Akihito Hiromori

Papers

Total Citations

H-Index

About

Akihito Hiromori is a leading researcher in spatial computing and indoor mapping, with a focus on developing robust algorithms for autonomous navigation and environmental reconstruction. His most-cited work, "Indoor Map Generation from Multiple LIDAR Point Clouds" (2018, 9 citations), addresses a critical challenge in mobile robotics: creating accurate indoor maps from noisy, multi-sensor LIDAR data. Hiromori advanced the iterative closest point (ICP) algorithm, a cornerstone of simultaneous localization and mapping (SLAM), by integrating point clouds from multiple 2D LIDAR scanners to improve map consistency and reduce drift. This contribution directly supports applications in warehouse automation, disaster response, and smart building management. Beyond this paper, his research spans sensor fusion, 3D modeling, and real-time localization systems, with ongoing work exploring scalable mapping for dynamic environments. Hiromori’s impact is evident in the growing adoption of his methods in both academic SLAM benchmarks and commercial robotic platforms. His achievements include collaborations with industry partners to deploy indoor mapping solutions in real-world settings, bridging the gap between theoretical algorithms and practical deployment. For students and researchers, Hiromori’s work exemplifies how incremental algorithmic refinements can yield transformative gains in autonomous systems.