Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation

TL;DR

This paper introduces a sim-to-real method enabling legged robots to perform dynamic whole-body manipulation tasks with generalization across objects and tasks, using test-time control steering and planning.

Contribution

It presents a novel approach combining pre-trained policies with test-time planning to achieve versatile and generalizable loco-manipulation in real robots without additional training.

Findings

Successfully manipulated heavy objects like tires and barriers in real-world tests.

Generalized to humanoid tasks such as opening doors and pushing tables in simulation.

Method requires no additional training or tuning for new objects or tasks.

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 https://sumo.rai-inst.com/.