Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions

TL;DR

This paper presents a novel LLM-based agentic framework for goal-directed city navigation without instructions, leveraging perception, reflection, and planning to improve decision-making in complex urban environments.

Contribution

It introduces a new workflow for LLM agents that combines perception, memory-based reflection, and planning, significantly enhancing navigation performance.

Findings

Fine-tuned LLaVA-7B accurately perceives landmarks and distances.

Memory reflection improves decision consistency and long-term planning.

The proposed method outperforms state-of-the-art baselines in city navigation tasks.

Abstract

This paper considers a scenario in city navigation: an AI agent is provided with language descriptions of the goal location with respect to some well-known landmarks; By only observing the scene around, including recognizing landmarks and road network connections, the agent has to make decisions to navigate to the goal location without instructions. This problem is very challenging, because it requires agent to establish self-position and acquire spatial representation of complex urban environment, where landmarks are often invisible. In the absence of navigation instructions, such abilities are vital for the agent to make high-quality decisions in long-range city navigation. With the emergent reasoning ability of large language models (LLMs), a tempting baseline is to prompt LLMs to "react" on each observation and make decisions accordingly. However, this baseline has very poor performance that the agent often repeatedly visits same locations and make short-sighted, inconsistent decisions. To address these issues, this paper introduces a novel agentic workflow featured by its abilities to perceive, reflect and plan. Specifically, we find LLaVA-7B can be fine-tuned to perceive the direction and distance of landmarks with sufficient accuracy for city navigation. Moreover, reflection is achieved through a memory mechanism, where past experiences are stored and can be retrieved with current perception for effective decision argumentation. Planning uses reflection results to produce long-term plans, which can avoid short-sighted decisions in long-range navigation. We show the designed workflow significantly improves navigation ability of the LLM agent compared with the state-of-the-art baselines.