New classifier identifies four distinct urban vehicle deceleration behaviors

Researchers have developed a new classifier to identify distinct modes of urban vehicle deceleration behavior. By analyzing over a thousand deceleration events from the Argoverse 2 dataset, they identified four stable modes: anticipatory soft, reactive closing, brake-like jerk, and an outlier category. A classifier using early kinematic data achieved a macro-F1 score of 0.758, with scene context providing a marginal improvement. AI

RANK_REASON The cluster contains a research paper detailing a new classifier for urban vehicle deceleration behavior. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• Argoverse 2
• Urban Deceleration Behavior Modes Under Scene Context: An Early-Kinematic Classifier from Argoverse 2 Multi-Agent Trajectories

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →