step 4, It is proved that the expression of the coupling term satisfies the Lyapunov stability criterion and all starting points converge to the target; When t→∞, the phase variable x approaches 0; therefore, the simplified DMP equation It can be expressed as: point is the stationary point of the equation; construct a Lyapunov function V and prove Therefore, it is shown that all points will converge to this stationary point; using the energy function of the damped spring mass system Since R is a matrix rotated by π / 2, we can get v T Rv=0, It is proved that DMP converges to 8. A trajectory planning system for executing the trajectory planning method for a robot arm passing through a space waypoint based on an improved dynamic motion primitive as claimed in any one of claims 1 to 7, characterized in that: The trajectory planning system includes a preprocessing module, a DMP learning module, a steering force quantification module and a verification module: The preprocessing module enables the robot arm to obtain the teaching trajectory and perform preprocessing; The DMP learning module uses an improved dynamic motion primitive (DMP) algorithm to learn the preprocessed teaching trajectory, so that the DMP can generate a motion pattern similar to the teaching trajectory; The steering force quantification module obtains waypoint information and motion status in real time through a depth camera installed around the robot arm or at a fixed position, and uses the detected waypoint information as input to quantify the attraction steering force and the regression steering force; The verification module dynamically updates the DMP for real-time adjustment, and based on the Lyapunov stability theory, proves the stability of the improved DMP algorithm to ensure that the motion trajectory of the robot in a dynamic environment converges to the target point; finally, experiments are conducted to verify the ability of the robot to cross dynamic waypoints.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium for storing computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images