Interpretable Run-Time Prediction and Planning in Co-Robotic Environments

TL;DR

This paper introduces an interpretable, decision-tree based approach enabling mobile robots to predict, explain, and plan corrective actions to avoid interfering with human paths, improving social compliance and adaptability in real-time.

Contribution

It presents a novel, interpretable decision-tree framework for real-time prediction, explanation, and planning of non-interfering robot behaviors in human environments.

Findings

Effective prediction of interference with humans in simulations and experiments.

Real-time learning improves the model's accuracy during operation.

Robots demonstrate smooth, socially compliant navigation behaviors.

Abstract

Mobile robots are traditionally developed to be reactive and avoid collisions with surrounding humans, often moving in unnatural ways without following social protocols, forcing people to behave very differently from human-human interaction rules. Humans, on the other hand, are seamlessly able to understand why they may interfere with surrounding humans and change their behavior based on their reasoning, resulting in smooth, intuitive avoiding behaviors. In this paper, we propose an approach for a mobile robot to avoid interfering with the desired paths of surrounding humans. We leverage a library of previously observed trajectories to design a decision-tree based interpretable monitor that: i) predicts whether the robot is interfering with surrounding humans, ii) explains what behaviors are causing either prediction, and iii) plans corrective behaviors if interference is predicted. We also propose a validation scheme to improve the predictive model at run-time. The proposed approach is validated with simulations and experiments involving an unmanned ground vehicle (UGV) performing go-to-goal operations in the presence of humans, demonstrating non-interfering behaviors and run-time learning.