MCNav: Memory-Aware Dynamic Cognitive Map for Zero-shot Goal-oriented Navigation

TL;DR

MCNav introduces a memory-aware dynamic cognitive map and exploration strategies to improve zero-shot instance-level goal navigation in complex environments.

Contribution

It presents a novel memory-augmented navigation framework with strategies for goal re-validation and missed goal re-exploration, achieving state-of-the-art results.

Findings

Achieves state-of-the-art performance on HM3Dv1 and HM3Dv2 datasets.

Effectively re-validates previously seen objects to correct matching failures.

Successfully estimates the likelihood of targets in explored regions using contextual cues.

Abstract

Navigating to instance-level targets in complex environments is a challenging problem. Many existing zero-shot methods achieve strong performance by modeling the entire environment and leveraging large language models for scene understanding. However, such strategies primarily focus on exploring new regions while lacking a deeper exploitation of information from previously explored areas. Consequently, when targets are missed or misidentified within previously visited regions, navigation failures occur frequently. To address these limitations, we propose MCNav, a memory-aware navigation framework with a dynamic cognitive map. This map stores efficiently queryable information about relevant objects in explored areas. Building on this memory structure, MCNav introduces two memory-aware exploration strategies: goal re-validation, which re-assesses previously seen objects to correct matching failures, and missed goal re-exploration, which estimates the likelihood that a target is present in an explored region from contextual cues. These strategies are further stabilized by a blacklist mechanism to prevent repeated errors and a double-check mechanism for high-confidence confirmation. We evaluate MCNav on the HM3Dv1 and HM3Dv2 datasets across three different tasks, where it achieves state-of-the-art performance, particularly on the instance-level goal navigation task.