Uncertainty-Resilient Active Intention Recognition for Robotic Assistants

TL;DR

This paper introduces a framework for robotic assistants that robustly recognizes human intentions despite uncertainties and sensor noise, enhancing autonomous cooperation through a POMDP-based approach tested on real robots.

Contribution

It presents a novel intention recognition framework that incorporates uncertainty reasoning and sensor noise resilience using a POMDP-based method for robotic assistants.

Findings

Successfully tested on a physical robot

Demonstrated resilience to sensor noise

Improved intention recognition accuracy

Abstract

Purposeful behavior in robotic assistants requires the integration of multiple components and technological advances. Often, the problem is reduced to recognizing explicit prompts, which limits autonomy, or is oversimplified through assumptions such as near-perfect information. We argue that a critical gap remains unaddressed -- specifically, the challenge of reasoning about the uncertain outcomes and perception errors inherent to human intention recognition. In response, we present a framework designed to be resilient to uncertainty and sensor noise, integrating real-time sensor data with a combination of planners. Centered around an intention-recognition POMDP, our approach addresses cooperative planning and acting under uncertainty. Our integrated framework has been successfully tested on a physical robot with promising results.