Policy-Guided World Model Planning for Language-Conditioned Visual Navigation

• URL: http://arxiv.org/abs/2603.25981v1
• Date: Thu, 26 Mar 2026 23:47:49 GMT
• Title: Policy-Guided World Model Planning for Language-Conditioned Visual Navigation
• Abstract summary: We present PiJEPA, a two-stage framework that combines the strengths of learned navigation policies with latent world model planning for instruction-conditioned visual navigation.<n> Experiments on real-world navigation tasks demonstrate that PiJEPA significantly outperforms both standalone policy execution and uninformed world model planning.
• Score: 12.836371451772438
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Navigating to a visually specified goal given natural language instructions remains a fundamental challenge in embodied AI. Existing approaches either rely on reactive policies that struggle with long-horizon planning, or employ world models that suffer from poor action initialization in high-dimensional spaces. We present PiJEPA, a two-stage framework that combines the strengths of learned navigation policies with latent world model planning for instruction-conditioned visual navigation. In the first stage, we finetune an Octo-based generalist policy, augmented with a frozen pretrained vision encoder (DINOv2 or V-JEPA-2), on the CAST navigation dataset to produce an informed action distribution conditioned on the current observation and language instruction. In the second stage, we use this policy-derived distribution to warm-start Model Predictive Path Integral (MPPI) planning over a separately trained JEPA world model, which predicts future latent states in the embedding space of the same frozen encoder. By initializing the MPPI sampling distribution from the policy prior rather than from an uninformed Gaussian, our planner converges faster to high-quality action sequences that reach the goal. We systematically study the effect of the vision encoder backbone, comparing DINOv2 and V-JEPA-2, across both the policy and world model components. Experiments on real-world navigation tasks demonstrate that PiJEPA significantly outperforms both standalone policy execution and uninformed world model planning, achieving improved goal-reaching accuracy and instruction-following fidelity.

Related papers

• WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving [8.510409798128272]
  We present WA-JEPA, a VEPA-native world-action model for autonomous driving planning.<n>WA-JEPA employs hybrid future-masked pre-training, where the model infers future latents from observed context.<n>Results: WA-JEPA reaches 91.7S on NAVSIM, surpassing the strongest end-to-end and world-action baselines.
  arXiv  Detail & Related papers  (2026-08-21T10:54:35Z)
• Lifting Embodied World Models for Planning and Control [59.09016913513998]
  We train a lightweight policy that maps high-level actions to sequences of low-level joint actions.<n>We instantiate this framework for a human-like embodiment, defining the high-level action space as a small set of 2D waypoints.<n>We show that the lifted world model substantially outperforms searching directly in low-level joint space.
  arXiv  Detail & Related papers  (2026-04-28T23:59:19Z)
• ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving [19.081114003415863]
  We propose a unified understanding-and-generation framework to enable meaningful exploration and provide dense supervision.<n>We augment trajectory prediction with future RGB and depth image generation as dense world modeling objectives.<n>We incorporate this exploration signal into a safety-gated reward and optimize the policy.
  arXiv  Detail & Related papers  (2026-04-03T04:14:13Z)
• Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving [52.04950569530877]
  We present Uni-World VLA, a unified vision-language-action model that tightly interleaves future frame prediction and trajectory planning.<n>Our approach achieves competitive closed-loop planning performance while producing high-fidelity future frame predictions.
  arXiv  Detail & Related papers  (2026-03-28T14:39:51Z)
• ETP-R1: Evolving Topological Planning with Reinforcement Fine-tuning for Vision-Language Navigation in Continuous Environments [24.809501651450223]
  Vision-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to navigate towards target in continuous environments.<n>Current graph-based methods offer an efficient, structured approach by abstracting the environment into a topological map and simplifying the action space to waypoint selection.<n>We introduce ETP-R1, a framework that applies the paradigm of scaling up data and Reinforcement Fine-Tuning (RFT) to a graph-based VLN-CE model.
  arXiv  Detail & Related papers  (2025-12-24T04:53:03Z)
• NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction [12.352236127154761]
  We introduce NavForesee, a novel Vision-Language Model (VLM) that unifies high-level language planning and predictive world model imagination.<n>Our approach empowers a single VLM to concurrently perform planning and predictive foresight.<n>Our work highlights the immense potential of fusing explicit language planning with implicittemporal prediction, paving the way for more intelligent and capable embodied agents.
  arXiv  Detail & Related papers  (2025-12-01T11:24:16Z)
• From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction [57.56072009935036]
  We introduce a new driving paradigm named Policy World Model (PWM)<n>PWM integrates world modeling and trajectory planning within a unified architecture.<n>Our method matches or exceeds state-of-the-art approaches that rely on multi-view and multi-modal inputs.
  arXiv  Detail & Related papers  (2025-10-22T14:57:51Z)
• GoViG: Goal-Conditioned Visual Navigation Instruction Generation [69.79110149746506]
  We introduce Goal-Conditioned Visual Navigation Instruction Generation (GoViG), a new task that aims to autonomously generate precise and contextually coherent navigation instructions.<n>GoViG exclusively leverages raw egocentric visual data, substantially improving its adaptability to unseen and unstructured environments.
  arXiv  Detail & Related papers  (2025-08-13T07:05:17Z)
• DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation [73.80968452950854]
  Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces.<n>Existing VLN-CE approaches typically use a two-stage waypoint planning framework.<n>We propose DAgger Diffusion Navigation (DifNav) as an end-to-end optimized VLN-CE policy.
  arXiv  Detail & Related papers  (2025-08-13T02:51:43Z)
• LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation [45.02469804709771]
  We propose LaDi-WM, a world model that predicts the latent space of future states using diffusion modeling.<n>We show that LaDi-WM significantly enhances policy performance by 27.9% on the LIBERO-LONG benchmark and 20% on the real-world scenario.
  arXiv  Detail & Related papers  (2025-05-13T04:42:14Z)
• Imagine-2-Drive: Leveraging High-Fidelity World Models via Multi-Modal Diffusion Policies [9.639797094021988]
  World Model-based Reinforcement Learning (WMRL) enables sample efficient policy learning.<n>We propose Imagine-2-Drive, a novel WMRL framework that integrates a high-fidelity world model with a multi-modal diffusion-based policy actor.<n>By training DPA within DiffDreamer, our method enables robust policy learning with minimal online interactions.
  arXiv  Detail & Related papers  (2024-11-15T13:17:54Z)
• Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors [124.30562402952319]
  The ability to predict and plan into the future is fundamental for agents acting in the world. Current learning approaches for visual prediction and planning fail on long-horizon tasks. We propose a framework for visual prediction and planning that is able to overcome both of these limitations.
  arXiv  Detail & Related papers  (2020-06-23T17:58:56Z)

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.