Joschka Boedecker

Correct Me if I am Wrong: Interactive Learning for Robotic Manipulation

2021 · arXiv (Cornell University)

Learning to solve complex manipulation tasks from visual observations is a dominant challenge for real-world robot learning. Although deep reinforcement learning algorithms have recently demonstrated impressive results in this context, they still require an impractical …

On the calibration of underrepresented classes in LiDAR-based semantic segmentation

2022 · arXiv (Cornell University)

The calibration of deep learning-based perception models plays a crucial role in their reliability. Our work focuses on a class-wise evaluation of several model's confidence performance for LiDAR-based semantic segmentation with the aim of providing …