# Planning for Proactive Assistance in Environments with Partial Observability

arXiv: https://arxiv.org/abs/2105.00525 · HTML: https://mlsanity.com/paper/2105.00525/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 31 references that are in the map.
- First posted on arXiv 2 May 2021.

## Builds on (most cited first, 3 of 3)

- [A Unified Framework for Planning in Adversarial and Cooperative Environments](https://mlsanity.com/paper/1802.06137/) (2018)
- [Compiling Uncertainty Away in Conformant Planning Problems with Bounded Width](https://mlsanity.com/paper/1401.3468/) (2014)
- [Attention-Sensitive Alerting](https://mlsanity.com/paper/1301.6707/) (2013)

## Built on by (most cited first, 1 of 1)

- [Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?](https://mlsanity.com/paper/2401.05302/) (2024)

## Abstract (arXiv)

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 textitproactive assistant is guided by the following three principles: (1) its activity decreases the human's cost towards her goal; (2) the human is able to recognize the potential reduction in her cost; (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.