Real-Time Vehicle Navigation Based on an Efficient Fuzzy Logic Model

Bian,Yue, Chaomin Luo, Mohan Krishnan, and Mark Paulik

Path planning is an essential issue for intelligent vehicles and many other robotic applications.  Real-time path planning is desirable for efficient performance in many applications. In this project, a novel fuzzy-logic-based model is proposed for real-time path planning of autonomous vehicles in unknown environments. The proposed model is compared with several existing path planning methodologies. The proposed method does not need any templates, even in unknown environments.  Environmental information of the real-world gathered by IR and ultrasonic sensors is transmitted to the fuzzy logic based coordination system. Simulation results validate how a fuzzy logic system directs an intelligent mobile robot to perform point-to-point navigation with obstacle avoidance.  Comparison studies of the proposed approach with the navigation models by neural networks and genetic algorithms show that the proposed method is capable of planning more reasonable and shorter collision-free paths.