Human-Centric Active Perception for Autonomous Observation

TL;DR

This paper introduces a novel semi-Markov decision process framework for autonomous robots to actively observe humans, optimizing observation rewards while balancing costs, validated in a space station simulation.

Contribution

It formulates the autonomous human observation problem as a semi-MDP and compares multi-objective optimization methods for effective robot planning.

Findings

Semi-MDP formulation effectively models active human observation.

Both scalarization and constrained MDP methods are viable solutions.

Validated approach in NASA Astrobee robot simulation.

Abstract

As robot autonomy improves, robots are increasingly being considered in the role of autonomous observation systems -- free-flying cameras capable of actively tracking human activity within some predefined area of interest. In this work, we formulate the autonomous observation problem through multi-objective optimization, presenting a novel Semi-MDP formulation of the autonomous human observation problem that maximizes observation rewards while accounting for both human- and robot-centric costs. We demonstrate that the problem can be solved with both scalarization-based Multi-Objective MDP methods and Constrained MDP methods, and discuss the relative benefits of each approach. We validate our work on activity tracking using a NASA Astrobee robot operating within a simulated International Space Station environment.