Physics-constrained model improves vehicle platoon stability prediction
SSP-DMGTimeNet: Physics-Constrained Learning for Spatiotemporal Trajectory Prediction of Vehicle Platoons
Artificial Intelligence
Summary
Predicting how cars follow each other is tricky because small disturbances can grow and cause traffic issues. The authors designed a new model that not only predicts each car’s path but also respects how delays and disturbances realistically spread along a line of cars. By including physical rules about these disturbances, their model better avoids unrealistic traffic waves while maintaining good prediction accuracy. Tests show it works well on several real traffic datasets and keeps the whole group of vehicles more stable.
What this means in practice
- •For automotive engineers: Improve adaptive cruise control systems by predicting stable vehicle following patterns that realistically model disturbance propagation.
- •For traffic simulation teams: Create more realistic simulations of vehicle platoons by incorporating physically consistent disturbance propagation in trajectory predictions.
Authors
Yuhang Wang, Kailang Ma, Zirui Li, Mingfeng Fan, Kitae Jang, Changju Lee, Heye Huang
Abstract
Existing car-following prediction methods mainly optimize trajectory accuracy, while rarely considering whether predicted disturbances propagate realistically along a vehicle platoon. This limitation may lead to accurate but string-unstable predictions. We propose SSP-DMGTimeNet, a physics-constrained learning framework for spatiotemporal trajectory prediction of vehicle platoons. The model combines multi-scale temporal representations with cross-vehicle interaction features to capture complex and time-varying platoon dynamics. A propagation-delay-aware causal attention mechanism explicitly models upstream-to-downstream disturbance propagation by learning response delays between adjacent vehicles and accumulating them along the platoon. In addition, time- and frequency-domain string-stability losses relieve disturbance amplification across both adjacent vehicles and arbitrary sub-platoons during training. Experiments on HighD show that SSP-DMGTimeNet achieves an unstable-window rate of 0.65\% for five-vehicle platoons and a maximum head-to-tail amplification of 0.898 on the ground-truth excitation subset, while maintaining competitive trajectory prediction performance. In zero-shot evaluation on NGSIM US-101 and I-80, the model achieves velocity MAEs of 1.316~m/s and 1.252~m/s, with unstable-window rates of 3.90\% and 4.10\%, respectively. These results demonstrate that incorporating platoon-level physical constraints can effectively balance trajectory prediction accuracy and disturbance propagation stability.