Reinforcement learning of collision-free motions for a robot arm with a sensing skin
A neural reactive controller is described that learns goal-oriented obstacle-avoiding motion strategies for such a manipulator in unknown 3-dimensional environments. The controller is made up of two main modules: a reinforcement-based action generator (AG) and a goal vector generator (GG). The AG uses local sensory data and position information to determine an appropriate deviation from the goal vector given by the GG. The task of collision-free reaching can be decomposed into two sequential subtasks: negotiate obstacles (NO subtask) and move to goal position (MG subtask). When the robot arm is not near the goal position and detects on obstacle in its way to the goal, the best strategy is to focus on negotiating the obstacle-moving along an efficient trajectory is not so important.
Bibliographic Reference: Paper presented: Eighth International Conference on Artificial Neural Networks, Skövde (SE), September 1-4, 1998
Availability: Available from (1) as Paper EN 41539 ORA
Record Number: 199810958 / Last updated on: 1998-09-01
Original language: en
Available languages: en