FMCWレーダーによる自己位置再推定の学習手法RadarLoc
RadarLoc: Learning to Relocalize in FMCW Radar
FMCWレーダースキャンから6自由度のグローバル姿勢を直接推定する自己注意機構付きのエンドツーエンド深層学習モデルを提案し、レーダースキャン間の幾何制約を活用して精度を向上させた。
著者: Wei Wang, Pedro P. B. de Gusmo, Bo Yang, Andrew Markham, Niki Trigoni
分類: cs.RO, cs.AI
原文アブストラクト
Relocalization is a fundamental task in the field of robotics and computer vision. There is considerable work in the field of deep camera relocalization, which directly estimates poses from raw images. However, learning-based methods have not yet been applied to the radar sensory data. In this work, we investigate how to exploit deep learning to predict global poses from Emerging Frequency-Modulated Continuous Wave (FMCW) radar scans. Specifically, we propose a novel end-to-end neural network with self-attention, termed RadarLoc, which is able to estimate 6-DoF global poses directly. We also propose to improve the localization performance by utilizing geometric constraints between radar scans. We validate our approach on the recently released challenging outdoor dataset Oxford Radar RobotCar. Comprehensive experiments demonstrate that the proposed method outperforms radar-based localization and deep camera relocalization methods by a significant margin.
