Closed-loop Bayesian Semantic Data Fusion for Collaborative Human-Autonomy Target Search

TL;DR

This paper presents a novel hierarchical Gaussian mixture model approach for collaborative human-autonomy target search, integrating semantic natural language observations with sensor data using CPOMDP planning, validated in real indoor scenarios.

Contribution

It introduces a scalable hierarchical Gaussian mixture model for CPOMDPs that efficiently combines semantic and sensor data in continuous dynamic environments.

Findings

Effective integration of semantic and sensor data in target search

Validated approach with real human-robot team experiments

Improved target reacquisition and localization performance

Abstract

In search applications, autonomous unmanned vehicles must be able to efficiently reacquire and localize mobile targets that can remain out of view for long periods of time in large spaces. As such, all available information sources must be actively leveraged -- including imprecise but readily available semantic observations provided by humans. To achieve this, this work develops and validates a novel collaborative human-machine sensing solution for dynamic target search. Our approach uses continuous partially observable Markov decision process (CPOMDP) planning to generate vehicle trajectories that optimally exploit imperfect detection data from onboard sensors, as well as semantic natural language observations that can be specifically requested from human sensors. The key innovation is a scalable hierarchical Gaussian mixture model formulation for efficiently solving CPOMDPs with semantic observations in continuous dynamic state spaces. The approach is demonstrated and validated with a real human-robot team engaged in dynamic indoor target search and capture scenarios on a custom testbed.