2020/05/05 by N. Herald Anantha Rufus, Unni Krishnan R Nair, Rufus, Nivedita +7 · 1 citation
Engineering · Environmental Science · #FOS: Computer and information sciences #Infrastructure Maintenance and Monitoring #Remote Sensing and LiDAR Applications #Robotics (cs.RO) #Robotics and Sensor-Based Localization
paper · pdf · doi:10.48550/arxiv.2005.02042
openalex publication_date 2020/05/05 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
In this paper, we present SROM, a novel real-time Simultaneous Localization\nand Mapping (SLAM) system for autonomous vehicles. The keynote of the paper\nshowcases SROM's ability to maintain localization at low sampling rates or at\nhigh linear or angular velocities where most popular LiDAR based localization\napproaches get degraded fast. We also demonstrate SROM to be computationally\nefficient and capable of handling high-speed maneuvers. It also achieves low\ndrifts without the need for any other sensors like IMU and/or GPS. Our method\nhas a two-layer structure wherein first, an approximate estimate of the\nrotation angle and translation parameters are calculated using a Phase Only\nCorrelation (POC) method. Next, we use this estimate as an initialization for a\npoint-to-plane ICP algorithm to obtain fine matching and registration. Another\nkey feature of the proposed algorithm is the removal of dynamic objects before\nmatching the scans. This improves the performance of our system as the dynamic\nobjects can corrupt the matching scheme and derail localization. Our SLAM\nsystem can build reliable maps at the same time generating high-quality\nodometry. We exhaustively evaluated the proposed method in many challenging\nhighways/country/urban sequences from the KITTI dataset and the results\ndemonstrate better accuracy in comparisons to other state-of-the-art methods\nwith reduced computational expense aiding in real-time realizations. We have\nalso integrated our SROM system with our in-house autonomous vehicle and\ncompared it with the state-of-the-art methods like LOAM and LeGO-LOAM.\n