WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation

• URL: http://arxiv.org/abs/2606.04907v1
• Date: Wed, 03 Jun 2026 14:05:19 GMT
• Title: WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation
• Abstract summary: Visual navigation requires generating smooth and collision-free trajectories under complex geometric and physical constraints.<n>We propose WAM-Nav, a Latent World-Action Model for embodied visual navigation that jointly learns action generation and latent visual foresight.
• Score: 31.539730066120374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual navigation requires generating smooth and collision-free trajectories under complex geometric and physical constraints. Existing reactive policies that directly map observations to actions lack anticipatory reasoning, limiting their ability to proactively avoid obstacles. While visual imagination offers predictive foresight, conventional modular approaches separate scene prediction from policy learning, often leading to error accumulation and inefficient inference. To address these limitations, we propose WAM-Nav, a Latent World-Action Model for embodied visual navigation that jointly learns action generation and latent visual foresight, enabling more robust and foresighted navigation decisions without compromising inference efficiency. Specifically, WAM-Nav utilizes a shared Diffusion Transformer for asymmetric joint diffusion to concurrently generate long-horizon actions and short-horizon visual foresight, reducing the inference latency and visual error accumulation inherent in multi-step autoregressive rollouts. To further encourage smooth and consistent trajectory generation, we introduce a dual-stream contextual conditioning mechanism that integrates episode-level ego-motion history with sequential visual observations. Combined with a unified goal alignment module that preserves balanced representations across goal types, WAM-Nav naturally supports Image-Goal, Point-Goal, and No-Goal exploration within a single policy. Extensive experiments on the challenging ClutterScenes and InternScenes benchmarks demonstrate strong generalization of WAM-Nav, particularly on Image-Goal and Point-Goal navigation, where it improves success rates by 15.7% and 3.3%, respectively. Real-world deployment further validates effective zero-shot sim-to-real transfer, achieving an average 85% task success rate across diverse indoor and outdoor environments.

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)
• Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation [24.310993695214094]
  We propose SWAM (Spatial-perceiving World Action Model), a task-centric joint observation-action generation framework.<n>Given start and goal RGB observations, SWAM performs single-pass inference to simultaneously generate intermediate RGB-D sequences and corresponding action trajectories.<n>We show that SWAM significantly outperforms state-of-the-art two-stage planners in success rate, trajectory accuracy, and inference efficiency.
  arXiv  Detail & Related papers  (2026-06-29T07:43:47Z)
• Ordinal Neural Collapse as a Representation Prior for Visual Navigation [14.612259909790454]
  We present ORION, a method that organizes the encoder's representation space according to the ordinal structure of navigation actions.<n>Experiments show that ORION consistently outperforms end-to-end and neural collapse baselines in navigation success rate and goal progress.
  arXiv  Detail & Related papers  (2026-06-25T10:25:25Z)
• VISTA: Scale-Aware Visual Navigation via Action History Conditioning [4.792216056979392]
  Vision Navigation Foundation Models (VNMs) promise end-to-end learned navigation policies capable of zero-shot deployment.<n>Current VNMs often struggle in visually repetitive environments that lack distinct features.<n>We present VISTA, which generalizes robustly to out-of-distribution environments, achieving 100% goal prediction accuracy in zero-shot, real-world deployment.
  arXiv  Detail & Related papers  (2026-06-15T21:01:30Z)
• LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning [51.969318585152116]
  LatentPilot exploits future observations during training as a valuable data source to learn action-conditioned visual dynamics.<n>We propose a flywheel-style training mechanism that iteratively collects on-policy trajectories and retrains the model to better match the agent's behavior distribution.<n> Experiments on R2R-CE, RxR-CE, and R2R-PE benchmarks achieve new SOTA results, and real-robot tests across diverse environments demonstrate LatentPilot's superior understanding of environment-action dynamics in scene.
  arXiv  Detail & Related papers  (2026-03-31T02:21:59Z)
• \textsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation [50.027425808733994]
  textscNaVIDA is a unified VLN framework that couples policy learning with action-grounded visual dynamics and adaptive execution.<n>textscNaVIDA augments training with chunk-based inverse-dynamics supervision to learn causal relationship between visual changes and corresponding actions.<n>Experiments show that textscNaVIDA achieves superior navigation performance compared to state-of-the-art methods with fewer parameters.
  arXiv  Detail & Related papers  (2026-01-26T06:16:17Z)
• 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)
• AstraNav-World: World Model for Foresight Control and Consistency [40.07910402326578]
  Embodied navigation in dynamic environments demands accurate foresight of how the world will evolve and how actions will unfold over time.<n>We propose AstraNav-World, an end-to-end world model that jointly reasons about future visual states and action sequences.<n>Our framework integrates a diffusion-based video generator with a vision-language policy, enabling synchronized rollouts.
  arXiv  Detail & Related papers  (2025-12-25T15:31:24Z)
• Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning [5.517595398768408]
  We present a unified aerial VLN framework that operates solely on ego monocular RGB observations and natural language instructions.<n>This task holds promise for real-world applications such as low-altitude inspection, search-and-rescue, and autonomous aerial delivery.
  arXiv  Detail & Related papers  (2025-12-09T14:25:24Z)
• Unified World Models: Memory-Augmented Planning and Foresight for Visual Navigation [69.94565127141483]
  Current approaches separate navigation planning from visual world modeling, leading to state-action misalignment and limited adaptability.<n>We propose UniWM, a unified, memory-augmented world model integrating egocentric visual foresight and planning within a single multimodal autoregressive backbone.<n>We show that UniWM substantially improves navigation success rates by up to 30%, significantly reduces trajectory errors compared to strong baselines, and exhibits impressive zero-shot generalization on the unseen TartanDrive dataset.
  arXiv  Detail & Related papers  (2025-10-09T18:18:11Z)
• 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)
• RSRNav: Reasoning Spatial Relationship for Image-Goal Navigation [57.197881161006904]
  Recent image-goal navigation (ImageNav) methods learn a perception-action policy by separately capturing semantic features of the goal and egocentric images.<n>We propose RSRNav, a simple yet effective method that reasons spatial relationships between the goal and current observations as navigation guidance.
  arXiv  Detail & Related papers  (2025-04-25T00:22:17Z)
• Ground-level Viewpoint Vision-and-Language Navigation in Continuous Environments [10.953629652228024]
  Vision-and-Language Navigation (VLN) agents associate time-sequenced visual observations with corresponding instructions to make decisions.<n>In this paper, we address the mismatch between human-centric instructions and quadruped robots with a low-height field of view.<n>We propose a Ground-level Viewpoint Navigation (GVNav) approach to mitigate this issue.
  arXiv  Detail & Related papers  (2025-02-26T10:30:40Z)
• Navigation World Models [68.58459393846461]
  We introduce a controllable video generation model that predicts future visual observations based on past observations and navigation actions.<n>In familiar environments, NWM can plan navigation trajectories by simulating them and evaluating whether they achieve the desired goal.<n>Experiments demonstrate its effectiveness in planning trajectories from scratch or by ranking trajectories sampled from an external policy.
  arXiv  Detail & Related papers  (2024-12-04T18:59:45Z)

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.