Show, Attend and Interact: Perceivable Human-Robot Social Interaction through Neural Attention Q-Network
This addresses the challenge of safe and natural human-robot social interaction, though it appears incremental as it builds on existing attention and Q-network methods.
The paper tackled the problem of enabling robots to exhibit perceivable and socially acceptable responses to complex human behaviors by introducing the Multimodal Deep Attention Recurrent Q-Network (MDARQN), which learned through 14 days of real-world interaction and end-to-end reinforcement learning, resulting in the robot successfully responding to human behaviors.
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.