Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation
John Z. Zhang, Maks Sorokin, Jan Brüdigam, Brandon Hung, Stephen Phillips + 12 more
TLDR
Sumo enables legged robots to dynamically manipulate large, heavy objects using a sim-to-real whole-body control policy steered by a sample-based planner.
Key contributions
- Sim-to-real approach for dynamic whole-body loco-manipulation in legged robots.
- Employs test-time steering of a pre-trained whole-body policy with a sample-based planner.
- Generalizes to diverse, heavy objects and tasks without additional tuning or training.
- Validated on a Spot robot (heavy tire, large barrier) and humanoids (door, table) in simulation.
Why it matters
This paper significantly advances robot manipulation by enabling legged robots to handle large, heavy objects dynamically. The method's ability to generalize across tasks and objects without retraining is a major step towards versatile, real-world robotic applications. It opens new possibilities for robots in logistics, construction, and disaster response.
Original Abstract
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 \href{https://sumo.rai-inst.com/}{https://sumo.rai-inst.com/}.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.