Welcome to my portfolio site. Feel free the take a look around.

Predator Robot

Robotics March 2015

This application was created as part of my assessment material for the Computer Vision and Robotics module undertaken during year 4 of my Masters of Computing degree with The University of Lincoln. If you wish to obtain a copy of the application or a copy of any documentation then please contact me using the features available on this website.

The aim of the assignment was to create either a predator and pray robot using the TurtleBot 2 available at the university. I decided to implement the predator robot, as this seemed like more fun. Regardless of which robot you decided to make, each one had to contain at least the following 3 modules. Firstly, object detection. Object detection is vital as this module will allow the robot to navigate through its environment without crashing in objects such as chairs, tables and walls. In addition, its also a critical safety feature allowing the robot to stop if someone were to move into its path. Object detection is also vital for locating the other robot, therefore allowing this robot to charge in its direction. The second module that had to be included is obstacle avoidance. As described previously, the robot needs to be able to detect objects, however methods of avoiding those objects is a difficult problem. When faced with an object, do you go around or turn away and go in another direction? In either case, which side do you turn to, what direction? There are so many different scenarios that accounting for all of them is very difficult. Lastly there was player behaviour component. This is the specific logic programming for the role the robot will play. In this case, its a predator component, which will include chasing towards its target when its spotted.

This project was extremely interesting and really fun to be apart of. From my experience robotics seems to combine the challenging, interesting computer vision problems with real world movement and actions. This in turn provides lots of interesting areas for investigation and progress when trying to develop a system such as this.

This content has been taken from the assessment documentation created as part of this module.

 

This was part of my Computer Vision and Robotics module for year 4 for my Masters of Computing (MCOMP) degree with The University of Lincoln. If you would like a copy any documentation (including the corresponding report), then please contact me using the facilities on this website.

Browse portfolio

Client

  • The University of Lincoln