Abstract—In this paper, we propose a method to accurately estimate the position of the vehicle by millimeter wave radar (MWR). In recent years, many techniques of autonomous driving have been developed actively. In order to realize a safety autonomous driving system, MWR plays an important role for its inherent robustness against external circumstances. However, MWR has low spatial resolution. To achieve highly accurate estimation, we propose a model-based matching approach to the point cloud observed from MWR. Simulation experiments show that accurate estimation of the position of a moving vehicle can be obtained.
Index Terms—Autonomous driving, object detection, Millimeter Wave Radar (MWR), point cloud, least-squares method.
Yoshihiro Suzuki, Yosuke Sugiura, and Tetsuya Shimamura are with the Graduate School of Science and Engineering, Saitama University, Saitama 338-0823, Japan (e-mail: {suzuki, sugiura, shima}@sie.ics.saitama-u.ac.jp).
Osamu Isaji, Kazuaki Hamada, and Kazuhiko Shite are with DENSO TEN Limited, Kobe 652-8510, Japan (e-mail: {osamu.isaji, kazuaki.hamada, kazuhiko.shite}@denso-ten.com).
[PDF]
Cite: Yoshihiro Suzuki, Yosuke Sugiura, Tetsuya Shimamura, Osamu Isaji, Kazuaki Hamada, and Kazuhiko Shite, "Model-Based Vehicle Position Estimation Using Millimeter Wave Radar," International Journal of Future Computer and Communication vol. 8, no. 3, pp. 94-98, 2019.
