Neural Configuration-Space Barriers for Manipulation Planning and Control

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Long, Kehan, Lee, Ki Myung Brian, Raicevic, Nikola, Attasseri, Niyas, Leok, Melvin, Atanasov, Nikolay
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913153496907776
author Long, Kehan
Lee, Ki Myung Brian
Raicevic, Nikola
Attasseri, Niyas
Leok, Melvin
Atanasov, Nikolay
author_facet Long, Kehan
Lee, Ki Myung Brian
Raicevic, Nikola
Attasseri, Niyas
Leok, Melvin
Atanasov, Nikolay
contents Planning and control for high-dimensional robot manipulators in cluttered dynamic environments require computational efficiency and robust safety guarantees. Inspired by recent advances in learning configuration-space distance functions (CDFs) as representations of robot bodies, we propose a unified approach for motion planning and control that formulates safety constraints as CDF barriers. A CDF barrier approximates the local free configuration space, substantially reducing the number of collision-checking operations during motion planning. However, learning a CDF barrier with a neural network and relying on online sensor observations introduces uncertainties that must be considered during control synthesis. To address this, we develop a distributionally robust CDF barrier formulation for control that accounts for modeling errors and sensor noise without assuming a known underlying distribution. Simulations and hardware experiments on a UFactory xArm6 manipulator show that our neural CDF barrier formulation enables efficient planning and robust safe control in cluttered and dynamic environments, relying only on onboard point-cloud observations.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04929
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Configuration-Space Barriers for Manipulation Planning and Control
Long, Kehan
Lee, Ki Myung Brian
Raicevic, Nikola
Attasseri, Niyas
Leok, Melvin
Atanasov, Nikolay
Robotics
Machine Learning
Systems and Control
Planning and control for high-dimensional robot manipulators in cluttered dynamic environments require computational efficiency and robust safety guarantees. Inspired by recent advances in learning configuration-space distance functions (CDFs) as representations of robot bodies, we propose a unified approach for motion planning and control that formulates safety constraints as CDF barriers. A CDF barrier approximates the local free configuration space, substantially reducing the number of collision-checking operations during motion planning. However, learning a CDF barrier with a neural network and relying on online sensor observations introduces uncertainties that must be considered during control synthesis. To address this, we develop a distributionally robust CDF barrier formulation for control that accounts for modeling errors and sensor noise without assuming a known underlying distribution. Simulations and hardware experiments on a UFactory xArm6 manipulator show that our neural CDF barrier formulation enables efficient planning and robust safe control in cluttered and dynamic environments, relying only on onboard point-cloud observations.
title Neural Configuration-Space Barriers for Manipulation Planning and Control
topic Robotics
Machine Learning
Systems and Control
url https://arxiv.org/abs/2503.04929