Metraipolis › archive › dc_dcc2aad1bceb
CST-WM: A Causally Structured World Model for Embodied Visual Tracking — arXiv:2609.06302
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06302
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:06:59.915Z
- SHA-256 of the archived text
ced5bb1467ff59c684e25d61aa4ca442c8dc53ba86600178e6d03feb62d45611- Stable URL of this page
https://metraipolis.com/documento/dc_dcc2aad1bceb
How to cite
CST-WM: A Causally Structured World Model for Embodied Visual Tracking — arXiv:2609.06302 — arXiv (en), https://arxiv.org/abs/2609.06302 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcc2aad1bceb (Metraipolis archive dc_dcc2aad1bceb, sha256 ced5bb1467ff59c684e25d61aa4ca442c8dc53ba86600178e6d03feb62d45611)
BibTeX
@misc{dcdcc2aad1bceb,
title = {CST-WM: A Causally Structured World Model for Embodied Visual Tracking — arXiv:2609.06302},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06302},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcc2aad1bceb; sha256 ced5bb1467ff59c684e25d61aa4ca442c8dc53ba86600178e6d03feb62d45611},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06302. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Embodied visual tracking requires a robot to choose actions that keep a moving target observable at a suitable distance, and to recover it after occlusion, out-of-view drift, or distractor crossings. We cast the task as planning over future target evidence with an action-conditioned world model. In logged tracking data, however, the behavior policy's actions are correlated with where the target is, so a generic predictor can learn a shortcut: it writes the current action directly into its prediction of target evidence, instead of letting the action affect that evidence only by moving the robot and changing what it observes. We call this failure causal hallucination; the resulting rollouts look plausible but rank candidate actions for the wrong reason. We propose CST-WM, a causally structured world model whose state is split into target-evidence, robot, and observation branches. Its transition removes the same-step edge from action to target evidence but keeps the path through robot motion and the resulting views, so candidate actions are still distinguished by their predicted ego-motion. With rollout-based model-predictive control, a single model handles both steady following and re-acquisition after target loss. On EVT-Bench and Habitat 3.0, covering standard tracking, target-loss recovery, and cross-dataset transfer, CST-WM improves following, distance-range control, safety, and re-acquisition over reactive trackers and world-model baselines, and removing the action mask causes the largest drop in re-acquisition among our ablations. Offline, CST-WM has lower multi-step rollout error, and its ranking of candidate actions agrees better with the simulator's. On a Unitree Go2 quadruped, CST-WM succeeds in 20 of 30 real-world trials under occlusion, distractor crossing, and fast motion, against 14 for TrackVLA. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.06302 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T14:49:57.070Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).