Learning Human-Aware Robot Policies for Adaptive Assistance

TL;DR

This paper introduces a framework enabling robots to infer human intentions and preferences through interaction, leading to more personalized, adaptive assistance that improves task success, efficiency, and user satisfaction in real-world scenarios.

Contribution

The paper presents a novel framework with modules for predicting human behavior and inferring utilities, addressing the challenge of individual preferences in human-robot interaction.

Findings

Enhanced task success and efficiency

Significant improvement in user satisfaction

Framework adaptable to various robot types and tasks

Abstract

Developing robots that can assist humans efficiently, safely, and adaptively is crucial for real-world applications such as healthcare. While previous work often assumes a centralized system for co-optimizing human-robot interactions, we argue that real-world scenarios are much more complicated, as humans have individual preferences regarding how tasks are performed. Robots typically lack direct access to these implicit preferences. However, to provide effective assistance, robots must still be able to recognize and adapt to the individual needs and preferences of different users. To address these challenges, we propose a novel framework in which robots infer human intentions and reason about human utilities through interaction. Our approach features two critical modules: the anticipation module is a motion predictor that captures the spatial-temporal relationship between the robot agent and user agent, which contributes to predicting human behavior; the utility module infers the underlying human utility functions through progressive task demonstration sampling. Extensive experiments across various robot types and assistive tasks demonstrate that the proposed framework not only enhances task success and efficiency but also significantly improves user satisfaction, paving the way for more personalized and adaptive assistive robotic systems. Code and demos are available at https://asonin.github.io/Human-Aware-Assistance/.