Optimized velocity planning for autonomous vehicles using tree-based sampling and cost constraints

Abstract

Velocity planning is a crucial component of trajectory planning in autonomous driving. The complexity of urban open road environments and the uncertainty of traffic participants’ behavior place higher demands on velocity planning. Currently, velocity planning still faces issues of heavy reliance on computational resources and poor perceived planning speed. This study proposes a velocity planner that meets the requirements of both high efficiency and high planning comfort by optimizing the search structure and evaluation function. Firstly, the driving capability boundaries are determined based on the vehicle’s dynamic performance, and these boundaries are used as the growth space for the improved RRT* algorithm during the search process, where ineffective nodes are pruned to enhance efficiency and address the computational resource consumption in high-dimensional velocity planning. Secondly, smooth constraints are introduced in the optimization process through quadratic programming to address the discontinuity or non-smoothness of speed and acceleration caused by discretization, ensuring that the generated velocity trajectory is smoother and more continuous. Finally, a nonlinear optimization of the quadratic programming results is conducted to reduce the impact of centripetal acceleration on the vehicle, ensuring the efficient output of a continuous and comfortable velocity trajectory. Simulation results indicate that, compared to the EM-Planner velocity planning scheme, the proposed scheme has significant advantages in terms of planning time and jerk, enhancing planning efficiency and comfort. The feasibility of the proposed scheme in real scenarios is verified through experiments.