Izvorni znanstveni članak
https://doi.org/10.7307/ptt.v36i4.528
Obstacle Avoidance Path Planning Strategy for Autonomous Vehicles Based on Genetic Algorithm
Xiaofeng WENG
; Shanghai University of Engineering Science
Fei LIU
; Shanghai University of Engineering Science
Sheng ZHOU
; Shanghai University of Engineering Science
Jiacheng MAI
; Shanghai University of Engineering Science
Shaoxiang FENG
; Shanghai University of Engineering Science
Sažetak
In order to enhance the driving ability of autonomous vehicles on structured roads and enable them to plan safe and comfortable paths, we propose an obstacle avoidance path strategy for autonomous vehicles based on genetic algorithm. The use of Frenet-Serret enhances the adaptability of the algorithm in complex environments. In order to improve the generation and optimisation of obstacle avoidance trajectory, we establish an anti-collision model. When the vehicle faces a potential collision with an obstacle, the genetic algorithm quickly iterates and selects the first nine genes to generate the rough solution and convex space of the path. Combined with convex space, the quadratic programming method will numerically optimise the generated rough solution to generate an accurate path that satisfies the constraints. In addition, in order to ensure the safety and comfort in the process of obstacle avoidance, based on the dynamic constraints of the vehicle, the speed planning is used to determine the speed curve. We simulate in various scenarios involving moving obstacles. The real-time simulation based on the HIL platform proves that the proposed path planning strategy is effective in various driving scenarios.
Ključne riječi
autonomous vehicle; genetic algorithm; anti-collision model; path planning; sequential quadratic programming (SQP)
Hrčak ID:
320281
URI
Datum izdavanja:
27.8.2024.
Posjeta: 148 *