“…Each time step in the series is analyzed by first calculating currents on all surfaces in the model using a user specified antenna pattern, and then radiating those currents back to another antenna pattern using the SBR method. The usage of the SBR technique has been demonstrated by [15] and [16] to perform full physics simulation of a realistic ADAS scenarios.…”
Section: Methodology a Physics Based Radar Simulationmentioning
Safety critical systems in Advanced Driver Assistance Systems (ADAS) depend on multiple sensors to perceive the environment in which they operate. Radar sensors provide many advantages and complementary capabilities to other available sensors but are not without their own shortcomings. Performance of radar perception algorithms still pose many challenges, one of which is in object detection and classification. In order to increase redundancy in ADAS, the ability for a radar system to detect and classify objects independent of other sensors is desirable. In this paper, an investigation of a machine learning based radar perception algorithm for object detection is implemented, along with a novel, automated workflow for generating large-scale virtual datasets used for training and testing. Physics-based electromagnetic simulation of a complex scattering environment is used to create the virtual dataset. Objects are classified and localized within Doppler-Range results using a single channel 77 GHz FMCW radar system. Utilizing a fully convolutional network, the radar perception model is trained and tested. The training is performed using a wide range of environments and traffic scenarios. Model inference is tested on completely new environments and traffic scenarios. These simulated radar returns are highly scalable and offer an efficient method for dataset generation. These virtual datasets facilitate a simple method of introducing variability in training data, corner case evaluation and root cause analysis, amongst other advantages.
“…Each time step in the series is analyzed by first calculating currents on all surfaces in the model using a user specified antenna pattern, and then radiating those currents back to another antenna pattern using the SBR method. The usage of the SBR technique has been demonstrated by [15] and [16] to perform full physics simulation of a realistic ADAS scenarios.…”
Section: Methodology a Physics Based Radar Simulationmentioning
Safety critical systems in Advanced Driver Assistance Systems (ADAS) depend on multiple sensors to perceive the environment in which they operate. Radar sensors provide many advantages and complementary capabilities to other available sensors but are not without their own shortcomings. Performance of radar perception algorithms still pose many challenges, one of which is in object detection and classification. In order to increase redundancy in ADAS, the ability for a radar system to detect and classify objects independent of other sensors is desirable. In this paper, an investigation of a machine learning based radar perception algorithm for object detection is implemented, along with a novel, automated workflow for generating large-scale virtual datasets used for training and testing. Physics-based electromagnetic simulation of a complex scattering environment is used to create the virtual dataset. Objects are classified and localized within Doppler-Range results using a single channel 77 GHz FMCW radar system. Utilizing a fully convolutional network, the radar perception model is trained and tested. The training is performed using a wide range of environments and traffic scenarios. Model inference is tested on completely new environments and traffic scenarios. These simulated radar returns are highly scalable and offer an efficient method for dataset generation. These virtual datasets facilitate a simple method of introducing variability in training data, corner case evaluation and root cause analysis, amongst other advantages.
“…Accurate computational methods in classification and identification of targets are very much desired. Autonomous self-driving car [ 1 ], intelligent robots [ 2 ], smart home devices [ 3 ], and diagnosing disease [ 4 ] are just some of the domains that usually target detection and target classification play an important role. Wireless radar sensing using millimeter wave signals is proven as an effective tool for various purposes [ 5 , 6 , 7 ].…”
A target’s movements and radar cross sections are the key parameters to consider when designing a radar sensor for a given application. This paper shows the feasibility and effectiveness of using 24 GHz radar built-in low-noise microwave amplifiers for detecting an object. For this purpose a supervised machine learning model (SVM) is trained using the recorded data to classify the targets based on their cross sections into four categories. The trained classifiers were used to classify the objects with varying distances from the receiver. The SVM classification is also compared with three methods based on binary classification: a one-against-all classification, a one-against-one classification, and a directed acyclic graph SVM. The level of accuracy is approximately 96.6%, and an F1-score of 96.5% is achieved using the one-against-one SVM method with an RFB kernel. The proposed contactless radar in combination with an SVM algorithm can be used to detect and categorize a target in real time without a signal processing toolbox.
“…Nowadays, mid-and short-range radars are widely available in the market, typically operating at micro and millimetre wave frequencies, for example, in the 24 and 77 GHz frequency bands, through commercially of-the-shelf and system-on-chip (SoC) kits [10][11][12]. This integration facilitates radar deployment making this technology very attractive for the automotive [13][14][15] and UAV markets [16][17][18], in particular for object detection and collision avoidance, and to assist with autonomous safety driving.…”
A compact parabolic reflector antenna aiming at radar applications in the K‐band is presented. It is mainly composed of a thermoplastic material and using classical additive techniques (also known as 3D printing), the proposed high‐gain antenna exhibits a novel and unique form factor, particularly of interest for applications with low payload capacity, for example unmanned aerial vehicles. The antenna is composed of four parts: (i) a paraboloid shape embodied in a supporting polylactic acid (PLA) material; (ii) a metallic coating applied to the paraboloid surface of (i), to enable it with electromagnetic reflecting properties; (iii) a PLA spacer that ensures the physical separation (i.e. focal distance) between parts (i) and (iv) and, finally, (iv) a microstrip patch antenna with a reduced ground plane to reduce feed blockage. Subsequently to an overview on the theoretical formulation of parabolic reflector antennas, an antenna targeting 20 dBi and a minimum bandwidth of 500 MHz operating in the 24 GHz ISM radar band have been dimensioned, optimised in CST Microwave Studio and validated against measurements performed on a physical prototype. The simulation and experimental results are in good agreement with the prototype yielding 18.3 dBi of gain and 2.2 GHz of useful bandwidth, clearly demonstrating the potential of the proposed antenna design.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.