4D Radar-Based Pose Graph SLAM With Ego-Velocity Pre-Integration Factor

Article Robotics

Multi-Class Road User Detection With 3+1D Radar in the View-of-Delft Dataset

Andras Palffy et al.

Summary: In this study, a state-of-the-art object detector (PointPillars) is applied to 3+1D radar data. The benefits of additional elevation information, together with Doppler, radar cross section, and temporal accumulation, are explored in multi-class road user detection. Results show that object detection performance on 64-layer LiDAR data outperforms that on 3+1D radar data, but the gap can be reduced by adding elevation information and integrating successive radar scans. The VoD dataset, a valuable experimental dataset, is provided for scientific benchmarking.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Millimeter Wave FMCW RADARs for Perception, Recognition and Localization in Automotive Applications: A Survey

Arthur Venon et al.

Summary: Millimeter-wave FMCW RADARs have broad potential applications in automotive industry with improved accuracy and affordability. However, they have lower-density outputs and noise compared to other RADAR technologies, requiring specific algorithms for adaptation.

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES (2022)

Add to Collection

Proceedings Paper Automation & Control Systems

A Normal Distribution Transform-Based Radar Odometry Designed For Scanning and Automotive Radars

Pou-Chun Kung et al.

Summary: The proposed radar odometry method is applicable to both scanning radar and automotive radar, achieving high accuracy and precision.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

Add to Collection

Proceedings Paper Automation & Control Systems

CFEAR Radarodometry - Conservative Filtering for Efficient and Accurate Radar Odometry

Daniel Adolfsson et al.

Summary: This paper proposes an accurate and highly efficient method for large-scale radar odometry estimation, utilizing a simple filtering technique, point-to-line metric, and robustness to outliers using Huber loss. Additionally, drift is reduced by jointly registering the latest scan to a history of keyframes. Generalization to different sensor models and datasets without parameter changes is achieved, with an overall translation error improvement demonstrated in various environments.

2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2021)

Add to Collection

Proceedings Paper Automation & Control Systems