Metraipolis › archive › dc_45bfe608dde1

What Do Latent Predictive Vehicle Representations Retain? Measuring State, Geometry, and Local Response — arXiv:2609.32512

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32512
License (as archived)
CC0-1.0
Archived
2026-10-07T22:36:39.588Z
SHA-256 of the archived text
0f686de8f511b587b0ffebef8be4e30036363c1437c8d47fe58b24c2ce87dc2b
Stable URL of this page
https://metraipolis.com/documento/dc_45bfe608dde1

How to cite

What Do Latent Predictive Vehicle Representations Retain? Measuring State, Geometry, and Local Response — arXiv:2609.32512 — arXiv (en), https://arxiv.org/abs/2609.32512 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45bfe608dde1 (Metraipolis archive dc_45bfe608dde1, sha256 0f686de8f511b587b0ffebef8be4e30036363c1437c8d47fe58b24c2ce87dc2b)
BibTeX
@misc{dc45bfe608dde1,
  title = {What Do Latent Predictive Vehicle Representations Retain? Measuring State, Geometry, and Local Response — arXiv:2609.32512},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32512},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45bfe608dde1; sha256 0f686de8f511b587b0ffebef8be4e30036363c1437c8d47fe58b24c2ce87dc2b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32512. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Models of vehicle dynamics learned from logged states and commands complement physics-based models, and latent world models, which predict in a learned representation, are used to plan and train controllers in other domains. Vehicle controllers are usually specified in physical terms: costs, limits, and references depend on position, yaw angle, speed, and yaw rate, and the optimizer compares or differentiates predicted outcomes across nearby commands. A latent model placed in such a controller must therefore let these quantities be recovered and must change its predictions with commands as the vehicle does, and prediction error on its own latent targets measures neither. We contribute a measurement protocol for action-conditioned latent predictors with a physical readout that separately tests retention, physical-neighborhood organization, forecasting, and local response to command perturbations, using an untrained-encoder reference and three matched response paths that locate errors in the representation or the predictor. In a case study of a temporal joint-embedding predictive model trained on signals logged in IPG CarMaker, the representations retain the measured planar outputs, though an untrained encoder of the same architecture retains them slightly better; future-command input improves one-second forecasts with retention nearly unchanged; and responses to small command pulses diverge from the simulator already in latent coordinates, raising regret when choosing among nearby commands in all comparisons. Updating the predictor on responses corrects them locally at a cost in forecast accuracy. Measuring retention, forecasting, and local response separately is thus what qualifies a predictive latent as a candidate model for control, and the protocol provides the basis for its closed-loop evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.32512 — 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 2026-10-07T22:14:27.707Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).