Abstract

In this paper, a neural networks (NNs) enhanced telerobot control system is designed and tested on a Baxter robot. Guaranteed performance of the telerobot control system is achieved at both kinematic and dynamic levels. At kinematic level, automatic collision avoidance is achieved by the control design at the kinematic level exploiting the joint space redundancy, thus the human operator would be able to only concentrate on motion of robot's end-effector without concern on possible collision. A posture restoration scheme is also integrated based on a simulated parallel system to enable the manipulator restore back to the natural posture in the absence of obstacles. At dynamic level, adaptive control using radial basis function NNs is developed to compensate for the effect caused by the internal and external uncertainties, e.g., unknown payload. Both the steady state and the transient performance are guaranteed to satisfy a prescribed performance requirement. Comparative experiments have been performed to test the effectiveness and to demonstrate the guaranteed performance of the proposed methods.

Highlights

  • I N THE last few decades, the teleoperated robots, known as telerobots, have been widely applied for human unfriendly tasks such as handing radioactive material and searching in dangerous environment

  • Collision Avoiding Without loss of generality, in this paper we only focus on the cases of collision avoidance that could be achieved using kinematic redundancy mechanism, i.e., the joint motion in the null space of Jacobian Je

  • The radial basis function neural networks (NNs) (RBFNN) is used to compensate for the unknown dynamics, especially that caused by the unknown payload, to guarantee the steady state performance of the controller

Read more

Summary

INTRODUCTION

I N THE last few decades, the teleoperated robots, known as telerobots, have been widely applied for human unfriendly tasks such as handing radioactive material and searching in dangerous environment. To decrease the workload of the human operator, we consider to employ the shared control framework, and embed an automatic collision avoidance mechanism into the teleoperation system, to enable the telerobot safely interact with a dynamic environment. The unknown or varying payload makes it impossible to obtain an accurate dynamics model in advance To solve such problems, the approximation-based control methods have been developed and have been successfully applied on a wide range of practical systems, e.g., formation control [14], multiagent’s consensus control [15], and the robotic manipulator control [16]. The goal of design at the dynamic level is to ensure that the reference trajectory can be tracked satisfying a specified performance requirement in the presence uncertainties

System Components
Workspace Matching
Coordinate Transformation
Identification of Collision Points
Dimension Reduction Method
Restoring Control
Control Design at Kinematic Level
CONTROL STRATEGY AT DYNAMICS LEVEL
Radial Basis Function NN
Control Design at Dynamic Level
Test of Neural-Learning Performance
Test of Tracking Performance
Test of Restoration Function
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call