Reinforcement Learning algorithms benchmark for Next-Best-View Estimation for Active Object Classification

Freitag, 24. Juni 2022

In this project, we tackle the problem of the next-best-view to classify occluded and self-occluded objects. We benchmark multiple Deep Reinforcement Learning algorithms to determine the most promising method and visualize the training process.

Studenten:

• Nada Beili

• Christian Korbach