Learning and Leveraging Features in Flow-Like Environments to Improve Situational Awareness

TL;DR

This paper introduces an online environmental feature generator based on coherent sets to enhance robot decision-making in flow-like environments, improving situational awareness for tasks like pedestrian monitoring and water navigation.

Contribution

It presents a novel online method for generating environmental features, specifically coherent sets, to improve robot reasoning and behavior in flow-like scenarios.

Findings

Online methods outperform offline approaches.

Coherent sets provide valuable environmental context.

Enhanced robot behavior in pedestrian and water navigation tasks.

Abstract

This paper studies how global dynamics and knowledge of high-level features can inform decision-making for robots in flow-like environments. Specifically, we investigate how coherent sets, an environmental feature found in these environments, inform robot awareness within these scenarios. The proposed approach is an online environmental feature generator which can be used for robot reasoning. We compute coherent sets online with techniques from machine learning and design frameworks for robot behavior that leverage coherent set features. We demonstrate the effectiveness of online methods over offline methods. Notably, we apply these online methods for robot monitoring of pedestrian behaviors and robot navigation through water. Environmental features such as coherent sets provide rich context to robots for smarter, more efficient behavior.