MIMO Radar for Advanced Driver-Assistance Systems and Autonomous Driving: Advantages and Challenges

Sun, Shunqiao; Petropulu, Athina P.; Poor, H. Vincent

doi:10.1109/msp.2020.2978507

Cited by 408 publications

(145 citation statements)

References 102 publications

Supporting

Mentioning

143

Contrasting

Order By: Relevance

“…sending N c frequency ramps in a sequence, the Doppler induced frequency shift f D can be extracted. Finally, by using antenna arrays in a multiple-input multiple-output (MIMO) configuration, the angle of arrival can be obtained from the phase differences at different receive antenna positions [59]. Altogether, the frequency and phase components to be estimated, can be described as…”

Section: B Radar System Simulationmentioning

confidence: 99%

“…In order to resolve targets, the corresponding frequencies from (1) need to be estimated from the pre-processed signal. This is accomplished by using a 3D fast-Fourier transform (FFT) along the respective dimensions, effectively converting the samples dimension to the fast-time, the chirps dimension to the slow-time, and the antennas dimension to the azimuth angle, respectively [59], [60]. The resulting 3D spectrum is referred to as range-Doppler-angle (RDA) cube.…”

Section: Automotive Radar Signal Processingmentioning

confidence: 99%

See 1 more Smart Citation

A Bayesian Framework for Integrated Deep Metric Learning and Tracking of Vulnerable Road Users Using Automotive Radars

et al. 2021

View full text Add to dashboard Cite

With the recent advancements in radar systems, radar sensors offer a promising and effective perception of the surrounding. This includes target detection, classification and tracking. Compared to the state-of-theart, where the state vector of classical tracker considers only localization parameters, this paper proposes an integrated Bayesian framework by augmenting state vector with feature embedding as appearance parameter together with localization parameter. In context of automotive vulnerable road users (VRUs) such as pedestrian and cyclist, the classical tracker poses multiple challenges to preserve the identity of the tracked target during partial or complete occlusion, due to low inter-class (pedestrian-cyclist) variations and strong similarity between intra-class (pedestrian-pedestrian). Subsequently, feature embedding corresponding to target's micro-Doppler signature are learned using novel Bayesian based deep metric learning approaches. The tracker's performance is optimized due to a better separability of the targets. At the same time, the classifiers' performance is enhanced due to Bayesian formulation utilizing the temporal smoothing of the classifier's embedding vector. In this work, we demonstrate the performance of the proposed Bayesian framework using several vulnerable user targets based on a 77 GHz automotive radar.

show abstract

Section: B Radar System Simulationmentioning

confidence: 99%

Section: Automotive Radar Signal Processingmentioning

confidence: 99%

A Bayesian Framework for Integrated Deep Metric Learning and Tracking of Vulnerable Road Users Using Automotive Radars

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Consequently, angle finding can be easily accomplished by DBF, i.e. by performing FFT processing on the estimated phases taken across multiple elements of the virtual array in a single frame interval [4], [64]. Note, however, that other angle estimation methods, achieving a better resolution than FFT processing are also available; here, we limit to mention the so called subspace-based methods (such as MUSIC and ESPRIT), sparse sensing-based methods [65], [66] and the iterative adaptive approach (IAA) developed in ref.…”

Section: Architecture Of a Colocated Tdm Mimo Radarmentioning

confidence: 99%

Machine Learning and Deep Learning Techniques for Colocated MIMO Radars: A Tutorial Overview

DAVOLI¹,

Guerzoni²,

Vitetta³

2021

Preprint

View full text Add to dashboard Cite

<p>Radars are expected to become the main sensors in various civilian applications, ranging from health-care monitoring to autonomous driving. Their success is mainly due to the availability of both low cost integrated devices, equipped with compact antenna arrays, and computationally efficient signal processing techniques. An increasingly important role in the field of radar signal processing is played by machine learning and deep learning techniques. Their use has been first taken into consideration in human gesture and motion recognition, and in various healthcare applications. More recently, their exploitation in object detection and localization has been also investigated. The research work accomplished in these areas has raised various technical problems that need to be carefully addressed before adopting the above mentioned techniques in real world radar systems. In this manuscript, a comprehensive overview of the machine learning and deep learning techniques currently being considered for their use in radar systems is provided. Moreover, some relevant open problems and current trends in this research area are analysed. Finally, various numerical results, based on both synthetically generated and experimental datasets, and referring to two different applications are illustrated. These allow readers to assess the efficacy of specific methods and to compare them in terms of accuracy and computational effort.</p>

show abstract

“…With the improvement in the intelligence of autonomous vehicles, the demand for the amount of information provided by millimeter-wave radar is higher and higher. As a result, in recent years, the concept of high-resolution imaging radar is brought up in the field of automotive radar [2]. The high-resolution imaging radar provides relatively dense millimeter-wave radar 4D point clouds based on the multiple-input multiple-output (MIMO) technology.…”

Section: Introductionmentioning

confidence: 99%

A New Automotive Radar 4D Point Clouds Detector by Using Deep Learning

Cheng

Chen

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

The millimeter-wave radar, as an important sensor, is widely used in autonomous driving. In recent years, to meet the requirement of high level autonomous driving applications, attentions have been paid to generate high-quality radar point clouds. However, in the complex roadway environment, the weaknesses of classical radar detectors are exposed, such as too much clutter points and sparse valid point clouds. Therefore, in this paper, we propose a new automotive radar detector based on deep learning using the spatial distribution feature of the real targets, in order to improve the performance of automotive radar detector in the real-world driving scene. Besides, aiming at the lack of radar data labels, we propose an autonomous labeling method by using synchronized Lidar data. Finally, we evaluate the detector on data collected in the real-world roadway scene and the result shows that the proposed radar detector out-performs the classical radar detectors in suppressing the clutter and generating denser point clouds.

show abstract

MIMO Radar for Advanced Driver-Assistance Systems and Autonomous Driving: Advantages and Challenges

Cited by 408 publications

References 102 publications

A Bayesian Framework for Integrated Deep Metric Learning and Tracking of Vulnerable Road Users Using Automotive Radars

A Bayesian Framework for Integrated Deep Metric Learning and Tracking of Vulnerable Road Users Using Automotive Radars

Machine Learning and Deep Learning Techniques for Colocated MIMO Radars: A Tutorial Overview

A New Automotive Radar 4D Point Clouds Detector by Using Deep Learning

Contact Info

Product

Resources

About