RoboDrive Competition (ICRA 2024)

Feb 2024 - Apr 2024

  • Participated in the RoboDrive Challenge, focusing on robust multi-modal BEV 3D object detection, using corrupted camera and LiDAR data from the NuScenes dataset.
  • Achieved 4th place with scores of 42.8 (NDS) and 26.4 (mAP), showcasing the ability of our model to handle camera and LiDAR corruptions.
  • Got invited to present at ICRA 2024 conference, highlighting our innovative approach inspired by FUTR3D, utilizing an architecture similar to BEVFusion.