ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion

2025-04-20

AI Summary

To address the challenges of zero-shot object navigation in unknown environments—specifically, low detection accuracy and inefficiency under weak semantic cues or visually similar distractors—this paper proposes an environment-aware adaptive navigation method. The approach features a semantic availability discrimination mechanism that dynamically switches between semantic reasoning and geometry-driven exploration; a target-centric long-horizon semantic fusion module to enhance robustness against false detections; and a cross-modal end-to-end reinforcement learning framework integrating semantic segmentation, geometric mapping, and memory-augmented navigation. Evaluated on HM3Dv1/v2 and MP3D, our method achieves state-of-the-art performance in Success weighted by Path Length (SPL) and success rate. Ablation studies confirm the effectiveness of each component. Furthermore, the method has been successfully deployed on a real-world robotic platform.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Natural Language Processing: Safety and Robustness
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Navigating unknown environments to find a target object is a significant challenge. While semantic information is crucial for navigation, relying solely on it for decision-making may not always be efficient, especially in environments with weak semantic cues. Additionally, many methods are susceptible to misdetections, especially in environments with visually similar objects. To address these limitations, we propose ApexNav, a zero-shot object navigation framework that is both more efficient and reliable. For efficiency, ApexNav adaptively utilizes semantic information by analyzing its distribution in the environment, guiding exploration through semantic reasoning when cues are strong, and switching to geometry-based exploration when they are weak. For reliability, we propose a target-centric semantic fusion method that preserves long-term memory of the target object and similar objects, reducing false detections and minimizing task failures. We evaluate ApexNav on the HM3Dv1, HM3Dv2, and MP3D datasets, where it outperforms state-of-the-art methods in both SR and SPL metrics. Comprehensive ablation studies further demonstrate the effectiveness of each module. Furthermore, real-world experiments validate the practicality of ApexNav in physical environments. Project page is available at https://sysu-star.com/ApexNav.

Problem

• Efficient navigation in unknown environments with weak semantic cues
• Reducing misdetections in environments with visually similar objects
• Adaptive semantic and geometry-based exploration for reliable navigation

Innovation

• Adaptive semantic-geometric exploration strategy
• Target-centric semantic fusion method
• Zero-shot object navigation framework