Display:

Results

Viewing 241 to 270 of 16574
2017-03-28
Technical Paper
2017-01-0043
Michael Smart, Satish Vaishnav, Steven Waslander
Abstract Robust lane marking detection remains a challenge, particularly in temperate climates where markings degrade rapidly due to winter conditions and snow removal efforts. In previous work, dynamic Bayesian networks with heuristic features were used with the feature distributions trained using semi-supervised expectation maximization, which greatly reduced sensitivity to initialization. This work has been extended in three important respects. First, the tracking formulation used in previous work has been corrected to prevent false positives in situations where only poor RANSAC hypotheses were generated. Second, the null hypothesis is reformulated to guarantee that detected hypotheses satisfy a minimum likelihood. Third, the computational requirements have been greatly reduced by computing an upper bound on the marginal likelihood of all part hypotheses upon generation and rejecting parts with an upper bound less likely than the null hypothesis.
2017-03-28
Technical Paper
2017-01-0110
Hao Sun, Weiwen Deng, Chen Su, Jian Wu
Abstract The ability to recognize traffic vehicles’ lane change maneuver lays the foundation for predicting their long-term trajectories in real-time, which is a key component for Advanced Driver Assistance Systems (ADAS) and autonomous automobiles. Learning-based approach is powerful and efficient, such approach has been used to solve maneuver recognition problems of the ego vehicles on conventional researches. However, since the parameters and driving states of the traffic vehicles are hardly observed by exteroceptive sensors, the performance of traditional methods cannot be guaranteed. In this paper, a novel approach using multi-class probability estimates and Bayesian inference model is proposed for traffic vehicle lane change maneuver recognition. The multi-class recognition problem is first decomposed into three binary problems under error correcting output codes (ECOC) framework.
2017-03-28
Technical Paper
2017-01-0099
Jose E. Solomon, Francois Charette
Abstract The proposed technique is a tailored deep neural network (DNN) training approach which uses an iterative process to support the learning of DNNs by targeting their specific misclassification and missed detections. The process begins with a DNN that is trained on freely available annotated image data, which we will refer to as the Base model, where a subset of the categories for the classifier are related to the automotive theater. A small set of video capture files taken from drives with test vehicles are selected, (based on the diversity of scenes, frequency of vehicles, incidental lighting, etc.), and the Base model is used to detect/classify images within the video files. A software application developed specifically for this work then allows for the capture of frames from the video set where the DNN has made misclassifications. The corresponding annotation files for these images are subsequently corrected to eliminate mislabels.
2017-03-28
Technical Paper
2017-01-0065
Bülent Sari, Hans-Christian Reuss
Abstract Safety is becoming more and more important with the ever increasing level of safety related E/E Systems built into the cars. Increasing functionality of vehicle systems through electrification of power train and autonomous driving leads to complexity in designing system, hardware, software and safety architecture. The application of multicore processors in the automotive industry is becoming necessary because of the needs for more processing power, more memory and higher safety requirements. Therefore it is necessary to investigate the safety solutions particularly for Automotive Safety Integrity Level (ASIL-D) Systems. This brings additional challenges because of additional requirements of ISO 26262 for ASIL-D safety concepts. This paper presents an approach for model-based “dependent failure analysis” which is required from ISO 26262 for ASIL-D safety concepts with decomposition approach.
2017-03-28
Technical Paper
2017-01-0103
Thomas Beyerl, Bernard Ibru, Charvi Popat, Deborah Ojo, Alexander Bakus, Jessica Elder, Valentin Soloiu
Abstract Autonomous vehicles must possess the capability to navigate complex intersections, which do not conform to typical models. Such intersections may have multiple roadways of different classes, highly acute angles, or unique multi-modal combinations. These may include railway grade crossings, bicycle lanes, or unique signal arrangements. Conventional navigation systems, which gather data from the surrounding area then plan a path through the collected data require faultless and complex analysis of extremely unstructured environments. The vehicle must then avoid obstacles as well as successfully navigate the intersection with extremely low tolerance for error. Computer decision making challenges can arise from this method of navigation, especially when interacting with non-autonomous vehicles.
2017-03-28
Technical Paper
2017-01-0116
Ankit Goila, Ambarish Desai, Feng Dang, Jian Dong, Rahul Shetty, Rakesh Babu Kailasa, Mahdi Heydari, Yang Wang, Yue Sun, Manikanta Jonnalagadda, Mohammed Alhasan, Hanlong Yang, Katherine R. Lastoskie
ADAS features development involves multidisciplinary technical fields, as well as extensive variety of different sensors and actuators, therefore the early design process requires much more resources and time to collaborate and implement. This paper will demonstrate an alternative way of developing prototype ADAS concept features by using remote control car with low cost hobby type of controllers, such as Arduino Due and Raspberry Pi. Camera and a one-beam type Lidar are implemented together with Raspberry Pi. OpenCV free open source software is also used for developing lane detection and object recognition. In this paper, we demonstrate that low cost frame work can be used for the high level concept algorithm architecture, development, and potential operation, as well as high level base testing of various features and functionalities. The developed RC vehicle can be used as a prototype of the early design phase as well as a functional safety testing bench.
2017-03-28
Technical Paper
2017-01-0114
Jorge De-J. Lozoya Santos, J. C. Tudon-Martinez
Abstract The project consists on the mechanical and electronic instrumentation of an existing vehicle (built at Universidad de Monterrey for the SAE Supermileage Competition) to be able to control its steering, braking and throttle systems “by wire”. Insight to the stages of turning the vehicle into an autonomous one is presented. This includes identification of the current mechanical properties, choosing adequate components and the use of a simulation to allow early work on the software involving cameras and motors to provide autonomy to the vehicle. Using software in the loop methodology mathematical models of the dynamics of the vehicle are run in Simulink and update the position and orientation of the 3D model of the vehicle in V-REP, a robot simulator.
2017-03-28
Technical Paper
2017-01-0238
Velappan Shalini, Sridharan Krishnamurthy, Srinivasan Narasimhan
Abstract This study compares the model efficacy of Neural Network and Vector Auto Regression. Further it also analyses the impact of predictors controlling for total industry volume. Understanding both the methodologies has their distinctive advantages and disadvantages. Our empirical findings indicate that based on the characteristics of data such as non-stationary, non-linearity and non-normality paves the way for use of machine learning algorithm relative to econometrics technique. Our results suggest that data type and its characteristics are more important in determining the methodology than the methodology itself. In industry, econometrics methodologies are widely used due to their usage simplicity and its ability to explain the relationships in simple terms.
2017-03-28
Technical Paper
2017-01-0240
Yanli Zhao, Hao Zhou, Yimin Liu
Abstract Ride Hailing service and Dynamic Shuttle are two key smart mobility practices, which provide on-demand door-to-door ride-sharing service to customers through smart phone apps. On the other hand, some big companies spend millions of dollars annually in third party vendors to offer shuttle services to pick up and drop off employees at fixed locations and provide them daily commutes for employees to and from work. Efficient fixed routing algorithms and analytics are the key ingredients for operating efficiency behind these services. They can significantly reduce operating costs by shortening bus routes and reducing bus numbers, while maintaining the same quality of service. This study developed an off-line optimization routing method for employee shuttle services including regular work shifts and demand based shifts (e.g. overtime shifts) in some regions.
2017-03-28
Technical Paper
2017-01-1147
Hyunjun Kim, Jingeon Kang, Dongsuk Kum
Abstract Input- and output-split hybrids using a single planetary gear (PG) can provide high fuel economy, but they tend to suffer from low acceleration performance. In order to improve their acceleration performance, speed reduction (multiplication) gears (SRG/SMG) have often been employed in various mass-produced split hybrids. In fact, adding one SRG (SMG) to input- or output-split hybrids can improve not only the acceleration performance, but also the fuel economy. Nevertheless, the full potentials of using SRGs (SMGs) have not yet been thoroughly investigated because the design space of input- and output-split configurations using one SRG (SMG) is huge; 432 configurations can be generated using two PGs where one PG is used as an SRG/SMG. Thus, in order to investigate the impacts of SRG (SMG) within a reasonable time, an efficient analysis procedure is required.
2017-03-28
Technical Paper
2017-01-1228
Masaya Nakanishi
Abstract Alternator, which supplies electric energy to a battery and electrical loads when it is rotated by engine via belt, is one of key components to improve vehicle fuel efficiency. We have reduced rectification loss from AC to DC with a MOSFET instead of a rectifier diode. It is important to turn on the MOSFET and off during a rectification period, called synchronous control, to avoid a current flow in the reverse direction from the battery. We turn it off so as to remain a certain conduction period through a body diode of the MOSFET before the rectification end. It is controlled by making a feedback process to coincide with an internal target conduction period based on the rotational speed of the alternator. We reduced a voltage surge risk at turn-off by changing the feedback gain depending on the sign of the time difference between the measured period and the target.
2017-03-28
Technical Paper
2017-01-1247
Mohammed Khorshed Alam, Lihua Chen, Yan Zhou, Fan Xu, Shuitao Yang
Abstract Direct bypass to DC-DC boost converter in traction inverter increases converter's capability and efficiency significantly by providing a lower loss path for power flow between the battery and DC-link terminal. A bypass using diode is an excellent solution to achieve this capability at low cost and system complexity. Bypass diode operates in the linear operating region (DC Q-point) when the battery discharges through the bypass diode to drive the electric motors. Therefore, thermal stress on the DC-link capacitor is shared between the input and DC-link capacitors through the bypass diode. On the other hand, inverters introduce voltage oscillation in the DC-link terminal which results in unwanted energy oscillation through the bypass diode during battery charging. Both of these phenomena have been explained in details.
2017-03-28
Technical Paper
2017-01-1251
Bin Zhou, Jeffrey Burl, Amir Rezaei
Abstract This paper presents results on how the Equivalent Consumption Minimization Strategy (ECMS) penalty factor effects Lithium ion battery aging. The vehicle studied is the Honda Civic Hybrid. The battery used is A123 Systems’. Vehicle simulation using multiple combinations of highway and city drive cycles. For each combination of drive cycles, six ECMS penalty factor values are used. Battery aging is evaluated using a semi-empirical model combined with accumulated Ah-throughput method which uses, as an input, the battery state of charge trajectory from the vehicle simulations. The tradeoff between fuel cost and battery aging cost is explicitly displayed. In addition, the results provide insight into how driving behavior affects battery aging. The paper concludes with a discussion of the optimal balance between fuel cost and battery aging.
2017-03-28
Technical Paper
2017-01-1253
Somnath Sengupta, Chethan Gururaja, Sushant Hingane, Prajwal A K, Malay Maniar, Ondřej Mikuláš, Jaroslav Pekar
Abstract Increasingly strict CO2 and emissions norms are pushing the automotive industry towards increasing adoption of Hybrid Electric Vehicle (HEV) technology. HEVs are complex hardware systems which are often controlled by software that is complex to maintain, time-consuming to calibrate, and not always guaranteed to deliver optimal fuel economy. Hence, coordinated, systematic control of different subsystems of HEV is an attractive proposition. In this paper, Model Predictive Control (MPC) and Equivalent Consumption Minimization Strategy (ECMS) based supervisory controllers have been developed to coordinate the power split between the two prime movers of an HEV – internal combustion engine and electric motor. A dynamical physics based HEV model has been developed for simulation of the system behavior. A cost function has been formulated to improve fuel economy and battery life.
2017-03-28
Technical Paper
2017-01-1241
Wei Zhang, Rajesh Malhan
Abstract Wireless power transfer (WPT) technology has started to be applied in charging electrical vehicles (EV). EV models with built-in wireless charging capability is expected to be available from several major automakers in the next few years. Meanwhile, problems associated with the massive adoption of automobiles require new format of vehicles, especially the form with compact size and electric power. An inductively charged autonomous bicycle (iCab) is proposed, which has both the automotive driving and wireless charging features. It is designed to be compatible with an EV wireless charger. The wireless charging interoperability issue of the single transmitting coil capable to charge both the EV and iCab is studied in this paper. The receiving coil of a wireless charger is usually designed to match with single transmitting coil and to have a fixed power level output.
2017-03-28
Technical Paper
2017-01-1245
Takamitsu Tajima, Hideki Tanaka, Takeo Fukuda, Yoshimi Nakasato, Wataru Noguchi, Yoshikazu Katsumasa, Tomohisa Aruga
Abstract The use of electric vehicles (EV) is becoming more widespread as a response to global warming. The major issues associated with EV are the annoyance represented by charging the vehicles and their limited cruising range. In an attempt to remove the restrictions on the cruising range of EV, the research discussed in this paper developed a dynamic charging EV and low-cost infrastructure that would make it possible for the vehicles to charge by receiving power directly from infrastructure while in motion. Based on considerations of the effect of electromagnetic waves, charging power, and the amount of power able to be supplied by the system, this development focused on a contact-type charging system. The use of a wireless charging system would produce concerns over danger due to the infiltration of foreign matter into the primary and secondary coils and the health effects of leakage flux.
2017-03-28
Technical Paper
2017-01-1206
Zhihong Jin, Zhenli Zhang, Perry Wyatt
Abstract Power limit estimation of a lithium-ion battery system plays an important balancing role of optimizing the battery design cost, maximizing for power and energy, and protecting the battery from abusive usage to achieve the intended life. The power capability estimation of any given lithium-ion battery system is impacted by the variability of many sources, such as cell and system components resistance, temperature, cell capacity, and real time state of charge and state of health estimation errors. This causes a distribution of power capability among battery packs that are built to the same design specification. We demonstrated that real time power limit estimation can only partially address the system variability due to the errors introduced by itself. Integrating feedback control algorithms with the lithium-ion battery model maximizes the battery power capability, improves the battery robustness to variabilities, and reduces the real time estimation errors.
2017-03-28
Technical Paper
2017-01-1210
R. Dyche Anderson, Regan Zane, Gregory Plett, Dragan Maksimovic, Kandler Smith, M. Scott Trimboli
Abstract A new cell balancing technology was developed under a Department of Energy contract which merges the DC/DC converter function into cell balancing. Instead of conventional passive cell balancing technology which bypasses current through a resistor, or active cell balancing which moves current from one cell to another, with significant cost and additional inefficiencies, this concept takes variable amount of current from each cell or small group of cells and converts it to current for the low voltage system.
2017-03-28
Technical Paper
2017-01-1200
Vijay Saharan, Kenji Nakai
Abstract Electric vehicles have a strong potential to reduce a continued dependence on fossil fuels and help the environment by reducing pollution. Despite the desirable advantage, the introduction of electrified vehicles into the market place continues to be a challenge due to cost, safety, and life of the batteries. General Motors continues to bring vehicles to market with varying level of hybrid functionality. Since the introduction of Li-ion batteries by Sony Corporation in 1991 for the consumer market, significant progress has been made over the past 25 years. Due to market pull for consumer electronic products, power and energy densities have significantly increased, while costs have dropped. As a result, Li-ion batteries have become the technology of choice for automotive applications considering space and mass is very critical for the vehicles.
2017-03-28
Technical Paper
2017-01-1222
Jeongwon Rho, Jeongbin Yim, Daewoong Han, Gubae Kang, Seongyeop Lim
Abstract The current sensor for motor control is one of the main components in inverters for eco-friendly vehicles. Recently, as the higher performance of torque control has become required, the current sensor measurement error and accuracy of motor controls have become more significant. Since the response time of the sensor affects the motor output power, the response delay of the sensor causes measurement errors of the current. Accordingly, the voltage vector changes, and a motor output power deviation occurs. In the case of the large response delay of the sensor, as motor speed increases, then difference between motoring and generating output power becomes larger and larger. This results in the deterioration of power performance in high-speed operation. The deviation of the voltage vector magnitude is the main cause of motor output power deviation and imbalance through the simulation.
2017-03-28
Technical Paper
2017-01-1212
Hong Jia Hong, Jesus Ruiz Sevillano, Clemens Kain, Guenter Hofer, Karl Felber, Wai Keung Chan
Abstract The automotive industry is moving from fossil carburant to electric drive trains due to the stringent CO2 reduction policies. In this context, the electric energy storage becomes one of the key parameters of successful rolling out electrified vehicles. Typical battery management systems comprises of battery cells measurement and monitoring, balancing function, temperature monitoring, together with the State of Charge and State of Health estimations based on the given measurements. Together with the functions above, a robust internal IC communication protocol is one of the key parameters to guarantee battery performance as well as safety. This paper focuses on the automotive battery communication system. On one side, the importance of the communication system and its impact in the EDT (electric drive train) is discussed including safety aspects. Later on, the different communication methods up to date are analyzed to further understand their limitations.
2017-03-28
Technical Paper
2017-01-1214
Jujun Xia, Haifeng Dai, Zechang Sun, Massimo Venturi
Abstract Lithium-ion batteries have been applied in the new energy vehicles more and more widely. The inconsistency of battery cells imposes a lot of difficulties in parameter and state estimations. This paper proposes a new algorithm which can online identify the parameters of each individual battery cell accurately with limited increase of computational cost. An equivalent circuit battery model is founded and based on the RLS (recursive least squares) algorithm, an optimization algorithm with the construction of weight vectors is proposed which can identify the parameters of lithium battery pack considering inconsistency of single battery cell. Firstly, the average value of the parameters of the battery pack is identified with the traditional RLS algorithm. Then the ratios between the parameters of each battery cell can be deduced from the mathematical model of battery. These ratios are used to determine the weight vector of each parameter of individual battery cells.
2017-03-28
Technical Paper
2017-01-0024
Yuto Imanishi, Naoyuki Tashiro, Yoichi Iihoshi, Takashi Okada
Abstract In recent years, improvement of in-use fuel economy is required with tightening of exhaust emission regulation. We assume that one of the most effective solutions is ACC (Adaptive Cruise Control), which can control a powertrain accurately more than a driver. We have been developing a fuel saving ADAS (Advanced Driver Assistance System) application named “Sailing-ACC”. Sailing-ACC system uses sailing stop technology which stops engine fuel injection, and disengages a clutch coupling a transmission when a vehicle does not need acceleration torque. This system has a potential to greatly improve fuel efficiency. In this paper, we present a predictive powertrain state switching algorithm using external information (route information, preceding vehicle information). This algorithm calculates appropriate switching timing between a sailing stop mode and an acceleration mode to generate a “pulse-and-glide” pattern.
2017-03-28
Technical Paper
2017-01-0032
Wei Yang, Ling Zheng, Yinong Li, Yue Ren, Yusheng Li
Abstract This paper proposed a two-section trajectory planning algorithm. In this trajectory planning, sigmoid function is adopted to fit two tangent arcs to meet limited parking spaces by reducing the radius of turning. Then the transverse preview model is established and the path tracking errors including distance error and angle error are estimated. The weight coefficient is considered to distribute the impact factor of traverse distance error or traverse angle error in the total error. The fuzzy controller is designed to track the two-section trajectory in autonomous intelligent parking system. The fuzzy controller is developed due to its real-time and robustness in the parking process. Traverse errors and its first-order derivative are selected as input variables and the outer wheel steering angle is selected as the output variable in fuzzy controller. They are also divided into seven fuzzy sets. Finally, forty rules are decided to achieve effective trajectory tracking.
2017-03-28
Technical Paper
2017-01-0030
Shunsuke Kogure, Takashi Kato, Shin Osuga
Abstract With the improved safety performance of vehicles, the number of accidents has been decreasing. However, accidents due to driver distraction still occur, which means that there is a high need to determine whether a driver is properly looking at the surroundings. Meanwhile, with the trend toward partial automatic driving of vehicles in recent years, it is also urgently required that the state of the driver be grasped. Even if automatic driving is not installed, it is desired that the state of the driver be grasped and an application for control be performed depending on the state of the driver. Under these circumstances, we have built an algorithm that determines of the direction a driver is looking, to make a basic determination of whether or not the driver is in a state suitable for safe driving of the vehicle.
2017-03-28
Technical Paper
2017-01-0041
Shengguang Xiong, Gangfeng Tan, Xuexun Guo, Longjie Xiao
Abstract Automotive Front Lighting System(AFS) can receive the steering signal and the vehicular speed signal to adjust the position of headlamps automatically. AFS will provide drivers more information of front road to protect drivers safe when driving at night. AFS works when there is a steering signal input. However, drivers often need the front road's information before they turn the steering wheel when vehicles are going to go through a sharp corner, AFS will not work in such a situation. This paper studied how to optimize the working time of AFS based on GIS (Geographic Information System) and GPS(Geographic Information System) to solve the problem. This paper analyzed the process of the vehicle is about to go through a corner. Low beams and high beams were discussed respectively.
2017-03-28
Technical Paper
2017-01-0037
Xianyao Ping, Gangfeng Tan, Yahui Wu, Binyu Mei, Yuxin Pang
Abstract The drivers' hysteretic perception to surrounding environment will affect vehicular fuel economy, especially for the heavy-duty vehicles driving under complex conditions and long distance in mountainous areas. Unreasonable acceleration or deceleration on the slope will increase the fuel consumption. Improving the performance of the engine and the transmission system has limited energy saving potential, and most fuel-efficient driving assistant systems don't consider the road conditions. The main purpose of this research is to introduce an economic driving scheme with consideration of the prestored slope information in which the vehicle speed in mountainous slopes is reasonably planned to guide the driver's behavior for reduction of the fuel consumption. Economic driving optimization algorithm with low space dimension and fast computation speed is established to plan accurate and real-time economic driving scheme.
2017-03-28
Technical Paper
2017-01-1257
Haotian Wu
Abstract Previous studies have investigated various hybrid and electric powertrain architectures to balance concerns about the energy consumption and drivability. However, present architectures have some intrinsic drawbacks on the powertrain torque winding up, weight, packaging and energy harvest. This study proposed an electric powertrain that is powered by four independent motor drive. In order to investigate the drivability and regeneration braking performance, physics-based models of vehicle, motor and battery were developed; meanwhile, the dual-loop feedforward motor control and hybrid sliding mode control were presented. The Physics model-based evaluation was conducted by using the co-simulation technology of LMS AMESim and Simulink. The results show that the proposed four-wheel independent electric powertrain can achieve better drivability and regeneration braking performance. The proposed hybrid sliding mode control can converge faster than the bang-bang control.
2017-03-28
Technical Paper
2017-01-0975
Pankaj Kumar, Imad Makki
Abstract A three-way catalytic converter (TWC) is an emissions control device, used to treat the exhaust gases in a gasoline engine. The conversion efficiency of the catalyst, however, drops with age or customer usage and needs to be monitored on-line to meet the on board diagnostics (OBD II) regulations. In this work, a non-intrusive catalyst monitor is developed to diagnose the track the remaining useful life of the catalyst based on measured in-vehicle signals. Using air mass and the air-fuel ratio (A/F) at the front (upstream) and rear (downstream) of the catalyst, the catalyst oxygen storage capacity is estimated. The catalyst capacity and operating exhaust temperature are used as an input features for developing a Support Vector Machine (SVM) algorithm based classifier to identify a threshold catalyst. In addition, the distance of the data points in hyperspace from the calibrated threshold plane is used to compute the remaining useful life left.
2017-03-28
Technical Paper
2017-01-1572
Wesley Kerstens
Abstract The detection and diagnosis of sensor faults in real-time is necessary for satisfactory performance of vehicle Electronic Stability Control (ESC) and Roll Stability Control (RSC) systems. This paper presents an observer designed to detect faults of a roll rate sensor that is robust to model uncertainties and disturbances. A reference vehicle roll angle estimate, independent of roll-rate sensor measurement, is formed from available ESC inertial sensor measurements. Residuals are generated by comparing the reference roll angle and roll rate, with the observer outputs. Stopping rules based on the current state of the vehicle and the magnitude of the residuals are then used to determine if a sensor fault is present. The system’s low order allows for efficient implementation in real-time on a fixed-point microprocessor. Modification of the roll rate sensor signal during in vehicle experiments shows the algorithm’s ability to detect faults.
Viewing 241 to 270 of 16574