In the near future, coordinated autonomous vehicles will heavily impact the transportation of people and goods. The vehicles must communicate and cooperate with each other to perform efficiently, but pre-defined protocols must be agreed upon by all vehicles/companies. This work instead develops reinforcement learning (RL) algorithms, where simulated, heterogeneous agents explore possible communication and cooperation strategies to maximize the overall team performance.

Through this SuperUROP project, I want to gain more experience in robotics research and make a positive contribution to my lab. Robotics is a fascinating field to be in. Especially considering the potential it has to improve our lives, I’m excited to bring together ideas from the computer vision and graphics communities and learn more about the problems in this research domain.