EmergeNav: Structured Embodied Inference for Zero-Shot Vision-and-Language Navigation in Continuous Environments

2026-03-16

AI Summary

Zero-shot vision-and-language navigation in continuous environments struggles to effectively translate the semantic priors of vision-language models into long-horizon embodied execution capabilities. To address this challenge, this work proposes EmergeNav, a novel framework that introduces an explicit Plan–Solve–Transition hierarchical execution structure. EmergeNav integrates goal-informed perception encoding (GIPE), contrastive dual-memory progress reasoning, and a role-disentangled Dual-FOV perception mechanism, enabling stable navigation without task-specific training or prior maps. Leveraging open-source VLM backbones such as Qwen3-VL, the method achieves success rates of 30.00% and 37.00% on the VLN-CE benchmark using only 8B and 32B parameter models, respectively, substantially outperforming existing zero-shot approaches.

Technology Category

• Computer Vision: Language and Vision
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Zero-shot vision-and-language navigation in continuous environments (VLN-CE) remains challenging for modern vision-language models (VLMs). Although these models encode useful semantic priors, their open-ended reasoning does not directly translate into stable long-horizon embodied execution. We argue that the key bottleneck is not missing knowledge alone, but missing an execution structure for organizing instruction following, perceptual grounding, temporal progress, and stage verification. We propose EmergeNav, a zero-shot framework that formulates continuous VLN as structured embodied inference. EmergeNav combines a Plan--Solve--Transition hierarchy for stage-structured execution, GIPE for goal-conditioned perceptual extraction, contrastive dual-memory reasoning for progress grounding, and role-separated Dual-FOV sensing for time-aligned local control and boundary verification. On VLN-CE, EmergeNav achieves strong zero-shot performance using only open-source VLM backbones and no task-specific training, explicit maps, graph search, or waypoint predictors, reaching 30.00 SR with Qwen3-VL-8B and 37.00 SR with Qwen3-VL-32B. These results suggest that explicit execution structure is a key ingredient for turning VLM priors into stable embodied navigation behavior.

Problem

• Vision-and-Language Navigation
• Zero-shot Learning
• Continuous Environments
• Embodied AI
• Execution Structure

Innovation

• structured embodied inference
• zero-shot VLN
• stage-structured execution
• dual-memory reasoning
• Dual-FOV sensing