A Deployable Embodied Vision-Language Navigation System with Hierarchical Cognition and Context-Aware Exploration

• URL: http://arxiv.org/abs/2604.21363v1
• Date: Thu, 23 Apr 2026 07:27:00 GMT
• Title: A Deployable Embodied Vision-Language Navigation System with Hierarchical Cognition and Context-Aware Exploration
• Abstract summary: In vision-language navigation (VLN), existing approaches often face a trade-off between strong reasoning capabilities and efficient deployment on real-world platforms.<n>We present a deployable embodied VLN system that achieves both high efficiency and robust high-level reasoning on real-world robotic platforms.
• Score: 29.871705369272124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bridging the gap between embodied intelligence and embedded deployment remains a key challenge in intelligent robotic systems, where perception, reasoning, and planning must operate under strict constraints on computation, memory, energy, and real-time execution. In vision-language navigation (VLN), existing approaches often face a fundamental trade-off between strong reasoning capabilities and efficient deployment on real-world platforms. In this paper, we present a deployable embodied VLN system that achieves both high efficiency and robust high-level reasoning on real-world robotic platforms. To achieve this, we decouple the system into three asynchronous modules: a real-time perception module for continuous environment sensing, a memory integration module for spatial-semantic aggregation, and a reasoning module for high-level decision making. We incrementally construct a cognitive memory graph to encode scene information, which is further decomposed into subgraphs to enable reasoning with a vision-language model (VLM). To further improve navigation efficiency and accuracy, we also leverage the cognitive memory graph to formulate the exploration problem as a context-aware Weighted Traveling Repairman Problem (WTRP), which minimizes the weighted waiting time of viewpoints. Extensive experiments in both simulation and real-world robotic platforms demonstrate improved navigation success and efficiency over existing VLN approaches, while maintaining real-time performance on resource-constrained hardware.

Related papers

• Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation [68.02899606570223]
  We propose TAMP-Nav, a unified framework for efficient embodied navigation.<n>First, we introduce a Pixel-to-3D Action Formulation (Point) that reformulates navigation into 2D visual coordinates.<n>Second, we propose an integrated Selective Reasoning and Anchor-Trajectory Memory mechanism (Think and Memorize)
  arXiv  Detail & Related papers  (2026-08-18T08:37:08Z)
• FSUNav: A Cerebrum-Cerebellum Architecture for Fast, Safe, and Universal Zero-Shot Goal-Oriented Navigation [8.950226217725994]
  This paper proposes FSUNav: a Cerebrum-Cerebellum architecture for fast, safe, and universal zero-shot goal-oriented navigation.<n>The proposed architecture integrates vision-language models (VLMs) with the proposed architecture.<n>FSUNav achieves state-of-the-art performance on object, instance image, and task navigation, significantly outperforming existing methods.
  arXiv  Detail & Related papers  (2026-04-03T16:01:58Z)
• ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation [66.02142169323521]
  Vision-Language-Action models and world models have recently emerged as promising paradigms for general-purpose robotic intelligence.<n>Existing benchmarks are largely simulator-centric, which provide controllability but fail to capture the reality gap caused by perception noise.<n>We introduce ManipArena, a standardized evaluation framework designed to bridge simulation and real-world execution.
  arXiv  Detail & Related papers  (2026-03-30T15:06:41Z)
• AgentVLN: Towards Agentic Vision-and-Language Navigation [78.739525400071]
  Vision-and-Language Navigation (VLN) requires an embodied agent to ground complex natural-language instructions into long-horizon navigation in unseen environments.<n>In this paper, we propose AgentVLN, a novel and efficient embodied navigation framework that can be deployed on edge computing platforms.
  arXiv  Detail & Related papers  (2026-03-18T12:43:47Z)
• History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation [18.716145266309802]
  Vision-Language Navigation (LNV) enables robots to follow natural-language instructions in visually grounded environments, serving as a key capability for embodied robotic systems.<n>Recent Vision-Language-Action-Models have demonstrated strong navigation performance, but their computational latency that limits real-time deployment.<n>We propose a training-free vision-language framework tailored to VLN-based VLN.
  arXiv  Detail & Related papers  (2026-03-06T17:03:16Z)
• TagaVLM: Topology-Aware Global Action Reasoning for Vision-Language Navigation [70.23578202012048]
  Vision-Language Navigation (VLN) presents a unique challenge for Large Vision-Language Models (VLMs) due to their inherent architectural mismatch.<n>We propose TagaVLM (Topology-Aware Global Action reasoning), an end-to-end framework that explicitly injects topological structures into the VLM backbone.<n>To enhance topological node information, an Interleaved Navigation Prompt strengthens node-level visual-text alignment.<n>With the embedded topological graph, the model is capable of global action reasoning, allowing for robust path correction.
  arXiv  Detail & Related papers  (2026-03-03T13:28:07Z)
• CoINS: Counterfactual Interactive Navigation via Skill-Aware VLM [13.352875026471445]
  We propose Counterfactual Interactive Navigation via Skill-aware VLM (CoINS)<n>We fine-tune a VLM, named InterNav-VLM, which incorporates skill affordance and concrete constraint parameters into the input context.<n>To execute the generated high-level plans, we develop a comprehensive skill library through reinforcement learning.
  arXiv  Detail & Related papers  (2026-01-07T14:10:46Z)
• How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective [103.44502230776352]
  We present a systematic investigation of Visual Spatial Reasoning (VSR) in Vision-Language Models (VLMs)<n>We categorize spatial intelligence into three levels of capability, ie, basic perception, spatial understanding, spatial planning, and curate SIBench, a spatial intelligence benchmark encompassing nearly 20 open-source datasets across 23 task settings.
  arXiv  Detail & Related papers  (2025-09-23T12:00:14Z)
• A Navigation Framework Utilizing Vision-Language Models [0.0]
  Vision-and-Language Navigation (VLN) presents a complex challenge in embodied AI.<n>Recent advances in large vision-language models (LVLMs), such as CLIP and Flamingo, have significantly improved multimodal understanding.<n>We propose a modular, plug-and-play navigation framework that decouples vision-language understanding from action planning.
  arXiv  Detail & Related papers  (2025-06-11T20:51:58Z)
• SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving [51.47621083057114]
  SOLVE is an innovative framework that synergizes Vision-Language Models with end-to-end (E2E) models to enhance autonomous vehicle planning.<n>Our approach emphasizes knowledge sharing at the feature level through a shared visual encoder, enabling comprehensive interaction between VLM and E2E components.
  arXiv  Detail & Related papers  (2025-05-22T15:44:30Z)
• Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation [60.80423207808076]
  Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation.<n>We propose the Dynamic Visual State Space (DVSS) block, which augments visual state space models with multi-scale convolutional operations.<n>We build HRVMamba, a novel model for efficient high-resolution representation learning.
  arXiv  Detail & Related papers  (2024-10-04T06:19:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.