AI & ML
Controllable Generative Trajectory Prediction via Weak Preference Alignment
arXiv cs.RO0 views
arXiv:2510.10731v2 Announce Type: replace Abstract: Deep generative models such as conditional variational autoencoders (CVAEs) have shown great promise for predicting trajectories of surrounding agents in autonomous vehicle planning. State-of-the-art models have achieved remarkable accuracy in such prediction tasks. Besides accuracy, diversity is also crucial for safe planning because human behaviors are inherently uncertain and multimodal. However, existing methods generally lack a scheme to generate controllably diverse trajectories, which is arguably more useful than randomly diversified trajectories, to the end of safe planning. To address this, we propose PrefCVAE, an augmented CVAE framework that uses weakly labeled preference pairs to imbue latent variables with semantic attributes. Using average velocity as an example attribute, we demonstrate that PrefCVAE enables controllable, semantically meaningful predictions without degrading baseline accuracy. Our results show the effectiveness of preference supervision as a cost-effective way to enhance sampling-based generative models.
Source:https://arxiv.org/abs/2510.10731PreviousGalilean Symmetry in RoboticsNextIllumination-Robust Localization around Unknown Space Objects using Multispectral Image Fusion
Related posts
PhantaField Projects $0.42/M Output Tokens in Orbit with White Matter and Sophon
0Hacker News New
New Study Shows How Young People Feel About AI Companions
0Hacker News New
Hackers Hijack Websites of CNN, BBC and Major Banks
0Hacker News New
PaloAlto Networks buys AppliedCompute founded last yr by 3 OpenAI alums for 4.5B
0Hacker News New
New models tested: Gemini 4 Hydrogen, Qwen4-Max, and GPT-6.2
0Hacker News New
Fable: Written, painted and directed by Claude Fable 5.2
0Hacker News New