Yeong Sang Park, Jinyong Jeong, Youngsik Shin and Ayoung Kim, Radar Dataset for Robust Localization and Mapping in Urban Environment. In ICRA Workshop on Dataset Generation and Benchmarking of SLAM Algorithms for Robotics and VR/AR, Montreal, May. 2019. [bib]
Highlights of the dataset
Multimodal range sensors: Radar and LiDAR → for robust structural place recognition algorithms
Multiple cities (multi-environments) → for environment-free loop detection algorithms
Multiple times with month-level temporal gaps → for long-term localization research
Multiple loop candidates, particularly
Reverse revisits → for rotation (viewpoint) invariant loop detection research
Revisits with lane-level differences → for translation change-robust loop detection research
6D baseline trajectories are provided for all sequences → not only place recognition, but also for odometry or SLAM studies.
NEWS (latest)
05/09/2023: We update the license for MulRan dataset. Users can find the license in the Citation tab.
31/05/2021: We now provide radar data which is an oxford-radar-robotcar-dataset compatible format (i.e., meta data such as ray-wise timestamps are embedded in a radar image. (request download and use polar_oxford_form.zip)
07/02/2021: We are constructing extended sequences for the same environments (if you are interested in it, please contact us)
19/11/2020: We additionally released IMU and GPS data!
27/10/2020: Radar Place Recognition example and evaluation code is released!
26/04/2020: Example use-cases of MulRan dataset are released.
31/01/2020: The paper is accepted at ICRA 2020!
13/11/2019: A ROS player (for LiDAR and Radar) is released.
10/09/2019: The site is under construction.
24/05/2019: Our initial version of radar dataset released at ICRA 2019
Contact
Official
rpmsnu@gmail.com
(deprecated) irapkaist@gmail.com
Maintainers
Giseop Kim (paulgkim@kaist.ac.kr)
Yeong Sang Park (pys0728k@kaist.ac.kr)
Hyesu Jang (dortz@snu.ac.kr)