Whole-Body Safe Control of Robotic Systems with Koopman Neural Dynamics

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jung, Sebin, Abuduweili, Abulikemu, Li, Jiaxing, Liu, Changliu
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910058695098368
author Jung, Sebin
Abuduweili, Abulikemu
Li, Jiaxing
Liu, Changliu
author_facet Jung, Sebin
Abuduweili, Abulikemu
Li, Jiaxing
Liu, Changliu
contents Controlling robots with strongly nonlinear, high-dimensional dynamics remains challenging, as direct nonlinear optimization with safety constraints is often intractable in real time. The Koopman operator offers a way to represent nonlinear systems linearly in a lifted space, enabling the use of efficient linear control. We propose a data-driven framework that learns a Koopman embedding and operator from data, and integrates the resulting linear model with the Safe Set Algorithm (SSA). This allows the tracking and safety constraints to be solved in a single quadratic program (QP), ensuring feasibility and optimality without a separate safety filter. We validate the method on a Kinova Gen3 manipulator and a Go2 quadruped, showing accurate tracking and obstacle avoidance.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03740
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Whole-Body Safe Control of Robotic Systems with Koopman Neural Dynamics
Jung, Sebin
Abuduweili, Abulikemu
Li, Jiaxing
Liu, Changliu
Robotics
Controlling robots with strongly nonlinear, high-dimensional dynamics remains challenging, as direct nonlinear optimization with safety constraints is often intractable in real time. The Koopman operator offers a way to represent nonlinear systems linearly in a lifted space, enabling the use of efficient linear control. We propose a data-driven framework that learns a Koopman embedding and operator from data, and integrates the resulting linear model with the Safe Set Algorithm (SSA). This allows the tracking and safety constraints to be solved in a single quadratic program (QP), ensuring feasibility and optimality without a separate safety filter. We validate the method on a Kinova Gen3 manipulator and a Go2 quadruped, showing accurate tracking and obstacle avoidance.
title Whole-Body Safe Control of Robotic Systems with Koopman Neural Dynamics
topic Robotics
url https://arxiv.org/abs/2603.03740