The Application of Connectionist Structures to LearningImpedance Control in Robotic Contact Tasks

Authors:
Dusko Katić;Miomir Vukobratović
Affiliations:
Robotics Department, Mihailo Pupin Institute, 11000 Belgrade,Yugoslavia;Robotics Department, Mihailo Pupin Institute, 11000 Belgrade,Yugoslavia
Venue:
Applied Intelligence
Year:
1997

Citing 4
Cited 0

Historical perspective and state of the art in robot force control

International Journal of Robotics Research
Robust force control of a robot manipulator

International Journal of Robotics Research
Impedance Control as a Particular Case of the Unified Approach to the Control of Robots Interacting with a Dynamic Known Environment

Journal of Intelligent and Robotic Systems
Adaptation to Environment Stiffness in the Control of Manipulators

The First International Symposium on Experimental Robotics I

Quantified Score

Hi-index	0.00

Visualization

Abstract

The goal of this paper is to consider the synthesis of learningimpedance control using recurrent connectionist structures foron-line learning of robot dynamic uncertainties in the case of robotcontact tasks. The connectionist structures are integrated innon-learning impedance control laws that are intended to improve thetransient dynamic response immediately after the contact. Therecurrent neural network as a part of hybrid learning controlalgorithms uses fast learning rules and available sensor informationin order to improve the robotic performance progressively for aminimum possible number of learning epochs. Some simulation resultsof deburring process with the MANUTEC r3 robot are presented here inorder to verify the effectiveness of the proposed control learningalgorithms.