Investigating Classic and Biologically Inspired Vision Systems for Mobile Robots

Vision can serve many purposes when employed on a mobile robot. In order to explore the capabilities of a visually guided mobile robot, an existing robot kit used in the Intelligent Autonomous Robotics course at the University of Edinburgh was enhanced through the addition of a webcam. An API was then created for controlling the webcam within the development platform used by the robot kit. The API was used to implement two initial vision-based behaviours on a mobile robot. The first was a colour target tracking behaviour that was found to perform significantly better than a blind robot in locating coloured balls. The second was a deformable line following behaviour that extracted the line information using a classic method. The initial scope of the project proposal was then extended by implementing two more behaviours. The third behaviour relied on a biologically inspired learning technique that enabled a mobile robot to learn to follow a line using only a small amount of visual data. Finally, the same learning algorithm was combined with classic line detection so as to enable the robot to avoid obstacles. Computational efficiency and working in the face of general hardware limitations were of primary importance throughout, often requiring novel solutions to problems.