Logic Learning From Demonstrations for Multi-Step Manipulation Tasks in Dynamic Environments

Abstract

Learning from Demonstration (LfD) stands as an efficient framework for imparting human-like skills to robots. Nevertheless, designing an LfD framework capable of seamlessly imitating, generalizing, and reacting to disturbances for long-horizon manipulation tasks in dynamic environments remains a challenge. To tackle this challenge, we present Logic-LfD, which combines Task and Motion Planning (TAMP) with an optimal control formulation of Dynamic Movement Primitives (DMP), allowing us to incorporate motion-level via-point specifications and to handle task-level variations or disturbances in dynamic environments. We conduct a comparative analysis of our proposed approach against several baselines, evaluating its generalization ability and reactivity across three long-horizon manipulation tasks. Our experiment demonstrates the fast generalization and reactivity of Logic-LfD for handling task-level variants and disturbances in long-horizon manipulation tasks.