KISS-IMU: Self-supervised Inertial Odometry with Motion-balanced Learning and Uncertainty-aware Inference
Best Paper on Robot Perception Finalist
IEEE International Conference on Robotics and Automation (ICRA 2026)I'm an integrated M.S.โPh.D. student in the Department of Electrical and Computer Engineering at Inha University, advised by Younggun Cho in SPARO Lab. I also received my B.S. in Electrical Engineering from Inha University. During my M.S., I worked on learning-based state estimation, focusing on self-supervised inertial odometry, and I'm now working on proprioceptive state estimation โ explicitly modeling and correcting environment-induced error in proprioceptive odometry from inertial, kinematic, and contact signals alone. For my personal thoughts and research experiences, please check out my :)
Best Paper on Robot Perception Finalist
IEEE International Conference on Robotics and Automation (ICRA 2026)
No matching publications.
Best Paper on Robot Perception Finalist
IEEE International Conference on Robotics and Automation (ICRA 2026)
Coming Soon..๐ฅฒ
Ray-cast two real LiDAR sweeps, pick edge and planar features by curvature, and watch a Gauss-Newton solver recover the relative pose the way LOAM and LIO-SAM do.
Open labDrive a GO2 quadruped and watch stance-foot contact and leg kinematics fuse with an IMU into a body-velocity estimate.
Open simulatorNo posts in this category yet.