EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval

TL;DR

EfficientNav enables on-device object-goal navigation by using semantics-aware memory retrieval and caching techniques, significantly reducing latency and maintaining high success rates with smaller language models.

Contribution

The paper introduces semantics-aware memory retrieval and discrete caching methods to improve on-device LLM-based object navigation, reducing latency and enhancing performance.

Findings

11.1% success rate improvement over GPT-4 baselines

6.7x real-time latency reduction

4.7x end-to-end latency reduction

Abstract

Object-goal navigation (ObjNav) tasks an agent with navigating to the location of a specific object in an unseen environment. Embodied agents equipped with large language models (LLMs) and online constructed navigation maps can perform ObjNav in a zero-shot manner. However, existing agents heavily rely on giant LLMs on the cloud, e.g., GPT-4, while directly switching to small LLMs, e.g., LLaMA3.2-11b, suffer from significant success rate drops due to limited model capacity for understanding complex navigation maps, which prevents deploying ObjNav on local devices. At the same time, the long prompt introduced by the navigation map description will cause high planning latency on local devices. In this paper, we propose EfficientNav to enable on-device efficient LLM-based zero-shot ObjNav. To help the smaller LLMs better understand the environment, we propose semantics-aware memory retrieval to prune redundant information in navigation maps. To reduce planning latency, we propose discrete memory caching and attention-based memory clustering to efficiently save and re-use the KV cache. Extensive experimental results demonstrate that EfficientNav achieves 11.1% improvement in success rate on HM3D benchmark over GPT-4-based baselines, and demonstrates 6.7x real-time latency reduction and 4.7x end-to-end latency reduction over GPT-4 planner. Our code is available on https://github.com/PKU-SEC-Lab/EfficientNav.