Deploying Foundation Model-Enabled Air and Ground Robots in the Field: Challenges and Opportunities

TL;DR

This paper explores deploying foundation model-enabled robots in large-scale, unstructured environments, highlighting challenges, recent deployments, and the first demonstration of large-scale LLM-enabled robot planning in such settings.

Contribution

It introduces the SPINE framework for LLM-enabled robot autonomy, demonstrates large-scale unstructured environment deployment, and presents the first language-driven UAV planner on SWaP-limited devices.

Findings

First large-scale LLM-enabled robot planning in unstructured environments

Successful deployment of SPINE in field robotic missions covering several kilometers

Development of onboard language models for UAV planning

Abstract

The integration of foundation models (FMs) into robotics has enabled robots to understand natural language and reason about the semantics in their environments. However, existing FM-enabled robots primary operate in closed-world settings, where the robot is given a full prior map or has a full view of its workspace. This paper addresses the deployment of FM-enabled robots in the field, where missions often require a robot to operate in large-scale and unstructured environments. To effectively accomplish these missions, robots must actively explore their environments, navigate obstacle-cluttered terrain, handle unexpected sensor inputs, and operate with compute constraints. We discuss recent deployments of SPINE, our LLM-enabled autonomy framework, in field robotic settings. To the best of our knowledge, we present the first demonstration of large-scale LLM-enabled robot planning in unstructured environments with several kilometers of missions. SPINE is agnostic to a particular LLM, which allows us to distill small language models capable of running onboard size, weight and power (SWaP) limited platforms. Via preliminary model distillation work, we then present the first language-driven UAV planner using on-device language models. We conclude our paper by proposing several promising directions for future research.