FEG-VON: Frontier Embedding Graph for Efficient Visual Object Navigation

Visual object navigation, requiring agents to locate target objects in novel environments through egocentric visual observation, remains a critical challenge in Embodied AI. We propose FEG-VON, a training-free framework that constructs and maintains a Frontier Embedding Graph for efficient Visual Object Navigation. The graph initializes frontier embeddings using Vision Language Models (VLMs), where visual observations are encoded into spatially anchored semantic embeddings through cross-modal alignment with target text descriptors. We then update the graph by aggregating spatio-temporal semantic relations across frontiers, enabling online adaptation to new targets via similarity scoring without remapping. The evaluation results in public benchmarks demonstrate the superior performance of FEG-VON in both single- and multi-object navigation tasks compared with state-of-the-art methods. Crucially, FEG-VON eliminates dependency on task-specific training for exploration and advances the feasibility of zero-shot navigation in open-world environments.

Authors

• Yingru Dai
• Pengwei Xie
• Yikai Liu
• Siang Chen
• Wenming Yang
• Guijin Wang

Keywords

• Training
• Visualization
• Navigation
• Semantics
• Benchmark testing
• Cognition
• Artificial intelligence
• Intelligent robots
• Efficient Navigation
• Object Navigation
• Benchmark
• Similarity Score
• Target Object
• Language Model
• Navigation Task
• Semantic Embedding
• Ablation
• Shortest Path
• Semantic Information
• Failure Modes
• Semantic Segmentation
• RGB Images
• Exploration Process
• Semantic Map
• Map Reconstruction
• Simultaneous Localization And Mapping
• End Of Episode
• Navigation Performance
• Dynamic Update
• Unseen Environments
• Unseen Objects
• Image Embedding
• Semantic Coherence