International Journal of Electronics, Communication &
Instrumentation Engineering Research and
Development (IJECIERD)
ISSN 2249-684X
Vol.2, Issue 2 June 2012 19-29
© TJPRC Pvt. Ltd.,
AN EFFICIENT ARCHITECTURE FOR ROBOTIC PATH PLANNING
M.VIJAY
1
& M.JAGADEESWARI
2
1
P.G. Scholar
2
Professor & Head Dept. of VLSI DESIGN,
1,2
sri Ramakrishna Engineering College
coimbatore-641022 Tamilnadu, India
ABSTRACT
There are many path planning algorithms designed for mobile robots with software implementation.
In the case of dynamic environments high-speed planning and recomputation of paths is necessary to
avoid collision of robots with moving objects. A hardware-efficient algorithm is presented for finding a
path of a mobile robot on image of an environment captured by an overhead camera. The algorithm
computes the shortest path to identify collision free region for the robot. If multiple paths are provided,
the path is traced to nearest path. 2-D cell architecture has been presented for the Euclidean distance
Transform (EDT) and Nearest Neighbor Transform (NNT) for operating at high speed. The simulation
result shows that the architecture is suitable for path planning in a dynamic environment containing
obstacles with arbitrary shape and motion.
KEYWORDS: Euclidean distance transform (EDT), Nearest Neighbor Transform (NNT), image, path
planning, dynamic environment.
INTRODUCTION
The development of robots that are able to assist humans in their day-to-day tasks has become a
popular research area over the last few years [6], [11]. Mobile manipulator systems public service robots
(PSRs1 and 2) perform delivery, patrol, and floor-cleaning jobs [8]. The guide robot provides exhibition
guide services at a museum. These robots are equipped with a few laser range finders (LRFs) for
localization and obstacle detection. The PSR1 and PSR2 are driven by active caster-typed holonomic
omni directional wheels. The guide robot uses conventional two-wheel differential-type wheels.
Basically, these robots share common control architecture. Some software components were partially
modified according to the target robot system.. The control architecture design, navigation system, and
behavior selection framework were proposed in [16] for each robot. The focus on the localization
problem whose solution will enable robots to carry out dependable navigation in dynamic indoor
environments depends upon algorithm. Localization as in [16] is one of the most important issues for
successful autonomous navigation, and a great number of localization methods have been proposed so
far.
Many studies have addressed about position tracking problems. According to the International
Federation of Robotics (IFR), ‘‘a service robot is a robot which operates semi or fully autonomously to
perform services useful to the well being of human and equipment, excluding manufacturing operations’’
[6]. These devices are typically complex systems requiring the input of knowledge from numerous