Foresight: Iterative Reasoning About Clues that Matter for Navigation

• URL: http://arxiv.org/abs/2606.12550v1
• Date: Wed, 10 Jun 2026 18:01:06 GMT
• Title: Foresight: Iterative Reasoning About Clues that Matter for Navigation
• Abstract summary: Mapless navigation requires resolving underspecified goals and inferring which environmental cues are relevant for reaching the goal.<n>Prior works are limited by their reliance on known navigation factors and closed-set factor categories, or identify cues before motion planning and miss plan-dependent cues.<n>We argue that pretrained Vision-Language Models (VLMs) can discover novel instruction-relevant cues, but require adaptation to focus on which cues matter and how they should influence motion planning.<n>We realize these ideas in Foresight, a test-time framework in which a finetuned VLM alternates between proposing image-space motion plans and critiquing
• Score: 20.227441986534767
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Open-world mapless navigation from sparse language instructions requires resolving underspecified goals and inferring which environmental cues are relevant for reaching the goal. For instance, reaching an out-of-view destination may require interpreting ramps, signs, or detours that reveal where to go or which route to take. Prior works are limited by their reliance on known navigation factors and closed-set factor categories, or identify cues before motion planning and miss plan-dependent cues. We argue that pretrained Vision-Language Models (VLMs) can discover novel instruction-relevant cues, but require adaptation to focus on which cues matter and how they should influence motion planning. We realize these ideas in Foresight, a test-time framework in which a finetuned VLM alternates between proposing image-space motion plans and critiquing them using the language goal and visual context. Subsequent plans are conditioned on prior critiques, enabling iterative motion refinement before execution. To align plan critiques and refinements with open-set behavior preferences, we learn a reward model from human feedback and use it to post-train the VLM with reinforcement learning in the plan-critique loop. In offline evaluations and 6 real-world environments, Foresight improves average task success by 37% and reduces interventions per mission by 52% relative to state-of-the-art test-time reasoning and foundation-model baselines, while running in real-time on a Jetson AGX Orin. We will release code, data, and training details to support future work on test-time reasoning for robot motion refinement. Additional videos at: https://amrl.cs.utexas.edu/foresight

Related papers

• AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation [78.80536515102305]
  Vision-and-Language Navigation (VLN) requires an agent to ground language instructions to its own movement within a visual environment.<n>We propose AwareVLN, a novel framework that equips the navigation model with a self-aware reasoning mechanism.<n>Our approach features two key innovations: (1) a structural reasoning module that fosters spatial and task-oriented self-awareness, and (2) an automatic data engine with progress division for effective training.
  arXiv  Detail & Related papers  (2026-05-21T17:58:26Z)
• 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)
• AsgardBench -- Evaluating Visually Grounded Interactive Planning Under Minimal Feedback [28.254110943200683]
  AsgardBench aims to evaluate visually grounded, high-level action sequence generation and interactive planning.<n>Our evaluations show that performance drops sharply without visual input, revealing weaknesses in visual grounding and state tracking.<n>Our benchmark zeroes in on a narrower question: can a model actually use what it sees to adapt a plan when things do not go as expected?
  arXiv  Detail & Related papers  (2026-03-16T20:31:43Z)
• To Move or Not to Move: Constraint-based Planning Enables Zero-Shot Generalization for Interactive Navigation [14.745622942938532]
  In real-world scenarios, such as home environments and warehouses, clutter can block all routes.<n>We introduce the Lifelong Interactive Navigation problem, where a mobile robot can move clutter to forge its own path.<n>We propose an LLM-driven, constraint-based planning framework with active perception.
  arXiv  Detail & Related papers  (2026-02-23T17:10:00Z)
• DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigation [17.00613677919529]
  Vision-and-Language Navigation in Continuous Environments (VLN-CE) links language instructions to perception and control in the real world.<n>We present DreamNav, which focuses on three aspects: (1) for reducing sensory cost, our EgoView Corrector aligns viewpoints and stabilizes egocentric perception; (2) instead of point-level actions, our Trajectory Predictor favors global trajectory-level planning to better align with instruction semantics; and (3) to enable anticipatory and long-horizon planning, we propose an Imagination Predictor to endow the agent with proactive thinking capability.
  arXiv  Detail & Related papers  (2025-09-14T09:54:20Z)
• VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs [102.36953558562436]
  Vision language models (VLMs) are an exciting emerging class of language models (LMs) One understudied capability inVLMs is visual spatial planning. Our study introduces a benchmark that evaluates the spatial planning capability in these models in general.
  arXiv  Detail & Related papers  (2024-07-02T00:24:01Z)
• 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)
• SOON: Scenario Oriented Object Navigation with Graph-based Exploration [102.74649829684617]
  The ability to navigate like a human towards a language-guided target from anywhere in a 3D embodied environment is one of the 'holy grail' goals of intelligent robots. Most visual navigation benchmarks focus on navigating toward a target from a fixed starting point, guided by an elaborate set of instructions that depicts step-by-step. This approach deviates from real-world problems in which human-only describes what the object and its surrounding look like and asks the robot to start navigation from anywhere.
  arXiv  Detail & Related papers  (2021-03-31T15:01:04Z)
• Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction [57.56466850377598]
  Reasoning over visual data is a desirable capability for robotics and vision-based applications. In this paper, we present a framework on graph to uncover relationships in different objects in the scene for reasoning about pedestrian intent. Pedestrian intent, defined as the future action of crossing or not-crossing the street, is a very crucial piece of information for autonomous vehicles.
  arXiv  Detail & Related papers  (2020-02-20T18:50:44Z)

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.