The PRISMA Lab is looking for students interested in the use of deep learning, imitation learning, model predictive control and full body control techniques to train a humanoid robot in the various Olympic disciplines, starting from the queen discipline of all the Olympics: the 100m race.
The activities can be either on a voluntary basis, by participating in a working group that will be specially trained (UNINA Robotic Olympic Team), or developed through regular thesis activities. The training of the robot will include both the perceptive and cognitive aspects (for example the recognition of the lines on the track, the finish line, the obstacles, the presence of other robot athletes, etc.) and the kinematic and dynamic aspects of the humanoid robotic platform (starting from blocks, running in dynamic equilibrium, kinematic and dynamic constraints, etc.). The software platform used for training will be the NVIDIA ISAAC GYM, while the robot used will be the UNITREE H1 model.
Contact person: Prof. Vincenzo Lippiello (This email address is being protected from spambots. You need JavaScript enabled to view it.)
