Value of Assistance for Mobile Agents

TL;DR

This paper introduces a principled method called Value of Assistance (VOA) to quantify the expected benefit of providing help to mobile robots, optimizing assistance decisions to reduce localization uncertainty and improve task performance.

Contribution

It proposes a novel VOA measure based on Gaussian process uncertainty modeling, enabling informed assistance decisions in multi-robot systems.

Findings

VOA accurately predicts cost reduction from assistance in simulations.

VOA effectively guides assistance decisions in real-world robotic experiments.

The method provides a principled framework for assistance allocation in uncertain environments.

Abstract

Mobile robotic agents often suffer from localization uncertainty which grows with time and with the agents' movement. This can hinder their ability to accomplish their task. In some settings, it may be possible to perform assistive actions that reduce uncertainty about a robot's location. For example, in a collaborative multi-robot system, a wheeled robot can request assistance from a drone that can fly to its estimated location and reveal its exact location on the map or accompany it to its intended location. Since assistance may be costly and limited, and may be requested by different members of a team, there is a need for principled ways to support the decision of which assistance to provide to an agent and when, as well as to decide which agent to help within a team. For this purpose, we propose Value of Assistance (VOA) to represent the expected cost reduction that assistance will yield at a given point of execution. We offer ways to compute VOA based on estimations of the robot's future uncertainty, modeled as a Gaussian process. We specify conditions under which our VOA measures are valid and empirically demonstrate the ability of our measures to predict the agent's average cost reduction when receiving assistance in both simulated and real-world robotic settings.