マルチモーダル深層強化学習でロボットが社会的知能を獲得
Robot gains Social Intelligence through Multimodal Deep Reinforcement Learning
マルチモーダル深層Qネットワーク(MDQN)を用い、人との試行錯誤的な相互作用からロボットが人間らしい社会的スキルを学習できることを示した研究。
著者: Ahmed Hussain Qureshi, Yutaka Nakamura, Yuichiro Yoshikawa, Hiroshi Ishiguro
分類: cs.RO, cs.AI, cs.CV, stat.ML
原文アブストラクト
For robots to coexist with humans in a social world like ours, it is crucial that they possess human-like social interaction skills. Programming a robot to possess such skills is a challenging task. In this paper, we propose a Multimodal Deep Q-Network (MDQN) to enable a robot to learn human-like interaction skills through a trial and error method. This paper aims to develop a robot that gathers data during its interaction with a human and learns human interaction behaviour from the high-dimensional sensory information using end-to-end reinforcement learning. This paper demonstrates that the robot was able to learn basic interaction skills successfully, after 14 days of interacting with people.
