Dynamic Trajectory Planning and Optimization for Automated Driving on Ice and Snow Covered Road

The rapid development of 5G and Artificial Intelligence (AI) has promoted the widespread application of autonomous driving in various scenarios. Currently, autonomous vehicles (AVs) can autonomously perform operations such as turning, lane changing, and acceleration in accordance with road traffic rules. It is a challenge for autonomous vehicles (AVs) to plan a series of safe and efficient trajectories on ice and snow covered road (ISCR). This paper proposes an optimal trajectory planning algorithm based on the Frenet coordinate system, which ignores the influence of road curvature and improves the quality of trajectory. Specifically, the vehicle motion is decoupled into two dimensions using the Frenet coordinate system to build lateral and longitudinal trajectory planning models, respectively. Further, according to the information on the initial and target configuration, the corresponding trajectory sets of lateral and longitudinal motion were generated by sampling. Moreover, to improve the safety of autonomous vehicles (AVs) on ice and snow covered road (ISCR), the cost of driving distance and ice-obstacle distance is used as the core indicator to evaluate the trajectory planning cost, combined with the safe speed check. Simulation results show that this algorithm can plan an optimal trajectory for autonomous vehicles (AVs) that combines safety, comfort, and stability, especially on ice and snow covered road (ISCR).