AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning

• URL: http://arxiv.org/abs/2606.10927v1
• Date: Tue, 09 Jun 2026 14:35:53 GMT
• Title: AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning
• Abstract summary: We propose AllDayNav, a lifelong self-learning navigation framework that implicitly encodes scene dynamics into the billion-scale parameters of a large model via reinforcement learning.<n>Experiments show that AllDayNav achieves success rates approaching $100%$ and consistently surpasses strong map-based, VLM, and RL baselines in path efficiency and robustness.
• Score: 15.951251568937074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Lifelong embodied navigation in dynamic environments requires robots to form persistent scene understanding from fragmentary observations, which remains difficult for existing methods that rely on explicit maps or scene graphs and struggle to generalize beyond structured settings. We propose AllDayNav, a lifelong self-learning navigation framework that implicitly encodes scene dynamics into the billion-scale parameters of a large model via reinforcement learning, powered by a self-evolving multimodal memory that maintains and updates visual keyframes, semantic descriptions, and temporal context while autonomously generating open-vocabulary instructions, image goals, and structured rewards. Experiments in both synthetic and real-world environments across cross-room, cross-episode, and cross-task scenarios show that AllDayNav achieves success rates approaching $100\%$ and consistently surpasses strong map-based, VLM, and RL baselines in path efficiency and robustness, demonstrating implicit, memory-driven reinforcement learning as a scalable alternative to explicit mapping for reliable lifelong navigation.

Related papers

• LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation [52.91080323083409]
  Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments.<n>Here we present LightNav-0, a compact generalist embodied navigation model that elicits the spatial intelligence of a pretrained VLM and aligns it with navigation, without task-specific prediction heads.
  arXiv  Detail & Related papers  (2026-08-31T15:08:53Z)
• GUIDE: Goal-Initialized Directional Understanding for End-to-End Visual Navigation [22.535896749415627]
  GUIDE is a fully end-to-end reinforcement learning framework designed to cultivate internal directional awareness.<n>We evaluate the proposed framework across both simulation and real-world scenarios on a quadruped robot.<n>Experiments show that GUIDE learns reliable egomotion and directional awareness, enabling a fully end-to-end deployed policy.
  arXiv  Detail & Related papers  (2026-06-09T13:19:30Z)
• OpenFrontier: General Navigation with Visual-Language Grounded Frontiers [54.661157616245966]
  Open-world navigation requires robots to make decisions in complex everyday environments.<n>Recent advances in vision--language navigation (VLN) and vision--language--action (VLA) models enable end-to-end policies conditioned on natural language.<n>We propose OpenFrontier, a training-free navigation framework that seamlessly integrates diverse vision--language prior models.
  arXiv  Detail & Related papers  (2026-03-05T17:02:22Z)
• Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoning [58.25418970608328]
  Vision-Language Navigation aims to enable agents to navigate to a target location based on language instructions.<n>Recent research indicates that by means of fast and slow cognition systems, human beings could generate stable policies.<n>We propose the slow4fast-VLN, establishing a dynamic interactive fast-slow reasoning framework.
  arXiv  Detail & Related papers  (2026-01-14T03:22:16Z)
• VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory [43.2995099083993]
  VLA models have shown promising potential in embodied navigation by unifying perception and planning.<n>Most existing VLA models rely on reactive mappings directly from observations to actions.<n>We propose VLingNav, a VLA model for embodied navigation grounded in linguistic-driven cognition.
  arXiv  Detail & Related papers  (2026-01-13T15:43:43Z)
• CausalNav: A Long-term Embodied Navigation System for Autonomous Mobile Robots in Dynamic Outdoor Scenarios [20.83088545971651]
  CausalNav is the first scene graph-based semantic navigation framework tailored for dynamic outdoor environments.<n>We construct a multi-level semantic scene graph using LLMs, that hierarchically integrates coarse-grained map data with fine-grained object entities.<n>By fusing real-time perception with offline map data, the Embodied Graph supports robust navigation across varying spatial granularities.
  arXiv  Detail & Related papers  (2026-01-05T08:00:34Z)
• From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning [59.88543114325153]
  We introduce the Seeing-to-Experiencing framework to scale the capability of navigation foundation models with reinforcement learning.<n>S2E combines the strengths of pre-training on videos and post-training through RL.<n>We establish a comprehensive end-to-end evaluation benchmark, NavBench-GS, built on photorealistic 3DGS reconstructions of real-world scenes.
  arXiv  Detail & Related papers  (2025-07-29T17:26:10Z)
• Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based Adaptation [12.561993540768729]
  We present LE-Nav, an interpretable and scene-aware navigation framework for service robots.<n>To achieve zero-shot scene understanding, we utilize one-shot exemplars and chain-of-thought prompting strategies.<n>Experiments show that LE-Nav can generate hyperparameters achieving human-level tuning across diverse planners and scenarios.
  arXiv  Detail & Related papers  (2025-07-15T05:37:24Z)
• NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments [67.18144414660681]
  Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to execute sequential navigation actions in complex environments guided by natural language instructions.<n>Inspired by human cognition, we present NavMorph, a self-evolving world model framework that enhances environmental understanding and decision-making in VLN-CE tasks.
  arXiv  Detail & Related papers  (2025-06-30T02:20:00Z)
• NavigateDiff: Visual Predictors are Zero-Shot Navigation Assistants [24.689242976554482]
  Navigating unfamiliar environments presents significant challenges for household robots.<n>Existing reinforcement learning methods cannot be directly transferred to new environments.<n>We try to transfer the logical knowledge and the generalization ability of pre-trained foundation models to zero-shot navigation.
  arXiv  Detail & Related papers  (2025-02-19T17:27:47Z)
• Learning Navigational Visual Representations with Semantic Map Supervision [85.91625020847358]
  We propose a navigational-specific visual representation learning method by contrasting the agent's egocentric views and semantic maps. Ego$2$-Map learning transfers the compact and rich information from a map, such as objects, structure and transition, to the agent's egocentric representations for navigation.
  arXiv  Detail & Related papers  (2023-07-23T14:01:05Z)

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.