Search

In automotive applications, frequency modulated continuous wave (FMCW) radar is an established technology to determine the distance, velocity and angle of objects in the vicinity of the vehicle. The quality of predictions might be seriously impaired if mutual interference between radar sensors occurs. Previous work processes data from the entire receiver array in parallel to increase interference mitigation quality using neural networks (NNs). However, these architectures do not generalize well across different angles of arrival (AoAs) of interferences and objects. In this paper we introduce fully convolutional neural network (CNN) with rank-three convolutions which is able to transfer learned patterns between different AoAs. Our proposed architecture outperforms previous work while having higher robustness and a lower number of trainable parameters. We evaluate our network on a diverse data set and demonstrate its angle equivariance., Comment: 4 pages, 3 figures

In this paper we propose a new method for training neural networks (NNs) for frequency modulated continuous wave (FMCW) radar mutual interference mitigation. Instead of training NNs to regress from interfered to clean radar signals as in previous work, we train NNs directly on object detection maps. We do so by performing a continuous relaxation of the cell-averaging constant false alarm rate (CA-CFAR) peak detector, which is a well-established algorithm for object detection using radar. With this new training objective we are able to increase object detection performance by a large margin. Furthermore, we introduce separable convolution kernels to strongly reduce the number of parameters and computational complexity of convolutional NN architectures for radar applications. We validate our contributions with experiments on real-world measurement data and compare them against signal processing interference mitigation methods., Comment: 2023 IEEE International Radar Conference (RADAR), 6 pages, 4 figures

Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. With a rising number of radar sensors and the so far unregulated automotive radar frequency band, mutual interference is inevitable and must be dealt with. Algorithms and models operating on radar data are required to run the early processing steps on specialized radar sensor hardware. This specialized hardware typically has strict resource-constraints, i.e. a low memory capacity and low computational power. Convolutional Neural Network (CNN)-based approaches for denoising and interference mitigation yield promising results for radar processing in terms of performance. Regarding resource-constraints, however, CNNs typically exceed the hardware's capacities by far. In this paper we investigate quantization techniques for CNN-based denoising and interference mitigation of radar signals. We analyze the quantization of (i) weights and (ii) activations of different CNN-based model architectures. This quantization results in reduced memory requirements for model storage and during inference. We compare models with fixed and learned bit-widths and contrast two different methodologies for training quantized CNNs, i.e. the straight-through gradient estimator and training distributions over discrete weights. We illustrate the importance of structurally small real-valued base models for quantization and show that learned bit-widths yield the smallest models. We achieve a memory reduction of around 80\% compared to the real-valued baseline. Due to practical reasons, however, we recommend the use of 8 bits for weights and activations, which results in models that require only 0.2 megabytes of memory., Comment: 15 pages; published in IEEE Journal of Selected Topics in Signal Processing, Special Issue on Recent Advances in Automotive Radar Signal Processing, Volume: 15, Issue: 4, June 2021. arXiv admin note: text overlap with arXiv:2011.12706

Autonomous driving highly depends on capable sensors to perceive the environment and to deliver reliable information to the vehicles' control systems. To increase its robustness, a diversified set of sensors is used, including radar sensors. Radar is a vital contribution of sensory information, providing high resolution range as well as velocity measurements. The increased use of radar sensors in road traffic introduces new challenges. As the so far unregulated frequency band becomes increasingly crowded, radar sensors suffer from mutual interference between multiple radar sensors. This interference must be mitigated in order to ensure a high and consistent detection sensitivity. In this paper, we propose the use of Complex-Valued Convolutional Neural Networks (CVCNNs) to address the issue of mutual interference between radar sensors. We extend previously developed methods to the complex domain in order to process radar data according to its physical characteristics. This not only increases data efficiency, but also improves the conservation of phase information during filtering, which is crucial for further processing, such as angle estimation. Our experiments show, that the use of CVCNNs increases data efficiency, speeds up network training and substantially improves the conservation of phase information during interference removal.

Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous cars. Key performance factors are a fine range resolution and the possibility to directly measure velocity. With a rising number of radar sensors and the so far unregulated automotive radar frequency band, mutual interference is inevitable and must be dealt with. Sensors must be capable of detecting, or even mitigating the harmful effects of interference, which include a decreased detection sensitivity. In this paper, we evaluate a Convolutional Neural Network (CNN)-based approach for interference mitigation on real-world radar measurements. We combine real measurements with simulated interference in order to create input-output data suitable for training the model. We analyze the performance to model complexity relation on simulated and measurement data, based on an extensive parameter search. Further, a finite sample size performance comparison shows the effectiveness of the model trained on either simulated or real data as well as for transfer learning. A comparative performance analysis with the state of the art emphasizes the potential of CNN-based models for interference mitigation and denoising of real-world measurements, also considering resource constraints of the hardware., Comment: 2020 IEEE International Radar Conference (RADAR)

Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. Key performance factors are weather resistance and the possibility to directly measure velocity. With a rising number of radar sensors and the so far unregulated automotive radar frequency band, mutual interference is inevitable and must be dealt with. Algorithms and models operating on radar data in early processing stages are required to run directly on specialized hardware, i.e. the radar sensor. This specialized hardware typically has strict resource-constraints, i.e. a low memory capacity and low computational power. Convolutional Neural Network (CNN)-based approaches for denoising and interference mitigation yield promising results for radar processing in terms of performance. However, these models typically contain millions of parameters, stored in hundreds of megabytes of memory, and require additional memory during execution. In this paper we investigate quantization techniques for CNN-based denoising and interference mitigation of radar signals. We analyze the quantization potential of different CNN-based model architectures and sizes by considering (i) quantized weights and (ii) piecewise constant activation functions, which results in reduced memory requirements for model storage and during the inference step respectively., Comment: ITEM Workshop at ECML-PKDD 2020

Driver assistance systems as well as autonomous cars have to rely on sensors to perceive their environment. A heterogeneous set of sensors is used to perform this task robustly. Among them, radar sensors are indispensable because of their range resolution and the possibility to directly measure velocity. Since more and more radar sensors are deployed on the streets, mutual interference must be dealt with. In the so far unregulated automotive radar frequency band, a sensor must be capable of detecting, or even mitigating the harmful effects of interference, which include a decreased detection sensitivity. In this paper, we address this issue with Convolutional Neural Networks (CNNs), which are state-of-the-art machine learning tools. We show that the ability of CNNs to find structured information in data while preserving local information enables superior denoising performance. To achieve this, CNN parameters are found using training with simulated data and integrated into the automotive radar signal processing chain. The presented method is compared with the state of the art, highlighting its promising performance. Hence, CNNs can be employed for interference mitigation as an alternative to conventional signal processing methods. Code and pre-trained models are available at https://github.com/johanna-rock/imRICnn., Comment: FUSION 2019; 8 pages

This paper presents a robust and accurate positioning system that adapts its behavior to the surrounding environment, mimicking the capability of the visual brain to filtering out clutter and focusing attention on activity and relevant information. Especially in indoor environments, which are characterized by harsh multipath propagation, robust positioning is still hard to achieve under the constraint of reasonable infrastructural needs. In such environments it is essential to separate relevant from irrelevant information and attain an appropriate uncertainty model for measurements that are used for positioning., Comment: 11 pages, 9 figures

Location awareness is a key factor for a wealth of wireless indoor applications. Its provision requires the careful fusion of diverse information sources. For agents that use radio signals for localization, this information may either come from signal transmissions with respect to fixed anchors, from cooperative transmissions inbetween agents, or from radar-like monostatic transmissions. Using a-priori knowledge of a floor plan of the environment, specular multipath components can be exploited, based on a geometric-stochastic channel model. In this paper, a unified framework is presented for the quantification of this type of position-related information, using the concept of equivalent Fisher information. We derive analytical results for the Cram\'er-Rao lower bound of multipath-assisted positioning, considering bistatic transmissions between agents and fixed anchors, monostatic transmissions from agents, cooperative measurements inbetween agents, and combinations thereof, including the effect of clock offsets. Awareness of this information enables highly accurate and robust indoor positioning. Computational results show the applicability of the framework for the characterization of the localization capabilities of a given environment, quantifying the influence of different system setups, signal parameters, and the impact of path overlap., Comment: 14 pages, 10 figures, submitted to the IEEE Journal on Selected Areas in Communications: Localization-Awareness for Radios and Networks

Indoor localization systems that are accurate and robust with respect to propagation channel conditions are still a technical challenge today. In particular, for systems based on range measurements from radio signals, non-line-of-sight (NLOS) situations can result in large position errors. In this paper, we address these issues using measurements in a representative indoor environment. Results show that conventional tracking schemes using high- and a low-complexity ranging algorithms are strongly impaired by NLOS conditions unless a very large signal bandwidth is used. Furthermore, we discuss and evaluate the performance of multipath-assisted indoor navigation and tracking (MINT), that can overcome these impairments by making use of multipath propagation. Across a wide range of bandwidths, MINT shows superior performance compared to conventional schemes, and virtually no degradation in its robustness due to NLOS conditions., Comment: Published at the European Navigation Conference (ENC) 2013, Vienna, Austria