Processing range data for autonomous vehicle navigation

This project is basically to continue the research that has been done by last year FYP students. The idea of this project is to investigate the possibilities of a driverless vehicle, in this case is Segbot (Robotic version of the Segway RMP). Segbot is a two-wheeled robot, using the same principle o...

Full description

Bibliographic Details
Main Author: Wijaya, Andrew.
Other Authors: Martin David Adams
Format: Final Year Project (FYP)
Language:English
Published: 2010
Subjects:
Online Access:http://hdl.handle.net/10356/40752
Description
Summary:This project is basically to continue the research that has been done by last year FYP students. The idea of this project is to investigate the possibilities of a driverless vehicle, in this case is Segbot (Robotic version of the Segway RMP). Segbot is a two-wheeled robot, using the same principle of segway to balance itself. By connected to rangefinder sensor, Segbot is supposed to map surrounding area, do path planning and obstacle avoidance. Currently there are many types of path planning algorithm. The very first real time obstacle avoidance method is Potential Field Method, which then improved results in Certainty Grids Method, followed by Vector Force Field and lastly, Vector Polar Histogram. This report will discuss in VPH+ method, which is more efficient in complicated environment. This new method permits the detection of unknown obstacles and avoids collisions in real time while simultaneously steering the mobile robot toward the target. A brief introduction of laser measurement system will be covered in this report. Some simulations and real implementation data will be compared and elaborated further.