An Efficient Neural-Dynamics-Based Technique for Real-Time Map Building and Vehicle Motion Planning

He, Fan, and Chaomin Luo

Path planning is an essential issue for intelligent vehicles and many other robotic applications.  When vehicles work in unknown environments, map building is required for the vehicles to effectively search the workspace. Real-time concurrent map building and path planning are desirable for efficient performance in many applications. In this project, a novel neural-dynamics-based model is proposed for real-time map building and path planning of autonomous vehicles in a completely unknown environment. The proposed model is compared with an existing neural networks path planning method. The proposed method does not need any templates, even in unknown environments.  A local map composed of square cells is created through the neural dynamics during the path planning with limited sensory information. From the measured sensory information, a map of the robot’s immediate limited surroundings is dynamically built for the vehicle navigation.

Comparison studies of the proposed approach with the neural networks path planning approach show that the proposed method is capable of planning more reasonable and shorter collision-free paths in unknown environments. The work to implement this model on an actual mobile robot is on-going.