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

Abstract

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 of the vehicle, the corresponding trajectory sets of horizontal 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 are used as the core indicators 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).INDEX TERMS autonomous vehicles (AVs), ice and snow covered road (ISCR), trajectory planning, cost evaluate function, simulation.

Intelligent Vehicle Path Based on Discretized Sampling Points and Improved Cost Function: A Quadratic Programming Approach

“…Vehicles must adhere to traffic regulations while traveling safely and smoothly along their planned route [33]. To achieve this, the process begins by discretizing all drivable positions into a set of sampling points.…”

Lane Change Trajectory Planning Based on Quadratic Programming in Rainy Weather

“…Here, t f represents the delayed reaction time, S d is the critical value of safe visual distance (m), S f stands for rainy weather visibility (m), and t r is the normal reaction time, v 0 denotes the initial vehicle speed, with a value of 1 s [19].…”

“…Li et al proposed a layered trajectory planning framework that combines sampling and numerical optimization. The upper-−level planner samples rough trajectories, while the lower−level planner refines trajectories using numerical optimization methods [19]. This approach formulates the trajectory generation problem as an optimal control problem, employing numerical optimization to solve multi−objective functions and obtain trajectories that are continuous, comfortable, and collision−free, while adhering to various constraints [20].…”