The paper introduces a layered evaluation protocol for generative scenario models used in autonomous driving, focusing on physical consistency and plausibility. It examines internal representations through kinematic alignment, statistical baseline comparison, latent controllability, and activation analysis, and then tests outputs against vehicle dynamics constraints such as lateral jerk thresholds. The protocol is applied to a VAE-based scenario generator and other generative models, revealing deeper insights than standard output-level metrics.
By Manasa Mariam Mammen, Zafer Kayatas, Stefan Wagner
The paper introduces Structured Phase Space GAN (SPS‑GAN), a conditional generative model that learns structured dynamics from Cartesian trajectories and video. SPS‑GAN integrates a port‑Hamiltonian backbone with adversarial conditional generation, enabling representation of conservative, dissipative, and forced systems within a single architecture. Using a cyclic‑coordinate loss, the model recovers system degrees of freedom and canonical coordinates from raw observations, achieving better trajectory accuracy than supervised dynamics baselines and improved video consistency over generative baselines while consistently identifying correct latent mechanical coordinates.
By Yulong Yang, Jiayin Liu, Vineet Bansal, Christine Allen-Blanchette
arXiv:2607. 11497v1 Announce Type: cross Abstract: Existing generative models learn data distributions in flat Euclidean space.
By Ying Yan, Liwei Hu, Xiaoming Zhang
arXiv:2607. 07763v1 Announce Type: new Abstract: World models are typically trained to predict discrete-time physical dynamics with a fixed step size baked into the model weights, preventing prediction at variable temporal resolutions.
By Eli Laird, Corey Clark
arXiv:2505.15863v2 Announce Type: replace-cross
Abstract: Generative AI (GenAI) is rapidly advancing the field of Autonomous Driving (AD), extending beyond traditional applications in text, image, an...
By Katharina Winter, Abhishek Vivekanandan, Rupert Polley, Yinzhe Shen, Christian Schlauch, Mohamed-Khalil Bouzidi, Bojan Derajic, Natalie Grabowsky, Annajoyce Mariani, Dennis Rochau, Giovanni Lucente, Harsh Yadav, Firas Mualla, Adam Molin, Sebastian Bernhard, Christian Wirth, \"Omer \c{S}ahin Ta\c{s}, Nadja Klein, Fabian B. Flohr, Hanno Gottschalk
arXiv:2606. 11277v1 Announce Type: new Abstract: Reliable extrapolation remains a central challenge for generative models in computational physics, because models trained over finite ranges of time, parameters, or geometries may produce physically inconsistent predictions outside the training distribution.
By Zhongxin Yang, Yuanwei Bin, Xiang I. A. Yang, Shiyi Chen