New conference contribution at the "International Conference on Control, Mechatronics and Automation (ICCMA)" 2023

The article titled "Height Change Feature Based Free Space Detection" by Steven Schreck, Hannes Reichert, Manuel Hetzel, Konrad Doll and Bernhard Sick presents a novel method for detecting free spaces in dynamic environments such as factory floors, which is crucial for autonomous forklifts to avoid collisions. A technique for fast estimation of surface normals using spherically projected LiDAR data is presented, which helps in efficient detection of clearances in real time. The effectiveness of the method is demonstrated with an mIoU value of 50.90% on the Semantic KITTI dataset at 105 Hz and an mIoU value of 63.30% on a factory site dataset at 54 Hz.