Impedance learning for robotic contact tasks using natural actor-critic algorithm

Authors:
Byungchan Kim;Jooyoung Park;Shinsuk Park;Sungchul Kang
Affiliations:
Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Seoul, Korea;Department of Control and Instrumentation Engineering, Korea University, Jochiwon, Korea;School of Mechanical Engineering, Korea University, Seoul, Korea;Center for Cognitive Robotics Research, Korea Institute of Science and Technology, Seoul, Korea
Venue:
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Year:
2010

Citing 18
Cited 2

The control of hand equilibrium trajectories in multi-joint arm movements

Biological Cybernetics
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Machine Learning
Natural gradient works efficiently in learning

Neural Computation
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Robot Analysis and Control

Robot Analysis and Control
Least-Squares Temporal Difference Learning

ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
On Actor-Critic Algorithms

SIAM Journal on Control and Optimization
Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)

Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)
Natural Actor-Critic

Neurocomputing
Efficient reinforcement learning using recursive least-squares methods

Journal of Artificial Intelligence Research
An RLS-based natural actor-critic algorithm for locomotion of a two-linked robot arm

CIS'05 Proceedings of the 2005 international conference on Computational Intelligence and Security - Volume Part I
Online learning of virtual impedance parameters in non-contact impedance control using neural networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Comparison of Adaptive Critic-Based and Classical Wide-Area Controllers for Power Systems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Adaptive Critic Learning Techniques for Engine Torque and Air–Fuel Ratio Control

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Direct Heuristic Dynamic Programming for Damping Oscillations in a Large Power System

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Improved Adaptive–Reinforcement Learning Control for Morphing Unmanned Air Vehicles

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Control of Nonaffine Nonlinear Discrete-Time Systems Using Reinforcement-Learning-Based Linearly Parameterized Neural Networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Enhanced human-machine interface in braking

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Adaptive impedance control for natural human-robot collaboration

Proceedings of the Workshop at SIGGRAPH Asia
Compliant skills acquisition and multi-optima policy search with EM-based reinforcement learning

Robotics and Autonomous Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Compared with their robotic counterparts, humans excel at various tasks by using their ability to adaptively modulate arm impedance parameters. This ability allows us to successfully perform contact tasks even in uncertain environments. This paper considers a learning strategy of motor skill for robotic contact tasks based on a human motor control theory and machine learning schemes. Our robot learning method employs impedance control based on the equilibrium point control theory and reinforcement learning to determine the impedance parameters for contact tasks. A recursive least-square filter-based episodic natural actor-critic algorithm is used to find the optimal impedance parameters. The effectiveness of the proposed method was tested through dynamic simulations of various contact tasks. The simulation results demonstrated that the proposed method optimizes the performance of the contact tasks in uncertain conditions of the environment.