检索结果-内蒙古大学图书馆

Point Cloud Segmentation with a High-Resolution Automotive Radar

学校读者我要写书评

暂无评论

Point Cloud Segmentation with a High-Resolution Automotive R...

AmE 2019 - Automotive meets Electronics;10th GMM-Symposium

ISBN: (纸本)9783800748778

Deep Learning is currently widely used in video-based classification and segmentation tasks for autonomous vehicles. With images as input, pixels can be used as structured input data for a convolutional neural network. In order to improve the reliability of the perception system for automated vehicles, other sensors can simultaneously be employed to complement the shortcomings of the video camera sensors. Among these sensor candidates, RADAR and LIDAR sensors are the two prominent ones. For these two sensors, the input data format is totally different from that of the camera sensor, where object reflection points are collected instead of pixels. A simple way to handle these reflection points is to manually create a grid map and fill it up with the reflection points. However, this causes not only information loss during the filling process, but also increases the input data size significantly because of the large number of grid cells, especially when a 3D grid representation is used. So it can be advantageous to feed the reflection points directly into the neural network. Such unstructured input data format, however, will not work in conventional, grid-based convolutional neural networks. In this paper, we will present application results with a recently developed point-based neural network for radar reflection point cloud segmentation.

关键词： reflection point Grid Cells Neural network sensors road vehicle radar Autonomous Vehicles filling(process) data formats information loss incoming data

Instantaneous Actual Motion Estimation with a Single High-Resolution Radar sensor

学校读者我要写书评

暂无评论

Instantaneous Actual Motion Estimation with a Single High-Re...

2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility, ICMIM 2018

作者： Schlichenmaier, Johannes Yan, Leping Stolz, Martin Waldschmidt, Christian Institute of Microwave Engineering Ulm University Ulm89081 Germany Robert Bosch GmbH Advanced Engineering Sensor Systems Leonberg71226 Germany

ISBN: (纸本)9781538617250

Future high-resolution radars enable new functionalities in advanced driver assistance systems, relying on fast and reliable extraction of properties of vehicles on the road. A critical property for the prediction of trajectories and the assessment of potentially dangerous situations is that of the actual motion - the velocity vector and yaw rate - of observed objects. In this paper, an approach to distinguish linear from non-linear motions as well as estimating the yaw rate using only a single radar sensor is presented and evaluated via measurements. © 2018 IEEE.

关键词： advanced driver assistance systems

Direction of Movement Estimation of Cyclists with a High-Resolution Automotive Radar

学校读者我要写书评

暂无评论

Direction of Movement Estimation of Cyclists with a High-Res...

2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility, ICMIM 2018

作者： Stolz, Martin Li, Mingkang Feng, Zhaofei Kunert, Martin Menzel, Wolfgang Advanced Engineering Sensor Systems Robert Bosch GmbH Leonberg Germany Institute of Microwave Techniques Ulm University Ulm Germany

ISBN: (纸本)9781538617250

Prediction of the object movement from sensor data in the automotive sector is a widespread research and development topic. Dependent on the used sensor types, object tracking has been established over several measurement cycles. A prominent example of this is the Kalman filter. In time critical scenarios with less reaction time tracking over a number of measurement cycles is not suitable. To detect object movement within one single measurement cycle only the radar sensor is a candidate, due to the ability to measure the velocity of objects instantaneously by using the Doppler effect.A new approach to estimate the direction of movement of cyclists within one measurement cycle is introduced and explained in this paper. It is based on the approximation of the shape from a cyclist. The approximation is performed with two different methods and the solutions are compared with each other. To validate the results of the direction estimation, simulated and measured radar data are exercised. © 2018 IEEE.

关键词： Radar measurement

Description of collective magnetization processes with machine learning models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kornell, Alexander Exl, Lukas Breth, Leoni Fischbacher, Johann Kovacs, Alexander Oezelt, Harald Gusenbauer, Markus Yano, Masao Sakuma, Noritsugu Kinoshita, Akihito Shoji, Tetsuya Kato, Akira Mauser, Norbert J. Schrefl, Thomas Christian Doppler Laboratory for Magnet Design Through Physics Informed Machine Learning Viktor Kaplan-Straße 2E Wiener Neustadt2700 Austria Department for Integrated Sensor Systems Danube University Krems Viktor Kaplan-Straße 2E Wiener Neustadt2700 Austria Research Platform MMM Mathematics-Magnetism-Materials c/o Fak. Mathematik University of Vienna Oskar-Morgenstern-Platz 1 Vienna1090 Austria Wolfgang Pauli Institute c/o Fak. Mathematik University of Vienna Oskar-Morgenstern-Platz 1 Vienna1090 Austria Advanced Materials Engineering Div. Toyota Motor Corporation 1200 Mishuku Susono Shizuoka410-1193 Japan

This work introduces a latent space method to calculate the demagnetization reversal process of multigrain permanent magnets. The algorithm consists of two deep learning models based on neural networks. The embedded Stoner-Wohlfarth method is used as a reduced order model for computing samples to train and test the machine learning approach. The work is a proof of concept of the method since the used microstructures are simple and the only varying parameters are the magnetic anisotropy axes of the hard magnetic grains. A convolutional autoencoder is used for nonlinear dimensionality reduction, in order to reduce the required amount of training samples for predicting the hysteresis loops. We enriched the loss function with physical information about the underlying problem which increases the accuracy of the machine learning approach. A deep learning regressor is operating in the latent space of the autoencoder. The predictor takes a series of previously encoded magnetization states and outputs the next magnetization state along the hysteresis curve. To predict the complete demagnetization loop, we apply a recursive learning scheme. © 2022, CC BY.

关键词： Demagnetization

Exploring the hysteresis properties of nanocrystalline permanent magnets using deep learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kovacs, Alexander Exl, Lukas Kornell, Alexander Fischbacher, Johann Hovorka, Markus Gusenbauer, Markus Breth, Leoni Oezelt, Harald Yano, Masao Sakuma, Noritsugu Kinoshita, Akihito Shoji, Tetsuya Kato, Akira Schrefl, Thomas Christian Doppler Laboratory for Magnet design through physics informed machine learning Viktor Kaplan-Straße 2E Wiener Neustadt2700 Austria Department for Integrated Sensor Systems Danube University Krems Viktor Kaplan-Straße 2E Wiener Neustadt2700 Austria Department of Mathematics University of Vienna Oskar-Morgenstern-Platz 1 Vienna1090 Austria Wolfgang Pauli Institute Oskar-Morgenstern-Platz 1 Vienna1090 Austria Research Platform MMM Mathematics-Magnetism-Materials Oskar-Morgenstern-Platz 1 Vienna1090 Austria Advanced Materials Engineering Div. Toyota Motor Corporation 1200 Mishuku Susono Shizuoka410-1193 Japan

We demonstrate the use of model order reduction and neural networks for estimating the hysteresis properties of nanocrystalline permanent magnets from microstructure. With a data-driven approach, we learn the demagnetization curve from data-sets created by grain growth and micromagnetic simulations. We show that the granular structure of a magnet can be encoded within a low-dimensional latent space. Latent codes are constructed using a variational autoencoder. The mapping of structure code to hysteresis properties is a multi-target regression problem. We apply deep neural network and use parameter sharing, in order to predict anchor points along the demagnetization curves from the magnet’s structure code. The method is applied to study the magnetic properties of nanocrystalline permanent magnets. We show how new grain structures can be generated by interpolation between two points in the latent space and how the magnetic properties of the resulting magnets can be *** Codes 68T07 Copyright © 2022, The Authors. All rights reserved.

关键词： Permanent magnets

Verification of a Lane Detection Method with Automotive Radar based on a New Type of Road Marking

学校读者我要写书评

暂无评论

Verification of a Lane Detection Method with Automotive Rada...

2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility, ICMIM 2018

作者： Feng, Zhaofei Stolz, Martin Li, Mingkang Kunert, Martin Wiesbeck, Werner Advanced Engineering Sensor Systems Robert Bosch GmbH Leonberg71226 Germany Institute of Radio Frequency Engineering and Electronics Karlsruhe Institute of Technology Karlsruhe76131 Germany

ISBN: (纸本)9781538617250

Lane Change Assist, Lane Departure Warning, Lane Keeping System, and Automated Driving all require the sensors in vehicles to be able to detect the road and lane boundaries reliably and accurately under all circumstances. However, such functions rely currently solely on camera sensors, which in result unavoidably affects the stability of the whole system under certain extreme lighting conditions. Therefore, this paper shows a verification test result of a novel approach in lane boundary detection with an automotive radar and a specific kind of reflectors. A new approach of road course prediction and vehicle localization by utilizing its Range-Doppler characteristics is also presented in this paper. © 2018 IEEE.

关键词： Road and street markings

Two-dimensional Platinum Diselenide Waveguide-Integrated Infrared Photodetectors

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Parhizkar, Shayan Prechtl, Maximilian Giesecke, Anna-Lena Suckow, Stephan Wahl, Sophia Lukas, Sebastian Hartwig, Oliver Negm, Nour Quellmalz, Arne Gylfason, Kristinn B. Schall, Daniel Wuttig, Matthias Duesberg, Georg S. Lemme, Max C. Chair of Electronic Devices RWTH Aachen University Otto-Blumenthal-Str. 2 Aachen52074 Germany AMO GmbH Advanced Microelectronic Center Aachen Otto-Blumenthal-Str. 25 Aachen52074 Germany Center for Integrated Sensor Systems University of the Bundeswehr Munich Neubiberg85577 Germany Institute of Physics IA RWTH Aachen University Aachen52074 Germany Division of Micro and Nanosystems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology StockholmSE-10044 Sweden Black Semiconductor GmbH Schloss-Rahe-Str. 15 Aachen52072 Germany

Low cost, easily integrable photodetectors (PDs) for silicon (Si) photonics are still a bottleneck for photonic integrated circuits (PICs), especially for wavelengths above 1.8 µm. Multilayered platinum diselenide (PtSe2) is a semi-metallic two-dimensional (2D) material that can be synthesized below 450°C. We integrate PtSe2 based PDs directly by conformal growth on Si waveguides. The PDs operate at 1550 nm wavelength with a maximum responsivity of 11 mA/W and response times below 8.4 µs. Fourier transform infrared spectroscopy (FTIR) in the wavelength range from 1.25 µm to 28 µm indicates the suitability of PtSe2 for PDs far into the infrared wavelength range. Our PtSe2 PDs integrated by direct growth outperform PtSe2 PDs manufactured by standard 2D layer transfer. The combination of IR responsivity, chemical stability, selective and conformal growth at low temperatures, and the potential for high carrier mobility, make PtSe2 an attractive 2D material for optoelectronics and PICs. Copyright © 2021, The Authors. All rights reserved.

关键词： Selenium compounds

High resolution radar-based occupancy grid mapping and free space detection 4

学校读者我要写书评

暂无评论

High resolution radar-based occupancy grid mapping and free ...

4th International Conference on Vehicle Technology and Intelligent Transport systems, VEHITS 2018

作者： Li, Mingkang Feng, Zhaofei Stolz, Martin Kunert, Martin Henze, Roman Küçükay, Ferit Advanced Engineering Sensor Systems Robert Bosch GmbH Daimlerstr. 6 Leonberg71229 Germany Institute of Automotive Engineering Technische Universität Braunschweig Hans-Sommer-Str. 4 Braunschweig38106 Germany

ISBN: (纸本)9789897582936

The high-resolution radar sensors have the ability to detect thousands of reflection points per cycle, which promotes the perception capability on a pixel level similar to video systems. In this paper, an occupancy grid map is created to model the static environment. The reflection amplitudes of all detection points are compensated, normalized, and then converted to the detection probability based on a radar sensor model. According to the movement of the ego vehicle, the a posteriori occupancy probability is computed to build the occupancy grid map. Thereafter the occupancy grid map is converted to the binary grid map, where the grids in the obstacle areas are defined as occupied. In order to eliminate the outliers, the connected occupied grids are clustered using the Connected-Component Labelling algorithm. Through the Moore-Neighbour Tracing algorithm the boundaries of the clustered occupied grids are recognized. Based on the boundaries, the interval-based free space detection is performed using the Bresenham's line algorithm. As mentioned, the occupancy grid map and the free space detection results obtained from radar road measurements match with the real scenarios. Copyright © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.

关键词： Radar measurement

Conditional physics informed neural networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kovacs, Alexander Exl, Lukas Kornell, Alexander Fischbacher, Johann Hovorka, Markus Gusenbauer, Markus Breth, Leoni Oezelt, Harald Yano, Masao Sakuma, Noritsugu Kinoshita, Akihito Shoji, Tetsuya Kato, Akira Schrefl, Thomas Christian Doppler Laboratory for Magnet Design Through Physics Informed Machine Learning Viktor Kaplan-Straße 2E Wiener Neustadt2700 Austria Department for Integrated Sensor Systems Danube University Krems Viktor Kaplan-Straße 2E Wiener Neustadt2700 Austria Department of Mathematics University of Vienna Oskar-Morgenstern-Platz 1 Vienna1090 Austria Wolfgang Pauli Institute Oskar-Morgenstern-Platz 1 Vienna1090 Austria Research Platform MMM Mathematics-Magnetism-Materials Oskar-Morgenstern-Platz 1 Vienna1090 Austria Advanced Materials Engineering Div. Toyota Motor Corporation 1200 Mishuku Susono Shizuoka410-1193 Japan

We introduce conditional PINNs (physics informed neural networks) for estimating the solution of classes of eigenvalue problems. The concept of PINNs is expanded to learn not only the solution of one particular differential equation but the solutions to a class of problems. We demonstrate this idea by estimating the coercive field of permanent magnets which depends on the width and strength of local defects. When the neural network incorporates the physics of magnetization reversal, training can be achieved in an unsupervised way. There is no need to generate labeled training data. The presented test cases have been rigorously studied in the past. Thus, a detailed and easy comparison with analytical solutions is made. We show that a single deep neural network can learn the solution of partial differential equations for an entire class of *** Codes I.2.6 Copyright © 2021, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions