Radar is one of the primary active safety sensors for advanced driver assistance systems. Autonomous vehicles will heavily rely on the ability of automotive radar systems to accurately identify crucial targets while filtering out false targets. Road guardrails present a unique corner case challenge to automotive radar sensors due to their large radar cross section (RCS) that can lead to false targets alerts. This paper presents a full physics, full-scale electromagnetic simulation-based study on the radar returns of road guardrails. Results from this paper demonstrate how guardrails can obfuscate crucial targets, such as pedestrians and nearby stationary vehicles. A novel guardrail system for high-pedestrian density areas is proposed. Further RCS reduction of this design is achieved through a proposed diffraction mitigation technique. Simulations using this proposed guardrail system predict over 25-dB reduction in guardrail RCS. Results from this paper show that guardrails with low RCS improve the visibility of adjacent stationary targets, and thus have the potential to reduce accidents and possibly save lives.

Full Physics Simulation Study of Guardrail Radar-Returns for 77 GHz Automotive Radar Systems

The automobile industry has a strategic intent to develop vehicles capable of higher and higher levels of autonomy. Radar is a key sensing component, being the only viable option for all weather, 24-hour-a-day use. Autonomy will require the radar to provide much greater levels of detailed information than is available from today's cruise control and collision avoidance systems. In particular, much wider bandwidths are needed for high range resolution. Furthermore, high Doppler resolution, requiring long integration times, is needed for moving object classification. These two opposing requirements create significant design and signal processing challenges. This paper examines the way in which choices in the key design parameters effect performance, showing that as both range and Doppler resolutions are enhanced, the potential for received energy to migrate across resolution cells increases and must be corrected to enable measurement of both focused high-resolution imagery and micro-Doppler signatures, as well as restoring system sensitivity. An advanced range and Doppler cell migration correction algorithm is introduced and performance evaluated using both theory and experimentation.

Range and Doppler Cell Migration in Wideband Automotive Radar

The introduction of autonomous vehicles can potentially lead to enhanced situational awareness and safety for road transport. However, the performance required for autonomous operations places stringent requirements on the vehicle navigation systems design. Relevant performance measures include not only the accuracy of the system but also its ability to detect sensor faults within a specified Time-to-Alert (TTA) and without generating an excessive number of false alarms. A new integrated navigation system architecture is proposed which utilizes Global Navigation Satellite Systems (GNSS), low-cost Inertial Navigation Systems (INS), visual odometry and Vehicle Dynamic Models (VDM). The system design is based on various navigation modes, each with independent failure mechanisms and fault-detection capabilities. A two-step data fusion approach is adopted to optimize the system accuracy and integrity performance. This includes a Knowledge-Based Module (KBM) performing a detailed sensor integrity analysis followed by a conventional Extended Kalman Filer (EKF). CAV navigation integrity requirement (i.e., alert limits and time-to-alert) are considered in the KBM where fault detection probabilities are calculated for each mode and translated to protection levels. A simulation case study is executed to verify the performance of each navigation mode in the presence of faults affecting the individual navigation sensors. Results confirm that the required CAV integrity performances are met, while the inclusion of visual odometry and VDM data provides significant performance enhancements both in terms of accuracy and integrity over existing INS/GNSS systems.

A High-Integrity and Low-Cost Navigation System for Autonomous Vehicles

In this paper, two types of compressed Luneburg lenses based on transformation optics are investigated and simulated using two different sources, namely, waveguides and dipoles, which represent plane and spherical wave sources, respectively. We determined that the largest beam steering angle and the related feed point are intrinsic characteristics of a certain type of compressed Luneburg lens, and that the optimized distance between the feed and lens, gain enhancement, and side-lobe suppression are related to the type of source. Based on our results, we anticipate that these lenses will prove useful in various future antenna applications.

Beam steering performance of compressed Luneburg lens based on transformation optics

Automotive radar is one of the enabling technologies for advanced driver assistance systems (ADAS) and subsequently fully autonomous vehicles. Along with determining the range and velocity of targets with fairly high resolution, autonomous vehicles navigating complex urban environments need radar sensors with high azimuth and elevation resolution. Size and cost constraints limit the physical number of antennas that can be used to achieve high resolution direction-of-arrival (DoA) estimation. Multiple-input/multiple-output (MIMO) schemes achieve larger virtual arrays using fewer physical antennas than would be needed for a single-input/multiple-output (SIMO) system. This paper presents a high-fidelity physics simulation of a 77GHz, frequency-modulated continuous-waveform (FMCW)-based 128 channel (8 transmitters (T
 x
), 16 receivers (R
 x
)) MIMO radar sensor. The 77GHz synthetic radar returns from full scale traffic scenes are obtained using a high-fidelity physics, shooting and bouncing ray electromagnetics solver. A fast Fourier transform (FFT) based signal processing scheme is used across slow-time (chirp) and space (channel) to obtain range-Doppler and DoA maps, respectively. Detection and angular separation performance comparisons of 16, 64 and 128 channel MIMO radar sensors are made for two complex driving scenarios.

/pdf/high-fidelity-physics-simulation-of-128-channel-mimo-sensor-259onmr64m.pdf

High Fidelity Physics Simulation of 128 Channel MIMO Sensor for 77GHz Automotive Radar

Obtaining the accurate and real-time state of surrounding objects is essential for automated vehicle planning and decision-making to ensure safe driving. In complex traffic scenarios, object occlusion, clutter interference, and limited sensor detection capabilities lead to false alarms and missed object detection, making it challenging to ensure the stability of tracking and state prediction. To address these challenges, in this study, we developed a robust multi-object detection and tracking method for moving objects based on radar and camera data fusion. First, the radar and camera perform target detection independently, and the detection results are correlated in the image plane to generate a random finite set with an object type. Then, based on the Gaussian mixture probability hypothesis density algorithm framework, the tracking process is improved using elliptic discriminant thresholds, an attenuation function, and simplified pruning methods. The experimental results demonstrate that the improved algorithm can accurately estimate the number and state of targets in object occlusion, measurement loss scenarios, and achieve robust continuous multi-object tracking. The proposed method could guide the design of safer and more efficient intelligent driving systems.

Robust Detection and Tracking Method for Moving Object Based on Radar and Camera Data Fusion

The next-generation high-resolution automotive radar (4D radar) can provide additional elevation measurement and denser point clouds, which has great potential for 3D sensing in autonomous driving. In this paper, we introduce a dataset named TJ4DRadSet with 4D radar points for autonomous driving research. The dataset was collected in various driving scenarios, with a total of 7757 synchronized frames in 44 consecutive sequences, which are well annotated with 3D bounding boxes and track ids. We provide a 4D radar-based 3D object detection baseline for our dataset to demonstrate the effectiveness of deep learning methods for 4D radar point clouds. The dataset can be accessed via the following link: https://github.com/TJRadarLab/TJ4DRadSet.

TJ4DRadSet: A 4D Radar Dataset for Autonomous Driving

Automotive millimeter-wave (MMW) radar is essential in autonomous vehicles due to its robustness in all weather conditions. Traditional commercial automotive radars are limited by their resolution, which makes the object classification task difficult. Thus, the concept of a new generation of four-dimensional (4D) imaging radar was proposed. It has high azimuth and elevation resolution and contains Doppler information to produce a high-quality point cloud. In this paper, we propose an object classification network named Radar Transformer. The algorithm takes the attention mechanism as the core and adopts the combination of vector attention and scalar attention to make full use of the spatial information, Doppler information, and reflection intensity information of the radar point cloud to realize the deep fusion of local attention features and global attention features. We generated an imaging radar classification dataset and completed manual annotation. The experimental results show that our proposed method achieved an overall classification accuracy of 94.9%, which is more suitable for processing radar point clouds than the popular deep learning frameworks and shows promising performance.

https://www.mdpi.com/1424-8220/21/11/3854/pdf

Radar Transformer: An Object Classification Network Based on 4D MMW Imaging Radar.

Camera-Radar Data Fusion for Target Detection via Kalman Filter and Bayesian Estimation

Intelligent transportation systems (ITSs) play an increasingly important role in traffic management and traffic safety. Smart cameras are the most widely used sensors in ITSs. However, cameras suffer from a reduction in detection and positioning accuracy due to target occlusion and external environmental interference, which has become a bottleneck restricting ITS development. This work designs a stable perception system based on a millimeter-wave radar and camera to address these problems. Radar has better ranging accuracy and weather robustness, which is a better complement to camera perception. Based on an improved Gaussian mixture probability hypothesis density (GM-PHD) filter, we also propose an optimal attribute fusion algorithm for target detection and tracking. The algorithm selects the sensors’ optimal measurement attributes to improve the localization accuracy while introducing an adaptive attenuation function and loss tags to ensure the continuity of the target trajectory. The verification experiments of the algorithm and the perception system demonstrate that our scheme can steadily output the classification and high-precision localization information of the target. The proposed framework could guide the design of safer and more efficient ITSs with low costs.

Libo Huang

Papers

Robust Detection and Tracking Method for Moving Object Based on Radar and Camera Data Fusion

TJ4DRadSet: A 4D Radar Dataset for Autonomous Driving

Radar Transformer: An Object Classification Network Based on 4D MMW Imaging Radar.

Camera-Radar Data Fusion for Target Detection via Kalman Filter and Bayesian Estimation

Robust Target Detection and Tracking Algorithm Based on Roadside Radar and Camera.