Leveraging Stereo-Camera Data for Real-Time Dynamic Obstacle Detection and Tracking

We are celebrating another success for our team in leading robotics research! Our latest contribution enables autonomous robots to safely navigate around pedestrians in crowded places. We are looking forward to the IEEE International Conference on Intelligent Robots and Systems (IROS2020) to present our work!

The paper titled “Leveraging Stereo-Camera Data for Real-Time Dynamic Obstacle Detection and Tracking” introduces a state-of-the-art system that can be used for accurate and reliable detection and tracking of pedestrians.

Thanks to the Autonomous Systems Lab at ETH Zürich for the collaboration and congratulations to the authors Thomas Eppenberger, Gianluca Cesari, Marcin Dymczyk, Roland Siegwart, and Renaud Dubé!

Find the paper here: https://arxiv.org/abs/2007.10743