20 International Journal of Intelligent Mechatronics and Robotics, 1(1), 20-39, January-March 2011
Copyright © 2011, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global
is prohibited.
Keywords: Analogy Systems, Cellular Neural Network, Collision Avoidance, Dynamic Environments,
Robot Path Planning
INTRODUCTION
Real-time collision-free motion planning in
a non-stationary environment is an important
and challenging issue in many autonomous
systems including robotics and intelligent
systems. It provides intelligent robotic systems
with an ability to plan motions and to navigate
autonomously. This ability becomes critical
particularly for robots which operate in dynamic
environments, where unpredictable and sud-
den changes may occur. Whenever the robot’s
Optimal Robot Path Planning
with Cellular Neural Network
Yongmin Zhongm, Curtin University of Technology,Australia
Bijan Shirinzadeh, Monash University, Australia
Xiaobu Yuan, University of Windsor, Canada
ABSTRACT
This paper presents a new methodology based on neural dynamics for optimal robot path planning by drawing
an analogy between cellular neural network (CNN) and path planning of mobile robots. The target activity is
treated as an energy source injected into the neural system and is propagated through the local connectivity of
cells in the state space by neural dynamics. By formulating the local connectivity of cells as the local interac-
tion of harmonic functions, an improved CNN model is established to propagate the target activity within the
state space in the manner of physical heat conduction, which guarantees that the target and obstacles remain
at the peak and the bottom of the activity landscape of the neural network. The proposed methodology cannot
only generate real-time, smooth, optimal, and collision-free paths without any prior knowledge of the dynamic
environment, but it can also easily respond to the real-time changes in dynamic environments. Further, the
proposed methodology is parameter-independent and has an appropriate physical meaning.
sensory system detects a dynamic change, its
planning system has to adapt and modify its
paths accordingly. Prominent examples include
real world environments that involve interac-
tion with people, such as museums, shops, and
households.
Based on the analogy between cellular
neural network (CNN) and robot path plan-
ning, this paper presents a new neural dynamics
based methodology for optimal collision-free
robot path generation in an arbitrarily vary-
ing environment. The real-time collision-free
robot trajectory is formulated as the dynamic
CNN activity. The target activity is treated
as an energy source injected into the neural
DOI: 10.4018/ijimr.2011010102