milliEgo: mmWave Aided Egomotion Estimation with Deep Sensor Fusion.

Chris Xiaoxuan Lu, Muhamad Risqi U. Saputra, Peijun Zhao, Yasin Almalıoğlu, Pedro Porto Buarque de Gusmão, Changhao Chen, Ke Sun, Niki Trigoni, Andrew Markham

Abstract

Robust and accurate trajectory estimation of mobile agents such as people and robots is a key requirement for providing spatial awareness to emerging capabilities such as augmented reality or autonomous interaction. Although currently dominated by vision based techniques e.g., visual-inertial odometry, these suffer from challenges with scene illumination or featureless surfaces. As an alternative, we propose \sysname, a novel deep-learning approach to robust egomotion estimation which exploits the capabilities of low-cost mmWave radar. Although mmWave radar has a fundamental advantage over monocular cameras of being metric i.e., providing absolute scale or depth, current single chip solutions have limited and sparse imaging resolution, making existing point-cloud registration techniques brittle. We propose a new architecture that is optimized for solving this underdetermined pose transformation problem. Secondly, to robustly fuse mmWave pose estimates with additional sensors, e.g. inertial or visual sensor we introduce a mixed attention approach to deep fusion. Through extensive experiments, we demonstrate how mmWave radar outperforms existing state-of-the-art odometry techniques. We also show that the neural architecture can be made highly efficient and suitable for real-time embedded applications.
BibTeX
@inproceedings{lu2020milliego,
  author = {Chris Xiaoxuan Lu and Muhamad Risqi U. Saputra and Peijun Zhao and Yasin Almalıoğlu and Pedro Porto Buarque de Gusmão and Changhao Chen and Ke Sun and Niki Trigoni and Andrew Markham},
  title = {{milliEgo: mmWave Aided Egomotion Estimation with Deep Sensor Fusion.}},
  booktitle = {SenSys},
  year = {2020},
  doi = {10.1145/3384419.3430776},
}

Loading related content...

Figure