Visual scene understanding for indoor mobile robots (with the use case of trash picking)

Supervisor: Mark Adamik (, Ilaria Tiddi (


Pollution is one of the greatest challenges of our time. It is however a task that is both unpleasant and potentially dangerous for humans to perform (especially when the waste is contaminated), therefore an automated robotic solution is highly desired. A solution could be using a mobile robot equipped with a manipulator and to integrate knowledge representation and reasoning methods over the potential categories of trash, for example:


In this project, you will be using the LoCoBot, a mobile robot equipped with multiple sensors and a manipulator. Your task would be to integrate object recognition methods (e.g. YOLO) and knowledge representation & reasoning methods to solve pick and place problems representing trash collection.


  1. A literature review on the state-of-the-art methods integrating knowledge representation and reasoning with mobile robotics
  2. Familiarizing with the LoCoBot platform and ROS.
  3. Build a knowledge graph depending on the chosen use-case (trash picking is optional)
  4. Developing an integrated robot control system that is able to recognize and reason over objects.


Supervision will be by Mark Adamik and Ilaria Tiddi.