Planning for Proactive Assistance in Environments with Partial Observability

TL;DR

This paper develops a method for AI agents to proactively assist humans in shared environments with partial observability, ensuring the human recognizes the assistance's benefits and overall cost reduction.

Contribution

It introduces a principled approach for synthesizing proactive AI behavior that accounts for human awareness and partial observability, validated through empirical studies.

Findings

Proactive assistance reduces human task costs.

Humans recognize AI assistance benefits.

Approach improves task efficiency in shared environments.

Abstract

This paper addresses the problem of synthesizing the behavior of an AI agent that provides proactive task assistance to a human in settings like factory floors where they may coexist in a common environment. Unlike in the case of requested assistance, the human may not be expecting proactive assistance and hence it is crucial for the agent to ensure that the human is aware of how the assistance affects her task. This becomes harder when there is a possibility that the human may neither have full knowledge of the AI agent's capabilities nor have full observability of its activities. Therefore, our \textit{proactive assistant} is guided by the following three principles: \textbf{(1)} its activity decreases the human's cost towards her goal; \textbf{(2)} the human is able to recognize the potential reduction in her cost; \textbf{(3)} its activity optimizes the human's overall cost (time/resources) of achieving her goal. Through empirical evaluation and user studies, we demonstrate the usefulness of our approach.