A Weighted Gradient Projection Method for Inverse Kinematics of Redundant Manipulators Considering Multiple Performance Criteria

doi:10.5545/sv-jme.2017.5182

Cited by 5 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The gradient projection method projects the optimization function of the self-motion gradient to the null space of the Jacobian matrix, which can adjust the configuration to avoid obstacles without affecting the end-effector motion. The optimization function usually consists of distance in different forms, such as distance from the key point to obstacles [ 8 ] and repulsive potential field generated by obstacles [ 9 ]. However, the GPM may lead to joint singularity or joint position limits while avoiding obstacles; thus the manipulator will fail to track the desired trajectory.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning-Based Reactive Obstacle Avoidance Method for Redundant Manipulators

Shen

Jia

Huang

et al. 2022

Entropy

View full text Add to dashboard Cite

Redundant manipulators are widely used in fields such as human-robot collaboration due to their good flexibility. To ensure efficiency and safety, the manipulator is required to avoid obstacles while tracking a desired trajectory in many tasks. Conventional methods for obstacle avoidance of redundant manipulators may encounter joint singularity or exceed joint position limits while tracking the desired trajectory. By integrating deep reinforcement learning into the gradient projection method, a reactive obstacle avoidance method for redundant manipulators is proposed. We establish a general DRL framework for obstacle avoidance, and then a reinforcement learning agent is applied to learn motion in the null space of the redundant manipulator Jacobian matrix. The reward function of reinforcement learning is redesigned to handle multiple constraints automatically. Specifically, the manipulability index is introduced into the reward function, and thus the manipulator can maintain high manipulability to avoid joint singularity while executing tasks. To show the effectiveness of the proposed method, the simulation of 4 degrees of planar manipulator freedom is given. Compared with the gradient projection method, the proposed method outperforms in a success rate of obstacles avoidance, average manipulability, and time efficiency.

show abstract

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning-Based Reactive Obstacle Avoidance Method for Redundant Manipulators

Shen

Jia

Huang

et al. 2022

Entropy

View full text Add to dashboard Cite

show abstract

“…In order to make more reasonable and effective use of the existing working space and ensure the safe and reliable operation of the parallel power head, the method of trajectory planning and space limitation is often adopted [19] and [20]. Khoukhi et al [21] proposed a multi-objective dynamic trajectory planning method for the parallel mechanism under the constraints of task, workspace, and mechanism with the help of the discrete augmented Lagrangian technique.…”

Section: Introductionmentioning

confidence: 99%

Limit-protection Method for Workspace of a Parallel Power Head

Ni¹,

Lu²,

Song³

et al. 2022

sv-jme

View full text Add to dashboard Cite

The position and pose of the end of 1T2R mechanism with one translational motion and two rotational degrees of freedom in the operation space is the nonlinear mapping of the servo motor action in the joint space, and the postures and states of the end of the mechanism can only be obtained through complex modeling calculation. Because of this, the key problem to be solved urgently is to realize the real-time and accurate limit protection function of this kind of structure machine tool, and to reduce the process and calculation amount of the position and pose judgment of the end of the mechanism. In this paper, a simplified algorithm for position and attitude judgment is proposed by analyzing the workspace of 1T2R mechanism. The position and attitude judgment of the terminal moving platform of the mechanism under any configuration can be realized only by summing up the length of three branch chains of the mechanism and calculating the difference. Further, the limit protection method of parallel power head based on this algorithm can be implemented based on the software and hardware conditions of the existing control system. It is easy to implement and has a small amount of calculation, which can further improve the safety of the operation of such structure machine tools.

show abstract

“…It is hoped that the improvement of the driving method will make the soft manipulators move more quickly and more powerfully. Jun et al [16] proposed a weighted gradient projection method to resolve inverse kinematics problems of redundant manipulators with multiple performance criteria. Brown et al [17] developed a "coffee bag"-shaped blocking-based software manipulator that achieves the capture of objects of different shapes by blocking between different parts.…”

Section: Introductionmentioning

confidence: 99%

Design and Performance Analysis of Airbag-Soft-Manipulator According to Characteristic Parameters

Liu

Wang

et al. 2019

SV-JME

View full text Add to dashboard Cite

Manipulators are increasingly used in mechanical manufacturing due to the needs of industrial automation. The shortcomings of traditional manipulators, such as those in relation to their flexibility, interactivity, and safety, lead to certain limitations in their application for variable shapes and fragile objects. Given the above shortcomings of traditional manipulators, this research analysed a friction-enhanced multi-airbag soft manipulator and its performance. Analysis results of characteristic parameters show that the structure of the airbag soft manipulator is optimized, and the structural design and manufacture of the soft manipulator are completed. Deformation of the manipulator base material is described by the Neo-Hooke strain energy function, and the strain energy function coefficient is derived by obtaining the characteristic parameters of the material through tensile experiments. Finite element analysis of the manipulator is performed according to the determined strain energy function. The influence of the characteristic parameters on the mechanical bending of the manipulator is studied. Theoretical analysis proves the validity of the finite element analysis. The structural parameters of the manipulator are finally determined according to the simulation analysis results. The control system is designed according to the driving method and working mode of the soft manipulator to perform the soft manipulator grasp experiment. The manipulator can lift a weight of 300 g, thereby indicating that the soft manipulator designed in this paper has a good application effect and prospects.

show abstract

A Weighted Gradient Projection Method for Inverse Kinematics of Redundant Manipulators Considering Multiple Performance Criteria

Cited by 5 publications

References 17 publications

Reinforcement Learning-Based Reactive Obstacle Avoidance Method for Redundant Manipulators

Reinforcement Learning-Based Reactive Obstacle Avoidance Method for Redundant Manipulators

Limit-protection Method for Workspace of a Parallel Power Head

Design and Performance Analysis of Airbag-Soft-Manipulator According to Characteristic Parameters

Contact Info

Product

Resources

About