ISY researchers from the Telecooperation Lab presented their work at IROS 2024, held from October 14-18 in Abu Dhabi, UAE, one of the leading robotics conferences worldwide, focusing on innovations for sustainable development. The paper introduces a new approach for unsupervised domain adaptation for LiDAR semantic segmentation, which is a crucial perception task in robotics. The preprint is available here.

Citation information:

Thomas Kreutz, Jens Lemke, Max Mühlhäuser, and Alejandro Sanchez Guinea. 2024. LiOn-XA: Unsupervised Domain Adaptation via LiDAR-Only Cross-Modal Adversarial Training. 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) [to appear].