WildLMa: Long Horizon Loco-Manipulation in the Wild

TL;DR

WildLMa introduces a comprehensive framework combining learned skills, language-conditioned imitation, and planning for long-horizon, versatile mobile manipulation in diverse real-world environments using quadruped robots.

Contribution

The paper presents WildLMa, a novel system integrating a low-level controller, generalizable visuomotor skills, and LLM-based planning for in-the-wild manipulation tasks.

Findings

Higher grasping success rate with fewer demonstrations compared to RL baselines.

CLIP-based language-conditioned imitation generalizes to unseen objects.

Successful real-world applications like trash cleanup and object rearrangement.

Abstract

'In-the-wild' mobile manipulation aims to deploy robots in diverse real-world environments, which requires the robot to (1) have skills that generalize across object configurations; (2) be capable of long-horizon task execution in diverse environments; and (3) perform complex manipulation beyond pick-and-place. Quadruped robots with manipulators hold promise for extending the workspace and enabling robust locomotion, but existing results do not investigate such a capability. This paper proposes WildLMa with three components to address these issues: (1) adaptation of learned low-level controller for VR-enabled whole-body teleoperation and traversability; (2) WildLMa-Skill -- a library of generalizable visuomotor skills acquired via imitation learning or heuristics and (3) WildLMa-Planner -- an interface of learned skills that allow LLM planners to coordinate skills for long-horizon tasks. We demonstrate the importance of high-quality training data by achieving higher grasping success rate over existing RL baselines using only tens of demonstrations. WildLMa exploits CLIP for language-conditioned imitation learning that empirically generalizes to objects unseen in training demonstrations. Besides extensive quantitative evaluation, we qualitatively demonstrate practical robot applications, such as cleaning up trash in university hallways or outdoor terrains, operating articulated objects, and rearranging items on a bookshelf.