"This thesis presents an effective approach to study tactile based mobile robot navigation. A Matlab simulator, which can simulate the properties of the tactile sensors, the environment, and the motion of the robot, is developed. The simulator uses an abstraction model of a compliant tactile sensor to represent an array of sensors covering the robot. The tactile sensor can detect normal and shear forces. The simulator has been used by a set of human subjects to drive a robot in an indoor environment to capture data. The details of the implementation and the data collected are presented in this thesis. From the data, some contact features can be extracted. Regarding the features, this thesis uses the Gaussian classifier and Gaussian mixture model to classify the data and build the feature classification model. Comparing the classification results of these two methods, the Gaussian mixture model has better performance. Applying the feature classification model, some contact objects can be detected, such as wall and corner. Based on this classification tool, a simple navigation problem can be solved successfully."
| Identifer | oai:union.ndltd.org:wpi.edu/oai:digitalcommons.wpi.edu:etd-theses-1890 |
| Date | 13 June 2013 |
| Creators | Long, Xianchao |
| Contributors | Taskin Padir, Committee Member, Eduardo Torres-Jara, Advisor, Michael A. Gennert, Committee Member |
| Publisher | Digital WPI |
| Source Sets | Worcester Polytechnic Institute |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | Masters Theses (All Theses, All Years) |
Page generated in 0.0015 seconds