摘要详情

ID / 提交时间

204 / 2023-10-20 23:08:20

标题

The improved neural network algorithm is applied in the obstacle avoidance path planning of driverless vehicles

关键字

unmanned driving; route exploration; neural network algorithm; particle swarm algorithm

主题及专题

6.AI-driven technology > (3)、Advanced sensing and intelligent computation

状态

终稿

作者

Xiying Zhang / Qingdao University of Science and Technology

Shuyu An / Qingdao University of Science & Technology

Jingshuai Li / Qingdao University of Science & Technology

Jiachang Li / Qingdao University of Science & Technology

Xiaowen Li / Qingdao University of Science & Technology

Hongfeng Wang / Qingdao University of Science & Technology

摘要

The intelligent transportation system is gradually rising, and the driverless vehicle technology plays an important role in the development of the intelligent transportation system, whose core is the obstacle avoidance path planning. Bardless obstacle avoidance path planning is to explore the effective obstacle avoidance path from the starting point to the end point to achieve the optimal or approximate optimal value. Based to the shortcomings of traditional neural network algorithm based on the combination of neural network and particle swarm algorithm. The neural network is used to determine the relationship between moving point and obstacle; then the particle swarm algorithm is used to search the optimal value and optimize the generated path. Finally, the improved neural network algorithm is simulated on the MATLAB platform to verify that the improved algorithm can generate the global optimal path and realize the dynamic obstacle avoidance.