CST-WM: A Causally Structured World Model for Embodied Visual Tracking

• URL: http://arxiv.org/abs/2609.06302v1
• Date: Sat, 05 Sep 2026 23:24:32 GMT
• Title: CST-WM: A Causally Structured World Model for Embodied Visual Tracking
• Abstract summary: Embodied visual tracking requires a robot to choose actions that preserve or recover future evidence of a moving target.<n>CST-WM decomposes the latent state into target-evidence, robot, and observation branches.<n>It supports both stable following and temporary target re-acquisition in one planning framework.
• Score: 9.902564083063973
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Embodied visual tracking requires a robot not only to react to the current view, but to choose actions that preserve or recover future evidence of a moving target under ego-motion, occlusion, and distractors. It is therefore a predictive decision problem over future target observability and apparent scale. A central difficulty is a task-specific form of causal hallucination: in action-conditioned prediction, a model can exploit the strong correlation between robot control and target-related observations by hallucinating a direct causal effect from the current action to target evidence, rather than letting action influence that evidence only through robot motion and the resulting observation change. The shortcut yields plausible futures with the wrong semantics for tracking-oriented planning and re-acquisition. We propose CST-WM, a causally structured world model that decomposes the latent state into target-evidence, robot, and observation branches and factorizes the transition so that direct action injection into the target-evidence branch is blocked, while action remains available to robot motion and observation updates. Combined with rollout-based model-predictive control, CST-WM supports both stable following and temporary target re-acquisition in one planning framework. On EVT-Bench and Habitat 3.0, covering standard tracking, target-loss recovery, and cross-dataset transfer, it improves following quality, distance-range control, safety, and re-acquisition over reactive and world-model baselines; offline diagnostics show better multi-step rollout fidelity, stronger planning-value consistency, and substantially reduced direct action leakage. For embodied visual tracking, future prediction alone is not enough: the predictive structure itself must align with how target evidence enters planning.

Related papers

• World Models for Embodied Intelligence: From Plausible to Controllable to Actionable [100.13060753774657]
  World models connect perception and decision-making in embodied intelligence by maintaining hidden state, anticipating consequences, comparing interventions, and adapting when execution departs from expectations.<n>This raises a central question: which predictive capabilities improve behavior?<n>We introduce three progressively stronger capability levels: Plausible models preserve task-relevant temporal, geometric, or physical structure; Controllable models additionally predict how interventions alter that structure; and Actionable models translate predictions into measurable gains in planning, action, learning, evaluation, verification, recovery, or data selection.
  arXiv  Detail & Related papers  (2026-09-15T06:22:42Z)
• Towards Surgical World-Action Modeling: A Preliminary Joint Visual-Trajectory Forecasting for Surgical Motion Planning [37.17021354294023]
  We present a joint visual-trajectory world-action model that simultaneously forecasts future visual states and instrument trajectories from historical surgical observations.<n>We observe progressive visual degradation and accumulated trajectory errors over longer prediction horizons.
  arXiv  Detail & Related papers  (2026-08-20T17:18:02Z)
• Sensorimotor World Models: Perception for Action via Inverse Dynamics [59.121736411156384]
  We introduce a sensorimotor world model trained end-to-end with inverse dynamics regularization.<n>It prevents representation collapse and induces action-aligned representations.<n>It learns compact, interpretable latent spaces and enables competitive planning performance across simple 2D and 3D control tasks.
  arXiv  Detail & Related papers  (2026-06-18T11:25:16Z)
• JPPD: Joint Prediction_Planning Diffusion with Differentiable Safety Guidance for Dynamic Obstacle Avoidance in Intelligent Transportation Systems [1.9236465591431287]
  This paper presents a joint prediction-planning diffusion framework that treats participant prediction and robot planning as a single conditional trajectory generation problem.<n> Experiments in scenario-grounded simulation, naturalistic pedestrian replay, Isaac Sim validation, and ROS/Orin deployment show that joint sampling improves tail safety and runtime efficiency.
  arXiv  Detail & Related papers  (2026-06-14T11:15:44Z)
• 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)
• CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics [25.518388341069492]
  We propose CLaD, a framework that models how proprioceptive and semantic states jointly evolve under actions.<n>CLaD predicts grounded latent foresights via self-supervised objectives with EMA target encoders and auxiliary reconstruction losses.<n>On LIBERO-LONG benchmark, CLaD achieves 94.7% success rate, competitive with large VLAs with significantly fewer parameters.
  arXiv  Detail & Related papers  (2026-03-31T08:13:45Z)
• 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)
• See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation [59.07792608884117]
  We introduce See, Plan, Rewind (SPR), a progress-aware vision-language-action framework.<n>SPR operates through a continuous core cycle, Seeing the current state and upcoming milestone, Planning a trajectory towards the next 2D waypoint, and Rewinding to a recoverable state upon failure.<n>SPR achieves state-of-the-art robustness with the smallest performance drop, surpassing OpenVLA-OFT and UniVLA.
  arXiv  Detail & Related papers  (2026-03-10T07:22:51Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• 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)
• Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals [38.20643428486824]
  Learning the dense bird's eye view (BEV) motion flow in a self-supervised manner is an emerging research for robotics and autonomous driving. Current self-supervised methods mainly rely on point correspondences between point clouds. We introduce a novel cross-modality self-supervised training framework that effectively addresses these issues by leveraging multi-modality data.
  arXiv  Detail & Related papers  (2024-01-21T14:09:49Z)

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.