Show, Attend and Interact: Perceivable Human-Robot Social Interaction through Neural Attention Q-Network

Abstract

For a safe, natural and effective human-robot social interaction, it is essential to develop a system that allows a robot to demonstrate the perceivable responsive behaviors to complex human behaviors. We introduce the Multimodal Deep Attention Recurrent Q-Network using which the robot exhibits human-like social interaction skills after 14 days of interacting with people in an uncontrolled real world. Each and every day during the 14 days, the system gathered robot interaction experiences with people through a hit-and-trial method and then trained the MDARQN on these experiences using end-to-end reinforcement learning approach. The results of interaction based learning indicate that the robot has learned to respond to complex human behaviors in a perceivable and socially acceptable manner.

arXiv comment7 pages, 5 figures, accepted by IEEE-RAS ICRA'17

References in corpus (4)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Recurrent Models of Visual Attention
• Deep Attention Recurrent Q-Network

Cited by in corpus (5)

• Intrinsically motivated reinforcement learning for human-robot interaction in the real-world
• Neural Network Based Reinforcement Learning for Audio-Visual Gaze Control in Human-Robot Interaction
• A Data-Efficient Deep Learning Approach for Deployable Multimodal Social Robots
• Composing Task-Agnostic Policies with Deep Reinforcement Learning
• Adversarial Imitation via Variational Inverse Reinforcement Learning