Improvement of Collision Avoidance in Cut-In Maneuvers Using Time-to-Collision Metrics
This addresses safety challenges in autonomous driving for cut-in scenarios, but appears incremental as it builds on existing TTC approaches.
The paper tackles the problem of collision avoidance in cut-in maneuvers for autonomous vehicles by proposing a new strategy that integrates deep learning with Time-to-Collision metrics, resulting in improved prediction and evasive actions compared to traditional methods.
This paper proposes a new strategy for collision avoidance system leveraging Time-to-Collision (TTC) metrics for handling cut-in scenarios, which are particularly challenging for autonomous vehicles (AVs). By integrating a deep learning with TTC calculations, the system predicts potential collisions and determines appropriate evasive actions compared to traditional TTC -based approaches.