Congratulations! Mr. Seungbin Kim’s paper is accepted to IEEE Transactions on Circuits and Systems I (T-CAS I)!

We propose a real-time and energy-efficient heterogeneous LOAM processor for efficient LiDAR odometry and mapping under massive keypoint-matching and heterogeneous NLO workloads.

The processor employs 3D spherical-bin partitioning and neighboring-bin search, hash-page-based memory management with neighboring-bin caching, and a reconfigurable NLO core for efficient LOAM acceleration.

The processor achieves up to 135 FPS and 0.81 mJ/frame, with 99.6% fewer kNN comparisons, 10.5× higher kNN energy efficiency, and 92.3% lower NLO latency.