RETRACTED: Improvement in Collision Avoidance in Cut-In Maneuvers Using Time-to-Collision Metrics

Abstract

Highlights: The study is focused on studying human driving behavior under uncertainty to transfer these behaviors to autonomous vehicles (AVs) represents a pivotal step toward improving the coexistence of human-driven and autonomous vehicles in mixed traffic environments. What are the main findings? The proposed collision avoidance system significantly improves collision avoidance performance in cut-in scenarios by integrating deep learning with time-to-collision (TTC) metrics. The Gaussian model enhances TTC analysis by providing a probabilistic framework that accounts for real-world uncertainties, such as sensor inaccuracies, vehicle velocity fluctuations, and unpredictable driving behavior. What is the implication of the main finding? The integration of deep learning and TTC metrics enables adaptive, real-time decision-making for collision avoidance in autonomous vehicles, improving safety in dynamic environments. The probabilistic Gaussian approach makes TTC-based systems more robust, allowing them to better handle uncertainties, leading to safer and more reliable autonomous driving systems. This paper proposes a new strategy for a collision avoidance system leveraging time-to-collision (TTC) metrics for handling cut-in scenarios, which are particularly challenging for autonomous vehicles (AVs). By integrating deep learning with TTC calculations, the system predicts potential collisions and determines appropriate evasive actions compared to traditional TTC-based approaches. The methodology is validated through extensive simulations, demonstrating a significant improvement in collision avoidance performance compared to traditional TTC-based approaches. By integrating deep learning models with TTC calculations, the system predicts potential collisions and determines appropriate evasive actions. The use of the Gaussian model to contributes to time-to-collision (TTC) analysis by providing a probabilistic framework to quantify collision risk under uncertainty. It calculates the likelihood that TTC will fall below a critical threshold (TTC_crit), indicating a potential collision. By modeling input variations—such as sensor inaccuracies, fluctuating vehicle velocity, and unpredictable driving behavior—as a Gaussian distribution, the system can handle real-world uncertainties more effectively. This enables continuous, real-time risk prediction, allowing for dynamic and adaptive collision avoidance decisions. The Gaussian approach enhances the robustness of TTC-based systems by improving their ability to predict and prevent collisions in uncertain driving conditions.