Robot gains social intelligence through multimodal deep reinforcement learning

Ahmed Hussain Qureshi, Yutaka Nakamura, Yuichiro Yoshikawa, Hiroshi Ishiguro
2016 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids)  
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 behavior from the high
more » ... rom 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.
doi:10.1109/humanoids.2016.7803357 dblp:conf/humanoids/QureshiNYI16 fatcat:bpg44o76abczborr5ifqeirakq