Tarhini, Fadel (University of Technology of Compiegne), TALJ, Reine (Université de Technologie de Compiègne, Heudiasyc), Doumiati, Moustapha (IREENA LAB UR4642)

Hybrid Energy-Efficient Local Path Planning for Autonomous Vehicles in Dynamic Environments

Scheduled for presentation during the Regular Session "Trajectory planning II" (ThAT9), Thursday, September 26, 2024, 11:10−11:30, Salon 17

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 3, 2024

Abstract

Efficient trajectory planning plays a crucial role in the development of autonomous vehicles, ensuring safe and optimized navigation in dynamic environments. This paper proposes a novel energy-efficient hybrid trajectory planning by integrating a sampling-based method with an optimization-based path refining method. It uses the strength of the sampling-based methods to reduce the solution space and generate a reactive trajectory in a dynamic environment. Following path selection, a septic path is generated and utilized as a reference for an energy-efficient path-refining optimization problem, producing a jerk-controlled trajectory with enhanced computational efficiency. The simulations were conducted in a joint-simulation environment using Simulink/Matlab and the Scaner Studio vehicle dynamics and driving environment simulator. The findings demonstrate the effectiveness of our approach in achieving significant energy savings while adeptly addressing dynamically changing environments.