Display:

Results

Viewing 31 to 60 of 16558
2017-09-23
Technical Paper
2017-01-1967
Wei Liu, Huan Tian, Jun Hu, Shuai Cheng, Huai Yuan
Abstract Image segmentation is critical in autonomous driving field. It can reveal essential clues such as objects’ shape or boundary information. The information, moreover, can be leveraged as input information of other tasks: vehicle detection, for example, or vehicle trajectory prediction. SegNet, one deep learning based segmentation model proposed by Cambridge, has been a public baseline for scene perception tasks. It, however, suffers an accuracy deficiency in objects marginal area. Segmentation of this area is very challenging with current models. To alleviate the problem, in this paper, we propose one edge enhanced deep learning based model. Specifically, we first introduced one simple, yet effective Artificial Interfering Mechanism (AIM) which feeds segmentation model manual extracted key features. We argue this mechanism possesses the ability to enhance essential features extraction and hence, ameliorate the model performance.
2017-09-23
Technical Paper
2017-01-1971
Sihan Chen, Libo Huang, Xin Bi, Jie Bai
Abstract For sensing system, the trustworthiness of the variant sensors is the crucial point when dealing with advanced driving assistant system application. In this paper, an approach to a hybrid camera-radar application of vehicle tracking is presented, able to meet the requirement of such demand. Most of the time, different types of commercial sensors available nowadays specialize in different situations, such as the ability of offering a wealth of detailed information about the scene for the camera or the powerful resistance to the severe weather for the millimeter-wave (MMW) radar. The detection and tracking in different sensors are usually independent. Thus, the work here that combines the variant information provided by different sensors is indispensable and worthwhile. For the real-time requirement of merging the measurement of automotive MMW radar in high speed, this paper first proposes a fast vehicle tracking algorithm based on image perceptual hash encoding.
2017-09-23
Technical Paper
2017-01-1974
Tao Chen, Jie Bai, Fang Wang, Libo Huang
Abstract In the last years, in order to fit the requirements of automotive radar application under the multi-target conditions, several proposals about Continuous Waveform (CW)have been developed. The transmit signal with Multiple Frequency Shift Keying (MFSK) technology was developed to analyze the target information in range domain and Doppler frequency domain simultaneously, but the MFSK waveform has lower estimation accuracy in phase measuring. A higher accuracy signal type is the chirp sequence waveform of monopulse radar, which is based on two-dimension independent frequency measuring. It can also get the range and velocity information, but might lead to ambiguities in Doppler domain. To avoid the Doppler ambiguity, a method is proposed in this paper, which uses the modified chirp sequence waveform. The carrier frequencies of the modified chirp sequence are different, which causes the Doppler frequency offset.
2017-09-23
Technical Paper
2017-01-1973
Yang Yin, Xin Bi, Libo Huang, Shitao Yan
Abstract Millimeter wave (MMW) automotive radar plays an important role in the advanced driving assistance system (ADAS), which detects vehicles, pedestrians and other obstacles. In the adaptive cruise control (ACC) and the automatic emergency brake (AEB) system, the target needs to be oriented. One of the automotive radar’s task is to get the direction information which includes the range, speed, azimuth and height of the target by high intermediate frequency (IF) signal sampling rate. In order to solve the problem of high sampling rate for the MMW radar caused by the traditional Nyquist sampling theorem when the target is located, a new method based on the compressed sensing (CS) for the target location is proposed in this paper. This paper presents the linear frequency modulated continuous wave (LFMCW) model and simulates the sampling and reconstruction of the radar’s IF signal via CS technique by using MATLAB.
2017-09-23
Technical Paper
2017-01-1977
Xin Bi, Bin Tan, Zhijun Xu, Libo Huang
Abstract Vehicle and pedestrian detection technology is the most important part of advanced driving assistance system (ADAS) and automatic driving. The fusion of millimeter wave radar and camera is an important trend to enhance the environmental perception performance. In this paper, we propose a method of vehicle and pedestrian detection based on millimeter wave radar and camera. Moreover, the proposed method complete the detection of vehicle and pedestrian based on dynamic region generated by the radar data and sliding window. First, the radar target information is mapped to the image by means of coordinate transformation. Then by analyzing the scene, we obtain the sliding windows. Next, the sliding windows are detected by HOG features and SVM classifier in a rough detect. Then using the match function to confirm the target. Finally detecting the windows in a precision detection and merging the detecting windows.
2017-09-23
Technical Paper
2017-01-1975
Wenhui Li, Wenlan Li, Jialun Liu, Yuhao Chen
Abstract Vehicle detection has been a fundamental problem in the research of Intelligent Traffic System (ITS), especially in urban driving environment. Over the past decades, vision-based vehicle detection has got a considerable attention. In addition to the rich appearance information, the stereo vision method also provides depth information, which could achieve higher accuracy and precision. In this paper, a hybrid method for stereo vision-based real-time vehicle detection in urban environment is proposed. Firstly, we extract vehicle features and generate the Region of Interest (ROI). Semi-global Matching (SGM) algorithm is then utilized on the ROIs to generate disparity maps and get the depth information, which could be used to compute the width of each ROI. The noise regions, always with obvious depth variation in the disparity maps are excluded by the clustering approach.
2017-09-23
Technical Paper
2017-01-1981
Bing Zhu, Weinan Li, Ning Bian, Jian Zhao, Weiwen Deng
Abstract Driver individualities is crucial for the development of the Advanced Driver Assistant System (ADAS). Due to the mechanism that specific driving operation action of individual driver under typical conditions is convergent and differentiated, a novel driver individualities recognition method is constructed in this paper using random forest model. A driver behavior data acquisition system was built using dSPACE real-time simulation platform. Based on that, the driving data of the tested drivers were collected in real time. Then, we extracted main driving data by principal component analysis method. The fuzzy clustering analysis was carried out on the main driving data, and the fuzzy matrix was constructed according to the intrinsic attribute of the driving data. The drivers’ driving data were divided into multiple clusters.
2017-09-23
Technical Paper
2017-01-1982
Xiaoming Lan, Hui Chen, Xiaolin He, Jiachen Chen, Yosuke Nishimura, Kazuya Ando, Kei Kitahara
Abstract In the recent years, the interaction between human driver and Advanced Driver Assistance System (ADAS) has gradually aroused people’s concern. As a result, the concept of personalized ADAS is being put forward. As an important system of ADAS, Lane Keeping Assistance System (LKAS) also attracts great attention. To achieve personalized LKAS, driver lane keeping characteristic (DLKC) indices which could distinguish different driver lane keeping behavior should be researched. However, there are few researches on DLKC indices for personalized LKAS. Although there are many researches on modeling driver steering behavior, these researches are not sufficient to obtain DLKC indices. One reason is that most of researches are for double lane change behavior which is different from driver lane keeping behavior.
2017-09-23
Technical Paper
2017-01-1989
Yi Chen, Gaoxiang Lin, Ying He
Abstract Chinese National projects “13th Five Year Plan” and “Made in China 2025” have both put forward a goal of developing Intelligent and Connected Vehicles(ICV). Shanghai is a typical city of automobile industry which spearhead the development of China’s ICV industry. After the adjustment and transition of industrial structure, Shanghai has initially formed the industrialization layout of ICV covering core areas including environmental perception, intelligent decision-making, actuator, human-computer interaction and vehicle integration. However, currently Shanghai is still in the beginning stage and there exists a large gap with world advanced level in both the core technology and marketization. This article is based on former qualitative survey combined with quantitative analysis which uses the Analytic Hierarchy Process(AHP) method to objectively evaluate the status quo and development trend of Shanghai’s ICV.
2017-09-23
Technical Paper
2017-01-1991
Adit Joshi
The automotive industry is heading towards the path of autonomy with the development of autonomous vehicles. An autonomous vehicle consists of two main components. The first is the software which is responsible for the decision-making capabilities of the system. The second is the hardware which encompasses all aspects of the physical vehicle which are responsible for vehicle motion such as the engine, brakes and steering subsystems along with their corresponding controls. This component forms the basis of the autonomous vehicle platform. For SAE Level 4 autonomous vehicles, where an automated driving system is responsible for all the dynamics driving tasks including the fallback driving performance in case of system faults, redundant mechanical systems and controls are required as part of the autonomous vehicle platform since the driver is completely out of the loop with respect to driving.
2017-09-23
Technical Paper
2017-01-1994
Adit Joshi
The advancement towards development of autonomy follows either the bottom-up approach of gradually improving and expanding existing Advanced Driver Assist Systems (ADAS) technology where the driver is present in the control loop or the top-down approach of directly developing Autonomous Vehicles (AV) hardware and software using alternative approaches without the driver present in the control loop. Most ADAS systems today fall under the classification of SAE Level 1 which is also referred to as the driver assistance level. The progression from SAE Level 1 to SAE Level 2 or partial automation involves the critical task of merging autonomous lateral control and autonomous longitudinal control such that the tasks of steering and acceleration/deceleration are not required to be handled by the driver under certain conditions [1].
2017-09-23
Technical Paper
2017-01-1992
Qin Xia, Jianli Duan, Feng Gao, Tao Chen, Cai Yang
Abstract ADAS must be tested thoroughly before they can be deployed for series production. Comparing with road and field test, bench test has been widely used owing to its advantages of less labor costs, more controllable scenarios, etc. However, there is no satisfied systematic approach to generate high-efficiency and full-coverage test scenarios automatically because of its integration of human, vehicle and traffic. Most of the test scenarios generated by the existing methods are either too simple or too few to be able to achieve full coverage of requirements. Besides, the cost is high when the ET method is used. To solve the aforementioned problems, an automatic test scenario generation method based on complexity for bench test is presented in this paper. Firstly, considering the fact that the device is easier to malfunction under complex cases, an index measuring the complexity of test case is proposed by using the method of AHP.
2017-09-23
Technical Paper
2017-01-1997
Cui Hua
Abstract Vision based driving environment perception is current research hotspot in automatic driving field, which has made great progress due to the continuous breakthroughs in the research of deep neural network. As is well known, deep neural network has won tremendous successes in a wide variety of image recognition tasks, such as pedestrian detection and vehicle identification, which have accomplished the commercialization successfully in intelligent monitor system. Nevertheless, driving environment perception has a higher request for the generalization performance of deep neural network, which needs further studies on its design and training methods. In this paper, we presented a new boosted deep neural network in order to improve its generalization performance and meanwhile keep computational budget constant. Above all, the most representative methods to improve the generalization performance of deep neural network were introduced.
2017-09-23
Technical Paper
2017-01-1998
Shun Yang, Weiwen Deng, Zhenyi Liu, Ying Wang
Abstract Intelligent driving, aimed for collision avoidance and self-navigation, is mainly based on environmental sensing via radar, lidar and/or camera. While each of the sensors has its own unique pros and cons, camera is especially good at object detection, recognition and tracking. However, unpredictable environmental illumination can potentially cause misdetection or false detection. To investigate the influence of illumination conditions on detection algorithms, we reproduced various illumination intensities in a photo-realistic virtual world, which leverages recent progress in computer graphics, and verified vehicle detection effect there. In the virtual world, the environmental illumination is controlled precisely from low to high to simulate different illumination conditions in the driving scenarios (with relative luminous intensity from 0.01 to 400). Sedan cars with different colors are modelled in the virtual world and used for detection task.
2017-09-23
Technical Paper
2017-01-2005
Zhihong Wu, Jian_ning Zhao, Yuan Zhu, Qingchen Li
Abstract Vehicle cybersecurity consists of internal security and external security. Dedicated security hardware will play an important role in car’s internal and external security communication. TPM (Trusted Platform Module) can serve as the security cornerstone when vehicle connects with external entity or constructs a trusted computing environment. Based on functions such as the storage of certificate, key derivation and integrity testing, we research the principle of how to construct a trusted environment in a vehicle which has telematics unit. HSM (Hardware Security Module) can help to realize the onboard cryptographic communication securely and quickly so as to protect data. For certain AURIX MCU consisting of HSM, the experiment result shows that cheaper 32-bit HSM’s AES calculating speed is 25 times of 32-bit main controller, so HSM is an effective choice to realize cybersecurity.
2017-09-23
Technical Paper
2017-01-2007
Fang Li, Lifang Wang, Yan Wu
Abstract With the rapid development of vehicle intelligent and networking technology, the IT security of automotive systems becomes an important area of research. In addition to the basic vehicle control, intelligent advanced driver assistance systems, infotainment systems will all exchange data with in-vehicle network. Unfortunately, current communication network protocols, including Controller Area Network (CAN), FlexRay, MOST, and LIN have no security services, such as authentication or encryption, etc. Therefore, the vehicle are unprotected against malicious attacks. Since CAN bus is actually the most widely used field bus for in-vehicle communications in current automobiles, the security aspects of CAN bus is focused on. Based on the analysis of the current research status of CAN bus network security, this paper summarizes the CAN bus potential security vulnerabilities and the attack means.
2017-09-23
Technical Paper
2017-01-2002
Yang Yang Wang, Guangda Chen, Xuanjing Ao, Shuhao Fan, Han Mei, Wei Li
Abstract After obtaining the optimal trajectory through the lane change decision and trajectory planning, the last key technology for the automatic lane change assist system is to carry out the precise and rapid steering actuation according to the front wheel angle demand. Therefore, an automatic lane change system model including a BLDCM (brushless DC motor) model, a steering system model and a vehicle dynamics model is first established in this paper. Electromagnetic characteristics of the motor, the moment of the inertia and viscous friction etc. are considered in these models. Then, a SMC (Sliding Mode Control) algorithm for the steering system is designed to follow the steering angle input. The control torque of the steering motor is obtained through the system model according to steering angle demand. After that, the control current is calculated considering of electromagnetic characteristics of the BLDCM.
2017-09-23
Technical Paper
2017-01-2004
Yangyang Wang, Rong Feng, Ding Pan, Zhiguang Liu, Nan Wu, Wei Li
Abstract The automatic lane change assist system is an intelligent driving assistance technology oriented to traffic safety, which requires trajectory planning of the lane change maneuver based on the lane change decision. A typical scene of lane change for overtaking is selected, where the front vehicle in the same lane and the rear vehicle in the left lane are deemed to be potential dangerous vehicles through the lane change. Lane change trajectory equation is first established according to the general law of steering wheel angle through lane changes. Based on the relative position, velocity and acceleration information of the dangerous vehicles and the lane change vehicle, motions of these surrounding dangerous vehicles are predicted. At the same time, a multi-objective optimization function is established based on the relative longitudinal safety boundary. The objectives are the minimum safety distance, the lane change time and the front wheel angle.
2017-09-23
Technical Paper
2017-01-2011
Suyash Singh, Ankur Mathur, Sandeep Das, Purnendu Sinha, Vinay Singh
Abstract In the Smart Cities, main objective is to promote cities that provide core infrastructure and give a decent quality of life to its citizens, a clean and sustainable environment and application of ‘Smart’ Solutions. The process said for utilization of available resources is the best fit for our concept. Our concept is to convert and refurbish the old and scrap vehicles which will increase their longevity and can be used in any smart city in India or abroad. The ultimate aim to provide this technology for the development of any new smart city in India is the utilization of available resources and reduction in the junk materials and environmental pollution. Refurbishing the old and scrap vehicles with replacement of IC engines doesn’t mean that they will be kept as a scrap and be thrown away, our idea is to utilize maximum of all the available resources. The IC engines taken out of these vehicles will be re-used appropriately.
2017-09-23
Technical Paper
2017-01-2010
Junfeng Yang, Michael Ward, Jahangir Akhtar‎
Abstract The Connected and Autonomous Vehicles (CAVs) promise huge economic, social and environmental benefits. The autonomous vehicles supposed to be safer than human drivers. However, the advanced systems and complex levels of automation could also bring accidents by tiny faults of hardware or errors of software. To achieve complete safety, a safety case providing guidance on the identification and classification of hazardous events, and the minimization of these risks needs to be developed throughout the entire development lifecycle process of CAVs. A comprehensible and valid safety case has to employ appropriate safety approaches complying with the automotive functional safety requirements in ISO 26262.
2017-09-23
Journal Article
2017-01-1966
Min Ke, Bing Zhu, Jian Zhao, Weiwen Deng
Abstract Knowledge of intelligent vehicle absolute position is a vital premise for the implementation of decision programming, kinematic and dynamics control. In order to achieve high accuracy positioning and reduce running cost as much as possible under all operating conditions, this paper proposed an integrated positioning method based on GPS and Ultra Wide Band(UWB) for intelligent vehicle’s navigation and position system. In this method, GPS and UWB are alternately active according to the confidence level of GPS signal. When the vehicle is traveling in a wide-open area and GPS signal is well received, the positioning results of Dead Reckoning system are corrected by the low frequency positioning output from GPS. During the correcting process, in order to realize the better fusion of measurement data, a simplified federal Kalman filter was designed by using indirect method.
2017-09-23
Journal Article
2017-01-1969
Yuanxin Zhong, Sijia Wang, Shichao Xie, Zhong Cao, Kun Jiang, Diange Yang
Abstract Real-time reconstruction of 3D environment attributed with semantic information is significant for a variety of applications, such as obstacle detection, traffic scene comprehension and autonomous navigation. The current approaches to achieve it are mainly using stereo vision, Structure from Motion (SfM) or mobile LiDAR sensors. Each of these approaches has its own limitation, stereo vision has high computational cost, SfM needs accurate calibration between a sequences of images, and the onboard LiDAR sensor can only provide sparse points without color information. This paper describes a novel method for traffic scene semantic segmentation by combining sparse LiDAR point cloud (e.g. from Velodyne scans), with monocular color image. The key novelty of the method is the semantic coupling of stereoscopic point cloud with color lattice from camera image labelled through a Convolutional Neural Network (CNN).
2017-09-23
Journal Article
2017-01-1970
Guizhen Yu, Zhangyu Wang, Xinkai Wu, Yalong Ma, Yunpeng Wang
Abstract: In this paper, an efficient lane detection using deep feature extraction method is proposed to achieve real-time lane detection in diverse road environment. The method contains three main stages: 1) pre-processing, 2) deep lane feature extraction and 3) lane fitting. In pre-processing stage, the inverse perspective mapping (IPM) is used to obtain a bird's eye view of the road image, and then an edge image is generated using the canny operator. In deep lane feature extraction stage, an advanced lane extraction method is proposed. Firstly, line segment detector (LSD) is applied to achieve the fast line segment detection in the IPM image. After that, a proposed adaptive lane clustering algorithm is employed to gather the adjacent line segments generated by the LSD method. Finally, a proposed local gray value maximum cascaded spatial correlation filter (GMSF) algorithm is used to extract the target lane lines among the multiple lines.
2017-09-23
Journal Article
2017-01-1972
Sen Li, Xin Bi, Libo Huang, Bin Tan
Abstract In Advanced Driver Assistant System (ADAS), the automotive radar is used to detect targets or obstacles around the vehicle. The procedure of Constant False Alarm Rate (CFAR) plays an important role in adaptive targets detection in noise or clutter environment. But in practical applications, the noise or clutter power is absolutely unknown and varies over the change of range, time and angle. The well-known cell averaging (CA) CFAR detector has a good detection performance in homogeneous environment but suffers from masking effect in multi-target environment. The ordered statistic (OS) CFAR is more robust in multi-target environment but needs a high computation power. Therefore, in this paper, a new two-dimension CFAR procedure based on a combination of Generalized Order Statistic (GOS) and CA CFAR named GOS-CA CFAR is proposed. Besides, the Linear Frequency Modulation Continuous Wave (LFMCW) radar simulation system is built to produce a series of rapid chirp signals.
2017-09-23
Technical Paper
2017-01-1978
Yuxiang Feng, Simon Pickering, Edward Chappell, Pejman iravani PhD, Chris Brace
Abstract The major contribution of this paper is to propose a low-cost accurate distance estimation approach. It can potentially be used in driver modelling, accident avoidance and autonomous driving. Based on MATLAB and Python, sensory data from a Continental radar and a monocular dashcam were fused using a Kalman filter. Both sensors were mounted on a Volkswagen Sharan, performing repeated driving on a same route. The established system consists of three components, radar data processing, camera data processing and data fusion using Kalman filter. For radar data processing, raw radar measurements were directly collected from a data logger and analyzed using a Python program. Valid data were extracted and time stamped for further use. Meanwhile, a Nextbase monocular dashcam was used to record corresponding traffic scenarios. In order to measure headway distance from these videos, object depicting the leading vehicle was first located in each frame.
2017-09-23
Technical Paper
2017-01-1952
ChengJun Ma, Fang Li, Chenglin Liao, Lifang Wang
Abstract With the load of urban traffic system becomes more serious, the Automatic Parking System (APS) plays an important role in alleviating the burden of drivers and improving vehicle safety. The APS is consisted of environmental perception, path planning and path following. The path following controls the lateral movement of vehicle during the parking process, and requires the trajectory tracking error to be as small as possible. At present, some control algorithms are used including PID control, pure pursuit control, etc. However, these algorithms relying heavily on parameters and environment, have some problems such as slow response and low precision. To solve this problem, a path following control method based on Model Predictive Control (MPC) algorithm is proposed in this paper. Firstly, Kinematic vehicle model and path tracker based on MPC algorithm are built. Secondly, a test bench that composed of CANoe hardware in the loop (HIL) system and steering wheel system is built.
2017-09-19
Technical Paper
2017-01-2020
Michael Croegaert
Abstract Modern military aircraft platforms are using more and more power which results in an ever increasing power density (SWaP). This in turn, generates more heat that has to be dissipated from the instrument panel and cockpit of the aircraft. Complicating this further is that the use of structural composites which are not efficient conductors of heat and the mission requirements of small heat signatures. Therefore alternative means of extracting the heat from the avionics systems must be used. Liquid cooled systems have the advantage over air cooled systems of a much higher heat transfer rate and the fact that the heat can be transported a significant distance from the source. Liquid cooled avionics have their own challenges as well.
2017-09-19
Technical Paper
2017-01-2028
Steven Nolan, Patrick Norman, Graeme Burt, Catherine Jones
Abstract Turbo-electric distributed propulsion (TeDP) for aircraft allows for the complete redesign of the airframe so that greater overall fuel burn and emissions benefits can be achieved. Whilst conventional electrical power systems may be used for smaller aircraft, large aircraft (~300 pax) are likely to require the use of superconducting electrical power systems to enable the required whole system power density and efficiency levels to be achieved. The TeDP concept requires an effective electrical fault management and protection system. However, the fault response of a superconducting TeDP power system and its components has not been well studied to date, limiting the effective capture of associated protection requirements. For example, with superconducting systems it is possible that a hotspot is formed on one of the components, such as a cable. This can result in one subsection, rather than all, of a cable quenching.
2017-09-19
Technical Paper
2017-01-2030
Benjamin Cheong, Paolo Giangrande, Patrick Wheeler, Pericle Zanchetta, Michael Galea
Abstract High power density for aerospace motor drives is a key factor in the successful realization of the More Electric Aircraft (MEA) concept. An integrated system design approach offers optimization opportunities, which could lead to further improvements in power density. However this requires multi-disciplinary modelling and the handling of a complex optimization problem that is discrete and nonlinear in nature. This paper proposes a multi-level approach towards applying random heuristic optimization to the integrated motor design problem. Integrated optimizations are performed independently and sequentially at different levels assigned according to the 4-level modelling paradigm for electric systems. This paper also details a motor drive sizing procedure, which poses as the optimization problem to solve here. Finally, results comparing the proposed multi-level approach with a more traditional single-level approach is presented for a 2.5 kW actuator motor drive design.
2017-09-19
Technical Paper
2017-01-2048
Bryan Shambaugh, Patrick Browning
Abstract In this research, the magnetoplasmadynamic (MPD) effects of applying a toroidal magnetic field around an ionized exhaust plume were investigated to manipulate the exhaust profile of the plasma jet under near vacuum conditions. Tests for this experiment were conducted using the West Virginia University (WVU) Hypersonic Arc Jet Wind Tunnel. A series of twelve N52 grade neodymium magnets were placed in different orientations around a steel toroid mounted around the arc jet’s exhaust plume. Four different magnet orientations were tested in this experiment. Two additional configurations were run as control tests without any imposed magnetic fields surrounding the plume. Each test was documented using a set of 12 photographs taken from a fixed position with respect to the flow. The photographic data was analyzed by comparing images of the exhaust plume taken 10, 20, and 30 seconds after the plasma jet was activated.
Viewing 31 to 60 of 16558