Safe and Stable Neural Network Dynamical Systems for Robot Motion Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Binny, Allen Emmanuel, Anand, Mahathi, Kussaba, Hugo T. M., Chen, Lingyun, Agrawal, Shreenabh, Abu-Dakka, Fares J., Swikir, Abdalla
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912868004265984
author Binny, Allen Emmanuel
Anand, Mahathi
Kussaba, Hugo T. M.
Chen, Lingyun
Agrawal, Shreenabh
Abu-Dakka, Fares J.
Swikir, Abdalla
author_facet Binny, Allen Emmanuel
Anand, Mahathi
Kussaba, Hugo T. M.
Chen, Lingyun
Agrawal, Shreenabh
Abu-Dakka, Fares J.
Swikir, Abdalla
contents Learning safe and stable robot motions from demonstrations remains a challenge, especially in complex, nonlinear tasks involving dynamic, obstacle-rich environments. In this paper, we propose Safe and Stable Neural Network Dynamical Systems S$^2$-NNDS, a learning-from-demonstration framework that simultaneously learns expressive neural dynamical systems alongside neural Lyapunov stability and barrier safety certificates. Unlike traditional approaches with restrictive polynomial parameterizations, S$^2$-NNDS leverages neural networks to capture complex robot motions, providing probabilistic guarantees through split conformal prediction in learned certificates. Experimental results in various 2D and 3D datasets -- including LASA handwriting and demonstrations recorded kinesthetically from the Franka Emika Panda robot -- validate the effectiveness of S$^2$-NNDS in learning robust, safe, and stable motions from potentially unsafe demonstrations. The source code, supplementary material and experiment videos can be accessed via https://github.com/allemmbinn/S2NNDS
format Preprint
id arxiv_https___arxiv_org_abs_2511_20593
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Safe and Stable Neural Network Dynamical Systems for Robot Motion Planning
Binny, Allen Emmanuel
Anand, Mahathi
Kussaba, Hugo T. M.
Chen, Lingyun
Agrawal, Shreenabh
Abu-Dakka, Fares J.
Swikir, Abdalla
Robotics
Systems and Control
Learning safe and stable robot motions from demonstrations remains a challenge, especially in complex, nonlinear tasks involving dynamic, obstacle-rich environments. In this paper, we propose Safe and Stable Neural Network Dynamical Systems S$^2$-NNDS, a learning-from-demonstration framework that simultaneously learns expressive neural dynamical systems alongside neural Lyapunov stability and barrier safety certificates. Unlike traditional approaches with restrictive polynomial parameterizations, S$^2$-NNDS leverages neural networks to capture complex robot motions, providing probabilistic guarantees through split conformal prediction in learned certificates. Experimental results in various 2D and 3D datasets -- including LASA handwriting and demonstrations recorded kinesthetically from the Franka Emika Panda robot -- validate the effectiveness of S$^2$-NNDS in learning robust, safe, and stable motions from potentially unsafe demonstrations. The source code, supplementary material and experiment videos can be accessed via https://github.com/allemmbinn/S2NNDS
title Safe and Stable Neural Network Dynamical Systems for Robot Motion Planning
topic Robotics
Systems and Control
url https://arxiv.org/abs/2511.20593