10-04-2017, 07:53 PM
The use of robots for every day use is becoming increasingly common. For this reason is important to develop an interface capable at the same time to be able to control the robot efficiently and to be user friendly. For example when the user wants to instruct the robot to turn right, there are many actions to be performed by the robot in order to turn correctly and yet the user may not be aware of all of them. The aim of this project is to allow any user to instruct a robot perform human-like actions without having to worry about the low-level procedures involved. In this project a real robot will be used with the aim to navigate in a closed environment (like our Department). The robot is equipped with one sensor only: a webcam. In other words, the only source of information are the images from the webcam. You will focus on processing the images in order to obtain the necessary information (i.e. detecting obstacles such as walls,etc) to successfully control the robot movements. After that you may also focus on developing a high-level procedure (such as turn or follow the corridor, etc) based on your image analysis results using pre-existing low-level procedures.
Any help.