An efficient autonomous vehicle navigation scheme based on LiDAR sensor in vehicular network

Recently, autonomous vehicles navigation (AVN) attracted many researches trying to improve road traffic without the human intervention. One of the main challenges in AVN is allowing a vehicle to discover its moving trajectory with a reduced computational complexity. To cope with this issue, we propose in this paper a new simulated annealing algorithm to discover an optimal trajectory when the vehicle encounters an obstacle using LiDAR perception. The found trajectory is then sent to a roadside unit (RSU), which communicates this discovery to other nodes in the network for further use. During its navigation, the vehicle perceives the environment by a LiDAR sensor to detect an eventual obstacle and launches an optimal path discovery to reach the final destination in a reduced time. The results obtained showed the effectiveness of our proposal to find an optimal route compared to Dijkstra algorithm.