Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915933057974272 |
|---|---|
| author | Zhang, John Z. Sorokin, Maks Brüdigam, Jan Hung, Brandon Phillips, Stephen Yershov, Dmitry Niroui, Farzad Zhao, Tong Fermoselle, Leonor Zhu, Xinghao Cao, Chao Ta, Duy Pang, Tao Wang, Jiuguang Culbertson, Preston Manchester, Zachary Cléac'h, Simon Le |
| author_facet | Zhang, John Z. Sorokin, Maks Brüdigam, Jan Hung, Brandon Phillips, Stephen Yershov, Dmitry Niroui, Farzad Zhao, Tong Fermoselle, Leonor Zhu, Xinghao Cao, Chao Ta, Duy Pang, Tao Wang, Jiuguang Culbertson, Preston Manchester, Zachary Cléac'h, Simon Le |
| contents | This paper presents a sim-to-real approach that enables legged robots to dynamically manipulate large and heavy objects with whole-body dexterity. Our key insight is that by performing test-time steering of a pre-trained whole-body control policy with a sample-based planner, we can enable these robots to solve a variety of dynamic loco-manipulation tasks. Interestingly, we find our method generalizes to a diverse set of objects and tasks with no additional tuning or training, and can be further enhanced by flexibly adjusting the cost function at test time. We demonstrate the capabilities of our approach through a variety of challenging loco-manipulation tasks on a Spot quadruped robot in the real world, including uprighting a tire heavier than the robot's nominal lifting capacity and dragging a crowd-control barrier larger and taller than the robot itself. Additionally, we show that the same approach can be generalized to humanoid loco-manipulation tasks, such as opening a door and pushing a table, in simulation. Project code and videos are available at https://sumo.rai-inst.com/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08508 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation Zhang, John Z. Sorokin, Maks Brüdigam, Jan Hung, Brandon Phillips, Stephen Yershov, Dmitry Niroui, Farzad Zhao, Tong Fermoselle, Leonor Zhu, Xinghao Cao, Chao Ta, Duy Pang, Tao Wang, Jiuguang Culbertson, Preston Manchester, Zachary Cléac'h, Simon Le Robotics This paper presents a sim-to-real approach that enables legged robots to dynamically manipulate large and heavy objects with whole-body dexterity. Our key insight is that by performing test-time steering of a pre-trained whole-body control policy with a sample-based planner, we can enable these robots to solve a variety of dynamic loco-manipulation tasks. Interestingly, we find our method generalizes to a diverse set of objects and tasks with no additional tuning or training, and can be further enhanced by flexibly adjusting the cost function at test time. We demonstrate the capabilities of our approach through a variety of challenging loco-manipulation tasks on a Spot quadruped robot in the real world, including uprighting a tire heavier than the robot's nominal lifting capacity and dragging a crowd-control barrier larger and taller than the robot itself. Additionally, we show that the same approach can be generalized to humanoid loco-manipulation tasks, such as opening a door and pushing a table, in simulation. Project code and videos are available at https://sumo.rai-inst.com/. |
| title | Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.08508 |