RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models

TL;DR

RATE-Nav introduces a region-aware termination strategy for zero-shot object navigation, significantly improving success rates by optimizing exploration termination using visual language models and exploration analysis.

Contribution

It proposes a novel termination enhancement method using region segmentation and exploration estimation, advancing zero-shot object navigation performance.

Findings

Achieves 67.8% success rate on HM3D dataset.

Shows 10% improvement over previous zero-shot methods on MP3D.

Enhances exploration efficiency with region-aware termination.

Abstract

Object Navigation (ObjectNav) is a fundamental task in embodied artificial intelligence. Although significant progress has been made in semantic map construction and target direction prediction in current research, redundant exploration and exploration failures remain inevitable. A critical but underexplored direction is the timely termination of exploration to overcome these challenges. We observe a diminishing marginal effect between exploration steps and exploration rates and analyze the cost-benefit relationship of exploration. Inspired by this, we propose RATE-Nav, a Region-Aware Termination-Enhanced method. It includes a geometric predictive region segmentation algorithm and region-Based exploration estimation algorithm for exploration rate calculation. By leveraging the visual question answering capabilities of visual language models (VLMs) and exploration rates enables efficient termination.RATE-Nav achieves a success rate of 67.8% and an SPL of 31.3% on the HM3D dataset. And on the more challenging MP3D dataset, RATE-Nav shows approximately 10% improvement over previous zero-shot methods.