Learning Accurate Whole-body Throwing with High-frequency Residual Policy and Pullback Tube Acceleration

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ma, Yuntao, Liu, Yang, Qu, Kaixian, Hutter, Marco
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913909209825280
author Ma, Yuntao
Liu, Yang
Qu, Kaixian
Hutter, Marco
author_facet Ma, Yuntao
Liu, Yang
Qu, Kaixian
Hutter, Marco
contents Throwing is a fundamental skill that enables robots to manipulate objects in ways that extend beyond the reach of their arms. We present a control framework that combines learning and model-based control for prehensile whole-body throwing with legged mobile manipulators. Our framework consists of three components: a nominal tracking policy for the end-effector, a high-frequency residual policy to enhance tracking accuracy, and an optimization-based module to improve end-effector acceleration control. The proposed controller achieved the average of 0.28 m landing error when throwing at targets located 6 m away. Furthermore, in a comparative study with university students, the system achieved a velocity tracking error of 0.398 m/s and a success rate of 56.8%, hitting small targets randomly placed at distances of 3-5 m while throwing at a specified speed of 6 m/s. In contrast, humans have a success rate of only 15.2%. This work provides an early demonstration of prehensile throwing with quantified accuracy on hardware, contributing to progress in dynamic whole-body manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16986
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Accurate Whole-body Throwing with High-frequency Residual Policy and Pullback Tube Acceleration
Ma, Yuntao
Liu, Yang
Qu, Kaixian
Hutter, Marco
Robotics
68T40, 93C85, 70E60
I.2.9; I.2.10; I.2.8
Throwing is a fundamental skill that enables robots to manipulate objects in ways that extend beyond the reach of their arms. We present a control framework that combines learning and model-based control for prehensile whole-body throwing with legged mobile manipulators. Our framework consists of three components: a nominal tracking policy for the end-effector, a high-frequency residual policy to enhance tracking accuracy, and an optimization-based module to improve end-effector acceleration control. The proposed controller achieved the average of 0.28 m landing error when throwing at targets located 6 m away. Furthermore, in a comparative study with university students, the system achieved a velocity tracking error of 0.398 m/s and a success rate of 56.8%, hitting small targets randomly placed at distances of 3-5 m while throwing at a specified speed of 6 m/s. In contrast, humans have a success rate of only 15.2%. This work provides an early demonstration of prehensile throwing with quantified accuracy on hardware, contributing to progress in dynamic whole-body manipulation.
title Learning Accurate Whole-body Throwing with High-frequency Residual Policy and Pullback Tube Acceleration
topic Robotics
68T40, 93C85, 70E60
I.2.9; I.2.10; I.2.8
url https://arxiv.org/abs/2506.16986