ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Siheng, Ze, Yanjie, Wang, Yue, Liu, C. Karen, Abbeel, Pieter, Shi, Guanya, Duan, Rocky
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908580382244864
author Zhao, Siheng
Ze, Yanjie
Wang, Yue
Liu, C. Karen
Abbeel, Pieter
Shi, Guanya
Duan, Rocky
author_facet Zhao, Siheng
Ze, Yanjie
Wang, Yue
Liu, C. Karen
Abbeel, Pieter
Shi, Guanya
Duan, Rocky
contents Humanoid whole-body loco-manipulation promises transformative capabilities for daily service and warehouse tasks. While recent advances in general motion tracking (GMT) have enabled humanoids to reproduce diverse human motions, these policies lack the precision and object awareness required for loco-manipulation. To this end, we introduce ResMimic, a two-stage residual learning framework for precise and expressive humanoid control from human motion data. First, a GMT policy, trained on large-scale human-only motion, serves as a task-agnostic base for generating human-like whole-body movements. An efficient but precise residual policy is then learned to refine the GMT outputs to improve locomotion and incorporate object interaction. To further facilitate efficient training, we design (i) a point-cloud-based object tracking reward for smoother optimization, (ii) a contact reward that encourages accurate humanoid body-object interactions, and (iii) a curriculum-based virtual object controller to stabilize early training. We evaluate ResMimic in both simulation and on a real Unitree G1 humanoid. Results show substantial gains in task success, training efficiency, and robustness over strong baselines. Videos are available at https://resmimic.github.io/ .
format Preprint
id arxiv_https___arxiv_org_abs_2510_05070
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning
Zhao, Siheng
Ze, Yanjie
Wang, Yue
Liu, C. Karen
Abbeel, Pieter
Shi, Guanya
Duan, Rocky
Robotics
Machine Learning
Humanoid whole-body loco-manipulation promises transformative capabilities for daily service and warehouse tasks. While recent advances in general motion tracking (GMT) have enabled humanoids to reproduce diverse human motions, these policies lack the precision and object awareness required for loco-manipulation. To this end, we introduce ResMimic, a two-stage residual learning framework for precise and expressive humanoid control from human motion data. First, a GMT policy, trained on large-scale human-only motion, serves as a task-agnostic base for generating human-like whole-body movements. An efficient but precise residual policy is then learned to refine the GMT outputs to improve locomotion and incorporate object interaction. To further facilitate efficient training, we design (i) a point-cloud-based object tracking reward for smoother optimization, (ii) a contact reward that encourages accurate humanoid body-object interactions, and (iii) a curriculum-based virtual object controller to stabilize early training. We evaluate ResMimic in both simulation and on a real Unitree G1 humanoid. Results show substantial gains in task success, training efficiency, and robustness over strong baselines. Videos are available at https://resmimic.github.io/ .
title ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning
topic Robotics
Machine Learning
url https://arxiv.org/abs/2510.05070