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

arXiv: https://arxiv.org/abs/2607.00027 · HTML: https://mlsanity.com/paper/2607.00027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 63 references that are in the map.
- First posted on arXiv 21 Jun 2026.

## Builds on (most cited first, 7 of 7)

- [Trust, but Verify: Cross-Modality Fusion for HD Map Change Detection](https://mlsanity.com/paper/2212.07312/) (2022)
- [FollowNet: A Comprehensive Benchmark for Car-Following Behavior Modeling](https://mlsanity.com/paper/2306.05381/) (2023)
- [Clustering of Driving Encounter Scenarios Using Connected Vehicle Trajectories](https://mlsanity.com/paper/1807.08415/) (2018)
- [Elementary proofs of several results on false discovery rate](https://mlsanity.com/paper/2201.09350/) (2022)
- [Exploring the stimulative effect on following drivers in a consecutive lane-change using microscopic vehicle trajectory data](https://mlsanity.com/paper/2205.11252/) (2022)
- [On the maximum of Cramer's V](https://mlsanity.com/paper/2501.12411/) (2025)
- [Kinematic Discriminants of Deceleration Behavior Modes in Car-Following: Evidence from NGSIM Trajectory Data](https://mlsanity.com/paper/2605.05050/) (2026)

## Abstract (arXiv)

Urban deceleration is one of the most empirically studied yet least taxonomically organized behaviors in car-following research. Recent perception-equipped autonomous-vehicle datasets enable trajectory-anchored mode discovery. We extract 1,219 sustained deceleration events from 234 urban driving logs of the Argoverse 2 Sensor dataset, encode each event in a 19-dimensional kinematic feature vector, discover behavioral modes via K-means clustering with bootstrap stability analysis, and quantify modulation by eleven scene-context variables. A HistGradientBoosting classifier predicts mode membership from the first 1.0 s of each event. Four stable modes emerge with a bootstrap Adjusted Rand Index of 0.897 across 50 resamples: anticipatory soft (62.8%), reactive closing (30.6%), brake-like jerk (4.8%), and an outlier category (1.8%). Only pair age shows a medium effect (epsilon^2 = 0.085); scene geometry and vulnerable-road-user proximity show negligible effects. The early-event classifier achieves macro-F1 = 0.758 at 1.0 s, with scene context contributing +0.059 F1 over kinematics alone. Modes are regime-invariant in medium-speed driving (ARI = 0.817) but regime-dependent at low speed (ARI = 0.166). A small set of stable kinematic modes structures urban deceleration; early-window jerk dominates predictive signal; and pair age is the primary contextual modulator.