EUVIMEDEUVIMED entdecken
Crossref

MAGIC VFM-Meta-Learning Adaptation for Ground Interaction Control with Visual Foundation Models (Abstract Reprint)

Elena-Sorina Lupu, Fengze Xie, James Preiss, Jedidiah Alindogan, Matthew Anderson, Soon-Jo Chung

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 39877-39877

DOI: 10.1609/aaai.v40i47.41392 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Elena-Sorina Lupu und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Control of off-road vehicles is challenging due to the complex dynamic interactions with the terrain. Accurate modeling of these interactions is important to optimize driving performance, but the relevant physical phenomena, such as slip, are too complex to model from first principles. Therefore, we present an offline meta-learning algorithm to construct a rapidly-tunable model of residual dynamics and disturbances. Our model processes terrain images into features using a visual foundation model (VFM), then maps these features and the vehicle state to an estimate of the current actuation matrix using a deep neural network (DNN). We then combine this model with composite adaptive control to modify the last layer of the DNN in real time, accounting for the remaining terrain interactions not captured during offline training. We provide mathematical guarantees of stability and robustness for our controller, and demonstrate the effectiveness of our method through simulations and hardware experiments with a tracked vehicle and a car-like robot. We evaluate our method outdoors on different slopes with varying slippage and actuator degradation disturbances, and compare against an adaptive controller that does not use the VFM terrain features. We show significant improvement over the baseline in both hardware experimentation and simulation.

Zitieren

APA

Lupu, E., Xie, F., Preiss, J., Alindogan, J., Anderson, M., & Chung, S. (2026). MAGIC VFM-Meta-Learning Adaptation for Ground Interaction Control with Visual Foundation Models (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 39877-39877. https://doi.org/10.1609/aaai.v40i47.41392

Vancouver

Lupu E, Xie F, Preiss J, Alindogan J, Anderson M, Chung S. MAGIC VFM-Meta-Learning Adaptation for Ground Interaction Control with Visual Foundation Models (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):39877-39877. doi:10.1609/aaai.v40i47.41392

BibTeX
@article{Lupu2026,
  author = {Lupu, Elena-Sorina and Xie, Fengze and Preiss, James and Alindogan, Jedidiah and Anderson, Matthew and Chung, Soon-Jo},
  title = {MAGIC VFM-Meta-Learning Adaptation for Ground Interaction Control with Visual Foundation Models (Abstract Reprint)},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {47},
  pages = {39877--39877},
  doi = {10.1609/aaai.v40i47.41392}
}
Kostenlos starten →