Success at IROS 2022 and ICRA 2023
The STAR Center has published a total of 13 papers at the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) and the 2023 IEEE International Conference on Robotics and Automation (ICRA). The MARS Lab has one paper with the title "Multical: Spatiotemporal Calibration for Multiple IMUs, Cameras and LiDARs" at IROS 2022. It presents a new approach to calibrate multiple heterogenious sensors.
Multical setup and 3D point cloud.
SLAM Hive System overview.
Our ICRA 2023 papers are "The SLAM Hive Benchmarking Suite" and "FloorplanNet: Learning Topometric Floorplan Matching for Robot Localization" (see full citation on our publications page). SLAM Hive is a novel benchmarking system for the systematic and reproducable evaluation of algorithms for Simultaneous Localization and Mapping (SLAM). It utilized virtualization for running the SLAM benchmarks and for evaluation of the results. It can be downloaded at github.com/SLAM-Hive. FloorplanNet is a learning-based topometric robot localization method FloorplanNet, which implements a match between a metric robot map and the potentially inaccurate building floorplan in nonuniform scales and different shapes by semantic information. It is available at github.com/fengdelin/FloorplanNet.git.
You are also invited to read the according news on the SIST website, with more info on the other papers: IROS 2022; IRCA 2023.
Floorplannet example where four maps (in grey) are matched to the floorplan in the center.