A Credible and Robust Approach to Ego-Motion Estimation Using an Automotive Radar
- 28 March 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (3) , 6020-6027
Abstract
Consistent motion estimation is fundamental for all mobile autonomous systems. While this sounds like an easy task, often, it is not the case because of changing environmental conditions affecting odometry obtained from vision, Lidar, or the wheels themselves. Unsusceptible to challenging lighting and weather conditions, radar sensors are an obvious alternative. Usually, automotive radars return a sparse point cloud, representing the surroundings. Utilizing this information to motion estimation is challenging due to unstable and phantom measurements, which result in a high rate of outliers. We introduce a credible and robust probabilistic approach to estimate the ego-motion based on these challenging radar measurements; intended to be used within a loosely-coupled sensor fusion framework. Compared to existing solutions, evaluated on the popular nuScenes dataset and others, we show that our proposed algorithm is more credible while not depending on explicit correspondence calculation.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Joint spatial- and Doppler-based ego-motion estimation for automotive radars2015
- A closed-form estimate of 3D ICP covariance2015
- Instantaneous ego-motion estimation using multiple Doppler radars2014
- Instantaneous ego-motion estimation using Doppler radar2013
- Fast and accurate scan registration through minimization of the distance between compact 3D NDT representationsThe International Journal of Robotics Research, 2012
- 3D is here: Point Cloud Library (PCL)2011
- Methods for merging Gaussian mixture componentsAdvances in Data Analysis and Classification, 2010
- Generalized-ICP2009
- Scan registration for autonomous mining vehicles using 3D‐NDTJournal of Field Robotics, 2007
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992