Acquisition of synergy for low-dimensional control of multi-fingered hands by reinforcement learning

Abstract

We propose a reinforcement learning platform to learn to perform various tasks with a robotic hand to acquire a synergy. The model of deep reinforcement learning is trained to grasp an object with a multi-fingered hand. The synergy space is calculated by principal component analysis of hand postures when the task is successfully executed. The reward system is designed to minimize the distance of orthogonal projection between the posture and the synergy space, and the synergy space is acquired simultaneously with reinforcement learning.