Logic Learning From Demonstrations for Multi-Step Manipulation Tasks in Dynamic Environments
IEEE Robotics and Automation Letters · 2024-08 · 9 (8) · 7214-7221
DOI: 10.1109/lra.2024.3418276 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Robotics and Automation Letters, 2024-08. Verfasst von Yan Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: State Secretariat for Education, Research and Innovation in Switzerland for participation in the European Commission's Horizon Europe Program, INTELLIMAN Project.
Abstract (Originalsprache)
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.
Förderung
- State Secretariat for Education
- Research and Innovation in Switzerland for participation in the European Commission's Horizon Europe Program
- INTELLIMAN Project
- HORIZON-CL4-Digital-Emerging
- SESTOSENSO Project
- China Scholarship Council
- SWITCH Project
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
Zitieren
APA
Zhang, Y., Xue, T., Razmjoo, A., & Calinon, S. (2024). Logic Learning From Demonstrations for Multi-Step Manipulation Tasks in Dynamic Environments. IEEE Robotics and Automation Letters, 9(8), 7214-7221. https://doi.org/10.1109/lra.2024.3418276
Vancouver
Zhang Y, Xue T, Razmjoo A, Calinon S. Logic Learning From Demonstrations for Multi-Step Manipulation Tasks in Dynamic Environments. IEEE Robotics and Automation Letters. 2024;9(8):7214-7221. doi:10.1109/lra.2024.3418276
BibTeX
@article{Zhang2024,
author = {Zhang, Yan and Xue, Teng and Razmjoo, Amirreza and Calinon, Sylvain},
title = {Logic Learning From Demonstrations for Multi-Step Manipulation Tasks in Dynamic Environments},
journal = {IEEE Robotics and Automation Letters},
year = {2024},
volume = {9},
number = {8},
pages = {7214--7221},
doi = {10.1109/lra.2024.3418276}
}
EUVIMED