Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges
Radar is a key component of the suite of perception sensors used for safe and reliable navigation of autonomous vehicles. Its unique capabilities include high-resolution velocity imaging, detection of agents in occlusion and over long ranges, and robust performance in adverse weather conditions. How...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10242101/ |
| _version_ | 1797685400795348992 |
|---|---|
| author | Arvind Srivastav Soumyajit Mandal |
| author_facet | Arvind Srivastav Soumyajit Mandal |
| author_sort | Arvind Srivastav |
| collection | DOAJ |
| description | Radar is a key component of the suite of perception sensors used for safe and reliable navigation of autonomous vehicles. Its unique capabilities include high-resolution velocity imaging, detection of agents in occlusion and over long ranges, and robust performance in adverse weather conditions. However, the usage of radar data presents some challenges: it is characterized by low resolution, sparsity, clutter, high uncertainty, and lack of good datasets. These challenges have limited radar deep learning research. As a result, current radar models are often influenced by lidar and vision models, which are focused on optical features that are relatively weak in radar data, thus resulting in under-utilization of radar’s capabilities and diminishing its contribution to autonomous perception. This review seeks to encourage further deep learning research on autonomous radar data by 1) identifying key research themes, and 2) offering a comprehensive overview of current opportunities and challenges in the field. Topics covered include early and late fusion, occupancy flow estimation, uncertainty modeling, and multipath detection. The paper also discusses radar fundamentals and data representation, presents a curated list of recent radar datasets, and reviews state-of-the-art lidar and vision models relevant for radar research. |
| first_indexed | 2024-03-12T00:44:37Z |
| format | Article |
| id | doaj.art-dffbda108d1a440f93db136ab70c9cfa |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T00:44:37Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-dffbda108d1a440f93db136ab70c9cfa2023-09-14T23:00:26ZengIEEEIEEE Access2169-35362023-01-0111971479716810.1109/ACCESS.2023.331238210242101Radars for Autonomous Driving: A Review of Deep Learning Methods and ChallengesArvind Srivastav0https://orcid.org/0000-0002-8760-0978Soumyajit Mandal1https://orcid.org/0000-0001-9070-2337Zoox, Inc., Foster City, CA, USABrookhaven National Laboratory, Upton, NY, USARadar is a key component of the suite of perception sensors used for safe and reliable navigation of autonomous vehicles. Its unique capabilities include high-resolution velocity imaging, detection of agents in occlusion and over long ranges, and robust performance in adverse weather conditions. However, the usage of radar data presents some challenges: it is characterized by low resolution, sparsity, clutter, high uncertainty, and lack of good datasets. These challenges have limited radar deep learning research. As a result, current radar models are often influenced by lidar and vision models, which are focused on optical features that are relatively weak in radar data, thus resulting in under-utilization of radar’s capabilities and diminishing its contribution to autonomous perception. This review seeks to encourage further deep learning research on autonomous radar data by 1) identifying key research themes, and 2) offering a comprehensive overview of current opportunities and challenges in the field. Topics covered include early and late fusion, occupancy flow estimation, uncertainty modeling, and multipath detection. The paper also discusses radar fundamentals and data representation, presents a curated list of recent radar datasets, and reviews state-of-the-art lidar and vision models relevant for radar research.https://ieeexplore.ieee.org/document/10242101/Radarperceptionautonomous drivingself-driving carselectric vehicles4D data |
| spellingShingle | Arvind Srivastav Soumyajit Mandal Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges IEEE Access Radar perception autonomous driving self-driving cars electric vehicles 4D data |
| title | Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges |
| title_full | Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges |
| title_fullStr | Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges |
| title_full_unstemmed | Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges |
| title_short | Radars for Autonomous Driving: A Review of Deep Learning Methods and Challenges |
| title_sort | radars for autonomous driving a review of deep learning methods and challenges |
| topic | Radar perception autonomous driving self-driving cars electric vehicles 4D data |
| url | https://ieeexplore.ieee.org/document/10242101/ |
| work_keys_str_mv | AT arvindsrivastav radarsforautonomousdrivingareviewofdeeplearningmethodsandchallenges AT soumyajitmandal radarsforautonomousdrivingareviewofdeeplearningmethodsandchallenges |