Reactive motion generation on learned Riemannian manifolds
The International Journal of Robotics Research · 2023-09 · 42 (10) · 729-754
DOI: 10.1177/02783649231193046 ↗Kurz gefasst
Fachartikel in der Zeitschrift The International Journal of Robotics Research, online erschienen am 28.08.2023. Verfasst von Hadi Beik-Mohammadi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: villum fonden, H2020 European Research Council, Center for Basic Machine Learning Research in Life Sciences.
Abstract (Originalsprache)
In recent decades, advancements in motion learning have enabled robots to acquire new skills and adapt to unseen conditions in both structured and unstructured environments. In practice, motion learning methods capture relevant patterns and adjust them to new conditions such as dynamic obstacle avoidance or variable targets. In this paper, we investigate the robot motion learning paradigm from a Riemannian-manifold perspective. We argue that Riemannian manifolds may be learned via human demonstrations in which geodesics are natural motion skills. The geodesics are generated using a learned Riemannian metric produced by our novel variational autoencoder (VAE), which is intended to recover full-pose end-effector states and joint-space configurations. In addition, we propose a technique for facilitating on-the-fly end-effector/multiple-limb obstacle avoidance by reshaping the learned manifold using an obstacle-aware ambient metric. The motion generated using these geodesics may naturally result in multiple-solution tasks that have not been explicitly demonstrated previously. We extensively tested our approach in task-space and joint-space scenarios using a 7-DoF robotic manipulator. We demonstrate that our method is capable of learning and generating motion skills based on complicated motion patterns demonstrated by a human operator. Additionally, we assess several obstacle-avoidance strategies and generate trajectories in multiple-mode settings.
Förderung
- villum fonden
- H2020 European Research Council
- Center for Basic Machine Learning Research in Life Sciences
Zitieren
APA
Beik-Mohammadi, H., Hauberg, S., Arvanitidis, G., Neumann, G., & Rozo, L. (2023). Reactive motion generation on learned Riemannian manifolds. The International Journal of Robotics Research, 42(10), 729-754. https://doi.org/10.1177/02783649231193046
Vancouver
Beik-Mohammadi H, Hauberg S, Arvanitidis G, Neumann G, Rozo L. Reactive motion generation on learned Riemannian manifolds. The International Journal of Robotics Research. 2023;42(10):729-754. doi:10.1177/02783649231193046
BibTeX
@article{BeikMohammadi2023,
author = {Beik-Mohammadi, Hadi and Hauberg, Søren and Arvanitidis, Georgios and Neumann, Gerhard and Rozo, Leonel},
title = {Reactive motion generation on learned Riemannian manifolds},
journal = {The International Journal of Robotics Research},
year = {2023},
volume = {42},
number = {10},
pages = {729--754},
doi = {10.1177/02783649231193046}
}
EUVIMED