Gas source localization via behaviour based robot and weighted arithmetic mean

This research is concerned with the localization of gas source in a dynamic indoor environment problem using a single mobile robot system. Since the environment is unknown to the robot, an intelligent algorithm is required to enable the robot to traverse through the environment without any interrup...

全面介绍

Saved in:
书目详细资料
格式: Thesis
语言:English
主题:
在线阅读:http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/78216/1/Page%201-24.pdf
http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/78216/2/Full%20text.pdf
http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/78216/4/Ahmad%20Shakaff.pdf
标签: 添加标签
没有标签, 成为第一个标记此记录!
实物特征
总结:This research is concerned with the localization of gas source in a dynamic indoor environment problem using a single mobile robot system. Since the environment is unknown to the robot, an intelligent algorithm is required to enable the robot to traverse through the environment without any interruption from obstacles. All experiments were done on an experimental testbed consisting of a large gas sensor array (LGSA) to monitor real-time gas concentration within the testbed. The measurements from the LGSA were taken as the ground truth and were useful as it can be compared to the measurements taken from the gas sensors on the mobile robot. A pattern tracking system was also utilized to record the robot's odometry. Initially, two preliminary experiments were conducted to better understand the conditions within the experimental testbed and the gas sensor's performance within the environment when the robot is moving at different speeds. From the preliminary experiments, we can confirm that the conditions within the testbed are indeed dynamic and gas sensor's performance differs when the mobile robot is moving at different speeds. We then proceed to implement two algorithms (i.e Zig-Zag and Braitenberg) to test the robot's performance in traversing through the experimental testbed while taking gas sensor measurements. The Braitenberg algorithm was separated into two variants (i.e Repel and Attract) which then were implemented with the mobile robot.