A modular reinforcement-based neural controller for a three-link manipulator

• Published in: Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Innovative Robotics for Real-World Applications. IROS '97 Vol. 2; pp. 785 - 792 vol.2
• Main Authors: Martin, P., Millan, J.D.R.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 1997
• Subjects: Artificial neural networks; Computer science; Learning; Manipulators; Motion control; Neural networks; Orbital robotics; Robot kinematics; Robot sensing systems; Robotics and automation
• ISBN: 9780780341197; 0780341198
• DOI: 10.1109/IROS.1997.655100

This paper presents a modular neural controller that learns goal-oriented obstacle-avoiding motion strategies for a sensor-based three-link planar robot arm. It acquires these strategies through reinforcement learning from local sensory data. The controller has two reinforcement-based modules: a module for negotiating obstacles and a module for moving to the goal. Both modules generate actions that are interpreted with regard to a goal vector in the robot joint space. A differential inverse kinematics (DIV) module is used to obtain such a goal vector. The DIV module is based on the inversion of a neural network that has been previously trained to approximate the manipulator forward kinematics in polar coordinates. The controller achieves a satisfactory performance quite rapidly and shows good generalization capabilities in the face of new environments.