We research how birds and robots can learn to solve complex kinematic problems. To this end, we are building kinematic puzzles, called lockboxes and observe how goffin cockatoos can learn to solve these. Together with colleagues from Oxford and Vienna (where the bird experiments happen), we analyze the problem solving and learning behavior of these birds and try to extract information that may prove to be useful for a robotic approach to similar problems.
The curious, but also food-directed behavior of cockatoos is recorded in experimental sessions with different lockboxes. We then code and analyze the videos to form hypotheses about mechanisms underlying the birds' behavior. These hypotheses are ultimately implemented in simulation or real robot experiments to test their predictive value for new, unseen kinematic puzzles that we provide to both, birds and artificial agents.
This project was seed funded and was a stepping stone to apply for funding for the project Intelligent Kinematic Problem solving.
This reserach project is funded by the OX/BER Research Partnership Seed Funding Fund under reference number OXBER_STEM3.