AI RESEARCH
Physics-Guided Temporal Fusion for Lane-Change Intention Prediction
arXiv CS.LG
•
ArXi:2512.24075v4 Announce Type: replace Lane-change intention prediction is safety-critical for autonomous driving and ADAS, but remains difficult in naturalistic traffic due to noisy kinematics, severe class imbalance, and limited generalization across heterogeneous highway scenarios. We propose Temporal Physics-Informed AI (TPI-AI), a hybrid framework that fuses deep temporal representations with physics-inspired interaction cues.