Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation
This addresses the challenge of dynamic loco-manipulation for legged robots, enabling them to handle varied real-world objects and tasks, though it appears incremental as it builds on existing sim-to-real and planning methods.
The paper tackles the problem of enabling legged robots to dynamically manipulate large and heavy objects with whole-body dexterity, achieving this through a sim-to-real approach that generalizes to diverse tasks without additional tuning, as demonstrated by real-world tasks like uprighting a tire heavier than the robot's capacity.
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/}.