AutoPlace: Robust Place Recognition with Low-cost Single-chip Automotive Radar

This paper presents a novel place recognition approach to autonomous vehicles by using low-cost, single-chip automotive radar. Aimed at improving recognition robustness and fully exploiting the rich information provided by this emerging automotive radar, our approach follows a principled pipeline that comprises (1) dynamic points removal from instant Doppler measurement, (2) spatial-temporal feature embedding on radar point clouds, and (3) retrieved candidates refinement from Radar Cross Section measurement. Extensive experimental results on the public nuScenes dataset demonstrate that existing visual/LiDAR/spinning radar place recognition approaches are less suitable for single-chip automotive radar. In contrast, our purpose-built approach for automotive radar consistently outperforms a variety of baseline methods via a comprehensive set of metrics, providing insights into the efficacy when used in a realistic system.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  Luc Van Gool,et al.  Depth Estimation from Monocular Images and Sparse Radar Data , 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[3]  Paul Newman,et al.  The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[4]  Ingmar Posner,et al.  Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[5]  Yang Li,et al.  The Millimeter-Wave Radar SLAM Assisted by the RCS Feature of the Target and IMU , 2020, Sensors.

[6]  Shin Ishii,et al.  Expanding histogram of colors with gridding to improve tracking accuracy , 2015, 2015 14th IAPR International Conference on Machine Vision Applications (MVA).

[7]  Niko Sünderhauf,et al.  On the performance of ConvNet features for place recognition , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[8]  Gordon Wyeth,et al.  SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights , 2012, 2012 IEEE International Conference on Robotics and Automation.

[9]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[10]  Martin David Adams,et al.  An augmented state SLAM formulation for multiple line-of-sight features with millimetre wave RADAR , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Matthew Gadd,et al.  Look Around You: Sequence-based Radar Place Recognition with Learned Rotational Invariance , 2020, 2020 IEEE/ION Position, Location and Navigation Symposium (PLANS).

[12]  Ayoung Kim,et al.  Scan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[13]  Jacek Komorowski,et al.  MinkLoc3D: Point Cloud Based Large-Scale Place Recognition , 2020, 2021 IEEE Winter Conference on Applications of Computer Vision (WACV).

[14]  Andrew Markham,et al.  See through smoke: robust indoor mapping with low-cost mmWave radar , 2020, MobiSys.

[15]  Sen Wang,et al.  RadarSLAM: Radar based Large-Scale SLAM in All Weathers , 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[16]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[17]  Michael Milford,et al.  SeqNet: Learning Descriptors for Sequence-Based Hierarchical Place Recognition , 2021, IEEE Robotics and Automation Letters.

[18]  Klaus C. J. Dietmayer,et al.  Instantaneous ego-motion estimation using Doppler radar , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

[19]  Chieh-Chih Wang,et al.  A Normal Distribution Transform-Based Radar Odometry Designed For Scanning and Automotive Radars , 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

[20]  Paul Newman,et al.  FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance , 2008, Int. J. Robotics Res..

[21]  Li He,et al.  M2DP: A novel 3D point cloud descriptor and its application in loop closure detection , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[22]  Andrew Kramer,et al.  Radar-Inertial Ego-Velocity Estimation for Visually Degraded Environments , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[23]  Michael Milford,et al.  DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition , 2020, ArXiv.

[24]  Jan-Michael Frahm,et al.  Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Shilin Zhou,et al.  Evaluation of Object Proposals and ConvNet Features for Landmark-based Visual Place Recognition , 2018, J. Intell. Robotic Syst..

[26]  Hermann Winner,et al.  Adaptive Cruise Control , 2015, Handbuch Fahrerassistenzsysteme.

[27]  Jürgen Dickmann,et al.  RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applications , 2021, 2021 IEEE 24th International Conference on Information Fusion (FUSION).

[28]  Qiang Xu,et al.  nuScenes: A Multimodal Dataset for Autonomous Driving , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Jiong Wang,et al.  Attention-based Pyramid Aggregation Network for Visual Place Recognition , 2018, ACM Multimedia.

[30]  Gim Hee Lee,et al.  PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[31]  Sen Wang,et al.  End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks , 2018, Int. J. Robotics Res..

[32]  Matthew Gadd,et al.  Kidnapped Radar: Topological Radar Localisation using Rotationally-Invariant Metric Learning , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[33]  Lingqiao Liu,et al.  Learning Context Flexible Attention Model for Long-Term Visual Place Recognition , 2018, IEEE Robotics and Automation Letters.