Assembly skill acquisition via reinforcement learning

Abstract

A neural network controller is proposed for the motion control of robot manipulators with force/torque feedback signals. This controller is trained with reinforcement learning algorithms and a model is extracted from the synaptic weights within the neural network. This model is continuously refined by the feedback signals to ensure its validity even in a stochastic and non‐stationary environment. With this model and the real‐time force/torque feedback data, the robot can acquire a fine skill for a particular assembly task for which it is trained.

Citation

Lau, H.Y.K. and Lee, I.S.K. (2001), "Assembly skill acquisition via reinforcement learning", Assembly Automation, Vol. 21 No. 2, pp. 136-142. https://doi.org/10.1108/01445150110388522