RAMBO: RL-Augmented Model-Based Whole-Body Control for Loco-Manipulation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cheng, Jin, Kang, Dongho, Fadini, Gabriele, Shi, Guanya, Coros, Stelian
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916882901106688
author Cheng, Jin
Kang, Dongho
Fadini, Gabriele
Shi, Guanya
Coros, Stelian
author_facet Cheng, Jin
Kang, Dongho
Fadini, Gabriele
Shi, Guanya
Coros, Stelian
contents Loco-manipulation, physical interaction of various objects that is concurrently coordinated with locomotion, remains a major challenge for legged robots due to the need for both precise end-effector control and robustness to unmodeled dynamics. While model-based controllers provide precise planning via online optimization, they are limited by model inaccuracies. In contrast, learning-based methods offer robustness, but they struggle with precise modulation of interaction forces. We introduce RAMBO, a hybrid framework that integrates model-based whole-body control within a feedback policy trained with reinforcement learning. The model-based module generates feedforward torques by solving a quadratic program, while the policy provides feedback corrective terms to enhance robustness. We validate our framework on a quadruped robot across a diverse set of real-world loco-manipulation tasks, such as pushing a shopping cart, balancing a plate, and holding soft objects, in both quadrupedal and bipedal walking. Our experiments demonstrate that RAMBO enables precise manipulation capabilities while achieving robust and dynamic locomotion.
format Preprint
id arxiv_https___arxiv_org_abs_2504_06662
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RAMBO: RL-Augmented Model-Based Whole-Body Control for Loco-Manipulation
Cheng, Jin
Kang, Dongho
Fadini, Gabriele
Shi, Guanya
Coros, Stelian
Robotics
Loco-manipulation, physical interaction of various objects that is concurrently coordinated with locomotion, remains a major challenge for legged robots due to the need for both precise end-effector control and robustness to unmodeled dynamics. While model-based controllers provide precise planning via online optimization, they are limited by model inaccuracies. In contrast, learning-based methods offer robustness, but they struggle with precise modulation of interaction forces. We introduce RAMBO, a hybrid framework that integrates model-based whole-body control within a feedback policy trained with reinforcement learning. The model-based module generates feedforward torques by solving a quadratic program, while the policy provides feedback corrective terms to enhance robustness. We validate our framework on a quadruped robot across a diverse set of real-world loco-manipulation tasks, such as pushing a shopping cart, balancing a plate, and holding soft objects, in both quadrupedal and bipedal walking. Our experiments demonstrate that RAMBO enables precise manipulation capabilities while achieving robust and dynamic locomotion.
title RAMBO: RL-Augmented Model-Based Whole-Body Control for Loco-Manipulation
topic Robotics
url https://arxiv.org/abs/2504.06662