Guided Exploration of Human Intentions for Human-Robot Interaction

TL;DR

This paper presents a probabilistic framework enabling robots to actively infer human intentions through behavior modeling and learning from expert demonstrations, improving interaction efficiency and safety in autonomous driving.

Contribution

It introduces a novel probabilistic model that combines intention inference, active exploration, and learning from demonstrations for better human-robot interaction.

Findings

Improved efficiency in intention inference during simulated driving scenarios.

Enhanced safety and interaction performance through active exploration.

Effective learning from human demonstrations to refine behavior models.

Abstract

Robot understanding of human intentions is essential for fluid human-robot interaction. Intentions, however, cannot be directly observed and must be inferred from behaviors. We learn a model of adaptive human behavior conditioned on the intention as a latent variable. We then embed the human behavior model into a principled probabilistic decision model, which enables the robot to (i) explore actively in order to infer human intentions and (ii) choose actions that maximize its performance. Furthermore, the robot learns from the demonstrated actions of human experts to further improve exploration. Preliminary experiments in simulation indicate that our approach, when applied to autonomous driving, improves the efficiency and safety of driving in common interactive driving scenarios.