TRUST AND INTENTION IN HUMAN-ROBOT INTERACTION: A POMDP FRAMEWORK

Abstract

Human-robot interaction (HRI) is rapidly gaining importance as robots enter our daily life, e.g., autonomous driving car, household robots, etc. To become an effective helper, the robot has to reason over human behaviors, and plan its own actions accordingly.

We propose several models for human-robot interaction, where we decompose human-robot interaction into two subproblems: (i) human behavior modeling, and (ii) robot decision making. When modeling human behaviors, we draw insights from previous works in psychology and social science, and identify trust and intention as the key mental states that help to understand human behaviors. Motivated by earlier works, we learn from data a model of adaptive human behaviors conditioned on trust or intention as a latent variable. The learned human behavior model is then embedded into a partially observable Markov decision process (POMDP) for robot decision making.

We validated our models on several human-robot interaction tasks. Experimental results showed that our robot was able to actively infer and influence human mental states, and leveraged that for improved robot efficiency and team effectiveness.