"A car-like indoor mobile robot is a kinematically constrained robot that can be modeled as a 2D object translating and rotating in the horizontal plane among well- defined obstacles. The kinematic constraints impose that the linear velocity of the robot is along its main axis (no sideways motion is possible) and restrict the range of admissible values for the steering angle. The goal of this study is to combine neural network techniques and motion planning algorithms to create a new methodology for coordinating the motion of multiple car-like robots avoiding collision with polygonal obstacles in a work environment. An incremental technique is used to develop this methodology. First, a strategy for planning the path of a point robot moving in the presence of obstacles is constructed. Second, this strategy is adapted to path planning for a polygonal robot. Third, holonomic and non-holonomic constraints are imposed on the robot and the method is further refined. Finally, a plan for the coordinated motion of multiple car-like robots is devised through use of the concept of coordination space"--Abstract, page iii.
Liou, Frank W.
Dagli, Cihan H., 1949-
Mechanical and Aerospace Engineering
M.S. in Mechanical Engineering
University of Missouri--Rolla
vii, 56 pages
© 2000 Prasanna Venkatesan Sadagopan, All rights reserved.
Thesis - Restricted Access
Print OCLC #
Electronic OCLC #
Link to Catalog Record
Electronic access to the full-text of this document is restricted to Missouri S&T users. Otherwise, request this publication directly from Missouri S&T Library or contact your local library.http://laurel.lso.missouri.edu/record=b4443455~S5
Sadagopan, Prasanna Venkatesan, "A neural network methodology for path planning and coordination of car-like robots" (2000). Masters Theses. 4401.
Share My Thesis If you are the author of this work and would like to grant permission to make it openly accessible to all, please click the button above.