Reasoning about the Unseen for Efficient Outdoor Object Navigation

TL;DR

This paper introduces a novel outdoor object navigation task, leveraging large language models for reasoning about unseen areas, with new metrics and successful real-world experiments on drones and quadrupeds.

Contribution

It presents a new outdoor navigation task, a reasoning mechanism for LLMs to hallucinate future states, and a success metric tailored for complex outdoor environments.

Findings

Outperforms naive LLM-based approaches in outdoor navigation

Demonstrates effective navigation on simulated drone and physical quadruped

Introduces a new success metric for outdoor object navigation

Abstract

Robots should exist anywhere humans do: indoors, outdoors, and even unmapped environments. In contrast, the focus of recent advancements in Object Goal Navigation(OGN) has targeted navigating in indoor environments by leveraging spatial and semantic cues that do not generalize outdoors. While these contributions provide valuable insights into indoor scenarios, the broader spectrum of real-world robotic applications often extends to outdoor settings. As we transition to the vast and complex terrains of outdoor environments, new challenges emerge. Unlike the structured layouts found indoors, outdoor environments lack clear spatial delineations and are riddled with inherent semantic ambiguities. Despite this, humans navigate with ease because we can reason about the unseen. We introduce a new task OUTDOOR, a new mechanism for Large Language Models (LLMs) to accurately hallucinate possible futures, and a new computationally aware success metric for pushing research forward in this more complex domain. Additionally, we show impressive results on both a simulated drone and physical quadruped in outdoor environments. Our agent has no premapping and our formalism outperforms naive LLM-based approaches