Reactive Temporal Logic Planning for Safe Human-Robot Interaction

Abstract

Human-robot interaction plays a critical role in scientific experiments by ensuring efficient and reliable execution of experimental tasks. To achieve successful task completion, robots must adapt in real time to unexpected task variations, external disturbances, and safety constraints. In this work, we propose a reactive task and motion planning framework designed to address these challenges. By formulating interaction tasks using Linear Temporal Logic (LTL), our approach introduces Planning Decision Tree and Augmented Planning Decision Tree approach to dynamically adjust task sequences in response to environmental changes. At the execution layer, we employ a Model Predictive Path Integral controller, which ensures both efficient and safe control. Additionally, the planning interface effectively coordinates the planning and execution layers, ensuring strict adherence to experimental task specifications. The effectiveness of the proposed reactive planning framework is demonstrated through physical experiments using a 7-DoFs robot. Project website: https://sites.google.com/view/rtlp-iros/