Radar in Robotics:
Resilience from Signal to Navigation

2024 IEEE International Conference on Robotics and Automation (ICRA)

May 17th, 2024 - Yokohama, Japan (Conference Center 411-412)

Workshop Overview

We witness wider adoption of autonomous robots in our society. This means they will need to work reliably for long-term autonomy, even facing adverse weather conditions, such as dense fog, heavy rain and snowfall. Although last decades the robotics community has made significant progress in these areas, achieving robust and reliable perception in all-weather conditions is still challenging.

The robustness and performance of robot autonomy strongly rely on its perceptual capability, for which radar technology is considered as indispensable. Compared with the popular vision and LiDAR techniques, radar sensing clearly offers some merits: longer range, measurement of relative velocity from Doppler effect, and robust operation in extreme weather conditions. However, its noisy characteristic caused by multi-path reflection, speckle noise and so on also bring in new problems on radar based robot perception, e.g., localization, mapping, SLAM and navigation, which requires significant fundamental research to tackle.

This Workshop aims to provide a platform for researchers, from both academia and industry, to share the state-of-the-art advances and lessons learned on radar perception, exchange ideas, and identify key challenges and opportunities to advance this field.

Invited Speakers

Dr. Daniele de Martini

Departmental Lecturer,
University of Oxford

Nikhil Khedekar

Norwegian University of Science and Technology (NTNU)

Sam Wood

Product Manager, Navtech

Shane Murray

Radar Perception Lead, NVIDIA

Prof. Chris Heckman

Associate Professor, University of Colorado

Prof. Martin Adams

Professor, University of Chile

Prof. Ayoung Kim

Associate Professor, Seoul National University (SNU)

Program

This workshop will be held in person during ICRA 2024 . Please see the tentative schedule below.

08:50-09:00 Welcome & introduction.
09:00-09:25 Prof. Ayoung Kim (SNU) "Radar SLAM for Unmanned Surface Vehicle Navigation"
09:25-10:00 Nikhil Vijar Khedekar (NTNU), "Tightly-coupled Radar-LiDAR fusion for Robust Odometry"
10:00-10:30 Coffee break & poster session
10:30-11:05 Shane Murray (Nvidia), "Machine learning based radar perception for autonomous vehicles"
11:05-11:45 Poster pitch presentations (3 min per paper)
- - "Modeling Point Uncertainty in Radar SLAM", Yang Xu, Qiucan Huang, Shaojie Shen and Huan Yin
  - "CR3DT: Camera-RADAR Fusion for 3D Detection and Tracking", Nicolas Baumann, Michael Baumgartner, Edoardo Ghignone, Jonas Kühne and Michele Magno
  - "Refining Radar-Lidar Localization Using Learned ICP Weights", Daniil Lisus, Johann Laconte, Keenan Burnett and Timothy Barfoot
  - "RIDERS: Radar-Infrared Depth Estimation for Robust Sensing", Han Li, Yukai Ma, Yuehao Huang, Yaqing Gu, Weihua Xu, Yong Liu and Xingxing Zuo
  - "2D Ego-Motion with Yaw Estimation using Only mmWave Radars via Two-Way weighted ICP", Hojune Kim, Hyesu Jang and Ayoung Kim
  - "Are Doppler Velocity Measurements Useful for Spinning Radar Odometry?", Daniil Lisus, Keenan Burnett, David Yoon and Tim Barfoot
  - "Towards introspective loop closure in 4D radar SLAM", Maximilian Hilger, Vladimír Kubelka, Daniel Adolfsson, Henrik Andreasson and Achim J. Lilienthal
  - "Unleashing HyDRa : Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception", Philipp Wolters, Johannes Gilg, Torben Teepe, Fabian Herzog, Anouar Laouichi, Martin Hofmann and Gerhard Rigoll
  - "ars548 ros: An ARS 548 RDI radar driver for ROS2", Fernando Fernández-Calatayud, Lucía Coto Elena, David Alejo, José Javier Carpio Jiménez, Fernando Caballero and Luis Merino
  - "Human Detection from 4D Radar Data in Low-Visibility Field Conditions". Mikael Skog, Oleksandr Kotlyar, Vladimír Kubelka and Martin Magnusson
  - "ReFeree: Radar-based efficient global descriptor using a Feature and Free space for Place Recognition", Byunghee Choi, Hogyun Kim and Younggun Cho
  - "Adaptive LiDAR-Radar Fusion for Outdoor Odometry Across Dense Smoke Conditions", Chiyun Noh and Ayoung Kim
11:45-12:20 Prof. Chris Heckman (Uni Colorado), "Sparse and Dense Methods in Radar for Robotics"
12:20-13:40 Lunch
13:40-14:15 Sam Wood (Navtech), "Lessons Learned in Building an Ideal Radar Sensor for Off-Road Autonomy"
14:15-14:50 Prof. Martin Adams (Uni Chile), "Lessons from Radar: New Approaches in Autonomous Navigation & Tracking"
14:50-15:20 Coffee break & poster session
15:20-15:55 Daniele de Martini (Oxford), "FMCW Radar, What’s Next? From off-road to Doppler"
15:55-16:20 Competition results & presentation from winning team(s)
16:20-16:50 Panel discussion
16:50-17:00 Closing remarks, ending

Call for Posters & Competition

The workshop is designed to advance research in radar-based robotics.
We welcome submissions of papers that focus on the application of radar technology in robotics. Additionally, we are organizing a competition for the development of radar odometry algorithms.

For more details, please refer to the relevant section.

Go to [Call for Poster]

Go to [Call for Competition]