An Efficient Neural Network Model for Path Planning of Car-like Robots in Dynamic Environment
Simon X. Yang* and Max Meng**
*Advanced Robotics & Intelligent Systems (ARIS) Group School of Engineering, University of Guelph Guelph, Ontario, Canada, NlG 2W1
**Advanced Robotics and Teleoperation (ART) Lab Department of Electrical and Computer Engineering, University of Alberta Edmonton, Alberta, Canada, T6G 2G7
In this paper, an effcient neural network approach to real-time path planning with obstacle avoidance of holonomic car-like robots in a dynamic environment is proposed. The dynamics of each neuron in this biologically inspired, topologically organized neural network is characterized by a shunting equation or an additive equation. The state space of the neural network is the configuration space of the robot. There are only local lateral connections among neurons. Thus the computational complexity linearly depends on the neural network size. The real-time collision-free path is planned through the dynamic neural activity landscape of the neural network without explicitly searching over neither the free workspace nor the collision paths, without any prior knowledge of the dynamic environment, without any learning procedures, and without any local collision checking procedures at each step of the robot movement. Therefore it is computationally efficient. The stability of the neural network is proven by both qualitative analysis and the Lyapunov stability theory. The effectiveness and efficiency are demonstrated through simulation studies.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 International License.