DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Yutong, Wen, Kehan, Yu, Fisher
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917619039207424
author Hu, Yutong
Wen, Kehan
Yu, Fisher
author_facet Hu, Yutong
Wen, Kehan
Yu, Fisher
contents Learning dexterous locomotion policy for legged robots is becoming increasingly popular due to its ability to handle diverse terrains and resemble intelligent behaviors. However, joint manipulation of moving objects and locomotion with legs, such as playing soccer, receive scant attention in the learning community, although it is natural for humans and smart animals. A key challenge to solve this multitask problem is to infer the objectives of locomotion from the states and targets of the manipulated objects. The implicit relation between the object states and robot locomotion can be hard to capture directly from the training experience. We propose adding a feedback control block to compute the necessary body-level movement accurately and using the outputs as dynamic joint-level locomotion supervision explicitly. We further utilize an improved ball dynamic model, an extended context-aided estimator, and a comprehensive ball observer to facilitate transferring policy learned in simulation to the real world. We observe that our learning scheme can not only make the policy network converge faster but also enable soccer robots to perform sophisticated maneuvers like sharp cuts and turns on flat surfaces, a capability that was lacking in previous methods. Video and code are available at https://github.com/SysCV/soccer-player
format Preprint
id arxiv_https___arxiv_org_abs_2403_14300
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision
Hu, Yutong
Wen, Kehan
Yu, Fisher
Robotics
Artificial Intelligence
Learning dexterous locomotion policy for legged robots is becoming increasingly popular due to its ability to handle diverse terrains and resemble intelligent behaviors. However, joint manipulation of moving objects and locomotion with legs, such as playing soccer, receive scant attention in the learning community, although it is natural for humans and smart animals. A key challenge to solve this multitask problem is to infer the objectives of locomotion from the states and targets of the manipulated objects. The implicit relation between the object states and robot locomotion can be hard to capture directly from the training experience. We propose adding a feedback control block to compute the necessary body-level movement accurately and using the outputs as dynamic joint-level locomotion supervision explicitly. We further utilize an improved ball dynamic model, an extended context-aided estimator, and a comprehensive ball observer to facilitate transferring policy learned in simulation to the real world. We observe that our learning scheme can not only make the policy network converge faster but also enable soccer robots to perform sophisticated maneuvers like sharp cuts and turns on flat surfaces, a capability that was lacking in previous methods. Video and code are available at https://github.com/SysCV/soccer-player
title DexDribbler: Learning Dexterous Soccer Manipulation via Dynamic Supervision
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2403.14300