The reviewed record of science sign in
Pith

arxiv: 2404.16138 · v2 · pith:63J6LWMA · submitted 2024-04-24 · cs.RO

Logic Learning from Demonstrations for Multi-step Manipulation Tasks in Dynamic Environments

Reviewed by Pithpith:63J6LWMAopen to challenge →

classification cs.RO
keywords dynamicmanipulationtasksdisturbancesenvironmentslong-horizonchallengeframework
0
0 comments X
read the original 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 Dynamic Movement Primitives (Logic-DMP), which combines Task and Motion Planning (TAMP) with an optimal control formulation of 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-DMP for handling task-level variants and disturbances in long-horizon manipulation tasks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.