LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning

• URL: http://arxiv.org/abs/2603.29165v1
• Date: Tue, 31 Mar 2026 02:21:59 GMT
• Title: LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning
• Abstract summary: 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.
• Score: 51.969318585152116
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Existing vision-and-language navigation (VLN) models primarily reason over past and current visual observations, while largely ignoring the future visual dynamics induced by actions. As a result, they often lack an effective understanding of the causal relationship between actions and how the visual world changes, limiting robust decision-making. Humans, in contrast, can imagine the near future by leveraging action-dynamics causality, which improves both environmental understanding and navigation choices. Inspired by this capability, we propose LatentPilot, a new paradigm that exploits future observations during training as a valuable data source to learn action-conditioned visual dynamics, while requiring no access to future frames at inference. Concretely, 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, with an expert takeover triggered when the agent deviates excessively. LatentPilot further learns visual latent tokens without explicit supervision; these latent tokens attend globally in a continuous latent space and are carried across steps, serving as both the current output and the next input, thereby enabling the agent to dream ahead and reason about how actions will affect subsequent observations. 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. Project page:https://abdd.top/latentpilot/

Related papers

• Towards Generalizable Visually Grounded Exploration of Household Devices [74.66117923766632]
  Key bottleneck of realizing general autonomous embodied agents lies in Generalizable Visually Grounded Exploration.<n>We introduce VGEBench, a benchmark designed to evaluate the generalizable visually grounded exploration capabilities of Vision-Language Models.<n>Unlike static datasets, we construct a Logic-Driven State Machine framework. This framework simulates multi-turn interaction loops, compelling agents to achieve goals by active visual perception and feedback-driven correction.
  arXiv  Detail & Related papers  (2026-09-01T07:42:45Z)
• Predicting Consequences and Reinforcing Navigation Policies with Latent World Models [31.865100130203317]
  We propose a compatibility prediction Latent World Model (LWM) for robot navigation.<n>Our key insight is that spatial proximity correlates with latent feature similarity, enabling action consequences to be evaluated directly in latent space.<n>Our approach significantly outperforms prior world model and imitation learning methods in prediction accuracy, policy learning, and real-world navigation performance.
  arXiv  Detail & Related papers  (2026-08-23T11:58:42Z)
• From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation [88.39072412680633]
  We propose MoLA, a control-oriented interface that transforms imagined future videos into executable representations.<n>We evaluate our approach on simulated benchmarks and real-world robot manipulation tasks.
  arXiv  Detail & Related papers  (2026-05-12T14:15:16Z)
• Being-H0.7: A Latent World-Action Model from Egocentric Videos [32.77431338471086]
  We present Being-H0.7, a latent world-action model that brings future-aware reasoning into VLA-style policies.<n>Being-H0.7 inserts learnable latent queries between perception and action as a compact reasoning interface.
  arXiv  Detail & Related papers  (2026-04-30T14:16:15Z)
• FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model [73.03346643967309]
  We argue that effective joint visuomotor predictive modeling requires both temporal continuity and visually-conditioned supervision decoupling.<n>FutureVLA is designed to extract joint visuomotor embeddings by first decoupling visual and motor information.<n>In the post-training stage, we employ a latent embeddings alignment strategy, enabling diverse downstream VLA models to internalize these temporal priors.
  arXiv  Detail & Related papers  (2026-03-11T12:39:55Z)
• ViThinker: Active Vision-Language Reasoning via Dynamic Perceptual Querying [15.728211622542267]
  ViThinker is a framework that enables vision-language models to autonomously generate decision tokens triggering the synthesis of expert-aligned visual features on demand.<n>ViThinker internalizes vision-expert capabilities during training, performing generative mental simulation during inference without external tool calls.
  arXiv  Detail & Related papers  (2026-02-02T22:29:57Z)
• \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)
• Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control [51.14656121641822]
  World models enable robots to "imagine" future observations given current observations and planned actions.<n>Novel visual distractors can corrupt action outcome predictions, causing downstream failures when robots rely on the world model imaginations for planning or action verification.<n>We propose Reimagination with Observation Intervention (ReOI), a simple yet effective test-time strategy that enables world models to predict more reliable action outcomes.
  arXiv  Detail & Related papers  (2025-06-19T19:41:29Z)
• TRACE: A Self-Improving Framework for Robot Behavior Forecasting with Vision-Language Models [1.3408365072149797]
  Predicting the near-term behavior of a reactive agent is crucial in many robotic scenarios.<n>We present TRACE, an inference framework that couples tree-of-thought generation with domain-aware feedback.<n>We validate TRACE on both ground-vehicle simulations and real-world marine autonomous surface vehicles.
  arXiv  Detail & Related papers  (2025-03-02T06:58:02Z)
• FIMP: Future Interaction Modeling for Multi-Agent Motion Prediction [18.10147252674138]
  We propose Future Interaction modeling for Motion Prediction (FIMP), which captures potential future interactions in an end-to-end manner. Experiments show that our future interaction modeling improves the performance remarkably, leading to superior performance on the Argoverse motion forecasting benchmark.
  arXiv  Detail & Related papers  (2024-01-29T14:41:55Z)
• Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams [64.82800502603138]
  This paper proposes a novel neural-network-based approach to progressively and autonomously develop pixel-wise representations in a video stream. The proposed method is based on a human-like attention mechanism that allows the agent to learn by observing what is moving in the attended locations. Our experiments leverage 3D virtual environments and they show that the proposed agents can learn to distinguish objects just by observing the video stream.
  arXiv  Detail & Related papers  (2022-04-26T09:52:31Z)
• Knowledge Distillation for Action Anticipation via Label Smoothing [21.457069042129138]
  Human capability to anticipate near future from visual observations and non-verbal cues is essential for developing intelligent systems. We implement a multi-modal framework based on long short-term memory (LSTM) networks to summarize past observations and make predictions at different time steps. Experiments show that label smoothing systematically improves performance of state-of-the-art models for action anticipation.
  arXiv  Detail & Related papers  (2020-04-16T15:38:53Z)
• Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling [65.99956848461915]
  Vision-and-Language Navigation (VLN) is a task where agents must decide how to move through a 3D environment to reach a goal.<n>One of the problems of the VLN task is data scarcity since it is difficult to collect enough navigation paths with human-annotated instructions for interactive environments.<n>We propose an adversarial-driven counterfactual reasoning model that can consider effective conditions instead of low-quality augmented data.
  arXiv  Detail & Related papers  (2019-11-17T18:02:51Z)

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.