Bridging the Indoor-Outdoor Gap: Vision-Centric Instruction-Guided Embodied Navigation for the Last Meters

• URL: http://arxiv.org/abs/2602.06427v1
• Date: Fri, 06 Feb 2026 06:52:23 GMT
• Title: Bridging the Indoor-Outdoor Gap: Vision-Centric Instruction-Guided Embodied Navigation for the Last Meters
• Abstract summary: Embodied navigation holds significant promise for real-world applications such as last-mile delivery.<n>We introduce a novel task: out-to-in prior-free instruction-driven embodied navigation.<n>We propose a vision-centric embodied navigation framework that leverages image-based prompts to drive decision-making.
• Score: 5.804644839559736
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embodied navigation holds significant promise for real-world applications such as last-mile delivery. However, most existing approaches are confined to either indoor or outdoor environments and rely heavily on strong assumptions, such as access to precise coordinate systems. While current outdoor methods can guide agents to the vicinity of a target using coarse-grained localization, they fail to enable fine-grained entry through specific building entrances, critically limiting their utility in practical deployment scenarios that require seamless outdoor-to-indoor transitions. To bridge this gap, we introduce a novel task: out-to-in prior-free instruction-driven embodied navigation. This formulation explicitly eliminates reliance on accurate external priors, requiring agents to navigate solely based on egocentric visual observations guided by instructions. To tackle this task, we propose a vision-centric embodied navigation framework that leverages image-based prompts to drive decision-making. Additionally, we present the first open-source dataset for this task, featuring a pipeline that integrates trajectory-conditioned video synthesis into the data generation process. Through extensive experiments, we demonstrate that our proposed method consistently outperforms state-of-the-art baselines across key metrics including success rate and path efficiency.

Related papers

• AutoPath: Learning Transferable Goal-Conditioned Stochastic Path Prior for Safe Navigation Without Human Demonstrations [103.61864552260316]
  Real-time navigation in dynamic environments requires collision-free and dynamically feasible motion under limited perception.<n>We formulate navigation as learning a transferable goal-aligned path prior that models a reusable distribution over goal-aligned geometry-consistent local paths conditioned on local observations.<n>We develop a structured prior learning framework that parameterizes local paths using a geometry-aware polar action manifold and incorporates risk-sensitive utility shaping with multi-goal distributional rollouts for stable and safety-aware planning.
  arXiv  Detail & Related papers  (2026-07-13T16:00:41Z)
• 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)
• Beyond Waypoints: Dual-Heatmap Grounding for Cross-Embodiment Semantic Navigation [13.081539889943906]
  In this work, we focus on the practical setting of in-FOV semantic navigation.<n>We propose a unified Vision-Language framework that abandons single-point regression in favor of a Dual-Heatmap representation.<n>Our framework achieves state-of-the-art performance among comparable 8B baselines.
  arXiv  Detail & Related papers  (2026-05-19T06:12:59Z)
• SignNav: Leveraging Signage for Semantic Visual Navigation in Large-Scale Indoor Environments [57.79171900005793]
  Humans routinely leverage semantic hints provided by signage to navigate to destinations within Large-Scale Indoor environments.<n>This paper introduces a novel embodied navigation task, SignNav, which requires the agent to interpret semantic hint from signage and reason about the subsequent action based on current observation.<n>We propose the spatial-aware module grounds the semantic hint of signage into physical world, while the temporal-aware module captures long-range dependencies between historical states and current observation.
  arXiv  Detail & Related papers  (2026-03-17T06:36:26Z)
• 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)
• AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild [62.47761809929869]
  Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations.<n>Current VLN research for unmanned aerial vehicles (UAVs) relies on detailed, pre-specified instructions to guide the UAV along predetermined routes.<n>We propose AutoFly, an end-to-end Vision-Language-Action model for autonomous UAV navigation.
  arXiv  Detail & Related papers  (2026-02-10T11:08:07Z)
• Learning Goal-Oriented Language-Guided Navigation with Self-Improving Demonstrations at Scale [90.91312440221306]
  We present SID, a goal-oriented language-guided navigation learning approach with Self-Improving Demonstrations.<n>Specifically, SID learns an initial agent on the shortest-path data sampled from environments and then leverages this agent to generate novel exploration trajectories.<n>We show that this iterative self-improving pipeline readily scales to new environments, and the resulting demonstrations can be transferred across a variety of language-guided navigation tasks.
  arXiv  Detail & Related papers  (2025-09-29T15:15:54Z)
• Grid2Guide: A* Enabled Small Language Model for Indoor Navigation [6.341317643879287]
  This research presents a hybrid navigation framework that combines the A* search algorithm with a Small Language Model (SLM) to generate clear, human-readable route instructions.<n>The results validate the proposed approach as a lightweight, infrastructure-free solution for real-time indoor navigation support.
  arXiv  Detail & Related papers  (2025-08-11T15:39:27Z)
• 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)
• IN-Sight: Interactive Navigation through Sight [20.184155117341497]
  IN-Sight is a novel approach to self-supervised path planning. It calculates traversability scores and incorporates them into a semantic map. To precisely navigate around obstacles, IN-Sight employs a local planner.
  arXiv  Detail & Related papers  (2024-08-01T07:27:54Z)
• TOP-Nav: Legged Navigation Integrating Terrain, Obstacle and Proprioception Estimation [5.484041860401147]
  TOP-Nav is a novel legged navigation framework that integrates a comprehensive path planner with Terrain awareness, Obstacle avoidance and close-loop Proprioception. We show that TOP-Nav achieves open-world navigation that the robot can handle terrains or disturbances beyond the distribution of prior knowledge.
  arXiv  Detail & Related papers  (2024-04-23T17:42:45Z)
• How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers [94.46825166907831]
  We present a training-free solution to tackle the object goal navigation problem in Embodied AI. Our method builds a structured scene representation based on the classic visual simultaneous localization and mapping (V-SLAM) framework. Our method propagates semantics on the scene graphs based on language priors and scene statistics to introduce semantic knowledge to the geometric frontiers.
  arXiv  Detail & Related papers  (2023-05-26T13:38:33Z)
• ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments [56.194988818341976]
  Vision-language navigation is a task that requires an agent to follow instructions to navigate in environments. We propose ETPNav, which focuses on two critical skills: 1) the capability to abstract environments and generate long-range navigation plans, and 2) the ability of obstacle-avoiding control in continuous environments. ETPNav yields more than 10% and 20% improvements over prior state-of-the-art on R2R-CE and RxR-CE datasets.
  arXiv  Detail & Related papers  (2023-04-06T13:07:17Z)
• Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration [83.96729205383501]
  We introduce prompt-based learning to achieve fast adaptation for language embeddings. Our model can adapt to diverse vision-language navigation tasks, including VLN and REVERIE.
  arXiv  Detail & Related papers  (2022-03-08T11:01:24Z)
• Occupancy Anticipation for Efficient Exploration and Navigation [97.17517060585875]
  We propose occupancy anticipation, where the agent uses its egocentric RGB-D observations to infer the occupancy state beyond the visible regions. By exploiting context in both the egocentric views and top-down maps our model successfully anticipates a broader map of the environment. Our approach is the winning entry in the 2020 Habitat PointNav Challenge.
  arXiv  Detail & Related papers  (2020-08-21T03:16:51Z)
• Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments [48.898567402373324]
  We develop a language-guided navigation task set in a continuous 3D environment. By being situated in continuous environments, this setting lifts a number of assumptions implicit in prior work.
  arXiv  Detail & Related papers  (2020-04-06T17:49:12Z)

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.