Display:

Results

Viewing 211 to 240 of 16442
2017-03-28
Technical Paper
2017-01-1224
Ryota Kitamoto, Shinnosuke Sato, Hiromichi Nakamura, Atsushi Amano
Abstract A new fuel cell voltage control unit (FCVCU) has been developed for a new fuel cell vehicle (FCV). In order to simultaneously reduce the electric powertrain size and increase the driving motor power, the FCVCU is needed to boost the voltage supplied from the fuel cell (FC) stack to the driving motor. The FCVCU circuit configuration has four single-phase chopper circuits arranged in parallel to form a 4-phase interleaved circuit. The intelligent power module (IPM) is a full SiC IPM, the first known use to date in a mass production vehicle, and efficiency has been enhanced by making use of the effects of the increased frequency to reduce both the size of the unit and the loss from passive parts. In addition, a coupled inductor was used to reduce the inductor size. As a result, the inductor volume per unit power was reduced approximately 30% compared to the previous VCU inductor.
2017-03-28
Technical Paper
2017-01-1189
Tsuyoshi Maruo, Masashi Toida, Tomohiro Ogawa, Yuji Ishikawa, Hiroyuki Imanishi, Nada Mitsuhiro, Yoshihiro Ikogi
Abstract Toyota Motor Corporation (TMC) has been developing fuel cell vehicles (FCVs) since 1992. As part of a demonstration program, TMC launched the FCHV-adv in 2008, which established major technical improvements in key performance areas such as efficiency, driving range, durability, and operation in sub-zero conditions. However, to encourage commercialization and widespread adoption of FCVs, further improvements in performance were required. During sub-zero operating conditions, the FC system output power was lower than under normal operating conditions. The FC stack in the FCHV-adv needed to dry the electrolyte membrane to remove unneeded water from the stack. This increased the stack resistance and caused low output power. In December 2014, TMC launched the world’s first commercially available FCV named the Mirai, which greatly improved output power even after start-up in sub-zero conditions.
2017-03-28
Technical Paper
2017-01-1409
Markus Schratter, Susie Cantu, Thomas Schaller, Peter Wimmer, Daniel Watzenig
Abstract Highly Automated Driving (HAD) opens up new middle-term perspectives in mobility and is currently one of the main goals in the development of future vehicles. The focus is the implementation of automated driving functions for structured environments, such as on the motorway. To achieve this goal, vehicles are equipped with additional technology. This technology should not only be used for a limited number of use cases. It should also be used to improve Active Safety Systems during normal non-automated driving. In the first approach we investigate the usage of machine learning for an autonomous emergency braking system (AEB) for the active pedestrian protection safety. The idea is to use knowledge of accidents directly for the function design. Future vehicles could be able to record detailed information about an accident. If enough data from critical situations recorded by vehicles is available, it is conceivable to use it to learn the function design.
2017-03-28
Technical Paper
2017-01-1441
Heungseok Chae, Kyong Chan Min, Kyongsu Yi
Abstract This paper describes design and evaluation of a driving mode decision and lane change control algorithm of automated vehicle in merge situations on highway intersection. For the development of a highly automated driving control algorithm in merge situation, driving mode change from lane keeping to lane change is necessary to merge appropriately. In a merge situation, the driving objective is slightly different to general driving situation. Unlike general situation, the lane change should be completed in a limited travel distance in a merge situation. Merge mode decision is determined based on surrounding vehicles states and remained distance of merge lane. In merge mode decision algorithm, merge availability and desired merge position are decided to change lane safely and quickly. Merge availability and desired merge position are based on the safety distance that considers relative velocity and relative position of subject and surrounding vehicles.
2017-03-28
Technical Paper
2017-01-1481
Kyung-bok Lee, Sanghyuk Lee, Namyoung Kim, Bong Soo Kim, Tae soo Chi, Do young Kim
Abstract Conventional EPS (Electric Power Steering) systems are operated by one type of steering tuning map set by steering test drivers before being released to customers. That is, the steering efforts can't change in many different driving conditions such as road conditions (low mu, high mu and unpaved roads) or some specific driving conditions (sudden stopping, entering into EPS failure modes and full accelerating). Those conditions can't give drivers consistent steering efforts. This paper approached the new concept technology detecting those conditions by using vehicle and EPS sensors such as tire wheel speeds, vehicle speed, steering angle, steering torque, steering speed and so on. After detecting those conditions and judging what the best steering efforts for safe vehicle driving are, EPS systems automatically can be changed with the steering friction level and selection of steering optimized mapping on several conditions.
2017-03-28
Technical Paper
2017-01-1399
Bin Wu, Xichan Zhu, Jianping Shen, Xuejun Cang, Lin li
Abstract A driver steering model for emergency lane change based on the China naturalistic driving data is proposed in this paper. The steering characteristic of three phases is analyzed. Using the steering primitive fitting by Gaussian function, the steering behaviors in collision avoidance and lateral movement phases can be described, and the stabilization steering principle of yaw rate null is found. Based on the steering characteristic, the near and far aim point used in steering phases is analyzed. Using the near and far aim point correction model, a driver steering model for emergency lane change is established. The research results show that the driver emergency steering model proposed in this paper performs well when explaining realistic steering behavior, and this model can be used in developing the ADAS system.
2017-03-28
Technical Paper
2017-01-1401
Trong-Duy Nguyen, Joseph Lull, Satish Vaishnav
Abstract In this paper, a method of improving the automated vehicle’s perception using a multi-pose camera system (MPCS) is presented. The proposed MPCS is composed of two identical colored and high frame-rate cameras: one installed in the driver side and the other in the passenger side. Perspective of MPCS varies depending on the width of vehicle type in which MPCS is installed. To increase perspective, we use the maximum width of the host vehicle as camera to camera distance for the MPCS. In addition, angular positions of the two cameras in MPCS are controlled by two separate electric motor-based actuators. Steering wheel angle, which is available from the vehicle Controller Area Network (CAN) messages, is used to supply information to the actuators to synchronize MPCS camera positions with the host vehicle steering wheel.
2017-03-28
Technical Paper
2017-01-1402
SeHwan Kim, Junmin Wang, Dennis Guenther, Gary Heydinger, Joshua Every, M. Kamel Salaani, Frank Barickman
Abstract The rapid development of driver assistance systems, such as lane-departure warning (LDW) and lane-keeping support (LKS), along with widely publicized reports of automated vehicle testing, have created the expectation for an increasing amount of vehicle automation in the near future. As these systems are being phased in, the coexistence of automated vehicles and human-driven vehicles on roadways will be inevitable and necessary. In order to develop automated vehicles that integrate well with those that are operated in traditional ways, an appropriate understanding of human driver behavior in normal traffic situations would be beneficial. Unlike many research studies that have focused on collision-avoidance maneuvering, this paper analyzes the behavior of human drivers in response to cut-in vehicles moving at similar speeds. Both automated and human-driven vehicles are likely to encounter this scenario in daily highway driving.
2017-03-28
Journal Article
2017-01-1403
Alexander Koenig, Michael Gutbrod, Sören Hohmann, Julian Ludwig
Abstract Highly automated driving (HAD) is under rapid development and will be available for customers within the next years. However the evidence that HAD is at least as safe as human driving has still not been produced. The challenge is to drive hundreds of millions of test kilometers without incidents to show that statistically HAD is significantly safer. One approach is to let a HAD function run in parallel with human drivers in customer cars to utilize a fraction of the billions of kilometers driven every year. To guarantee safety, the function under test (FUT) has access to sensors but its output is not executed, which results in an open loop problem. To overcome this shortcoming, the proposed method consists of four steps to close the loop for the FUT. First, sensor data from real driving scenarios is fused in a world model and enhanced by incorporating future time steps into original measurements.
2017-03-28
Technical Paper
2017-01-1407
Helene G. Moorman, Andrea Niles, Caroline Crump, Audra Krake, Benjamin Lester, Laurene Milan, Christy Cloninger, David Cades, Douglas Young
Abstract Lane Departure Warning (LDW) systems, along with other types of Advanced Driver Assistance Systems (ADAS), are becoming more common in passenger vehicles, with the general aim of improving driver safety through automation of various aspects of the driving task. Drivers have generally reported satisfaction with ADAS with the exception of LDW systems, which are often rated poorly or even deactivated by drivers. One potential contributor to this negative response may be an increase in the cognitive load associated with lane-keeping when LDW is in use. The present study sought to examine the relationship between LDW, lane-keeping behavior, and concurrent cognitive load, as measured by performance on a secondary task. Participants drove a vehicle equipped with LDW in a demarcated lane on a closed-course test track with and without the LDW system in use over multiple sessions.
2017-03-28
Technical Paper
2017-01-1408
Satoshi Kozai, Yoshihiko Takahashi, Akihiro Kida, Takayuki Hiromitsu, Shinji Kitaura, Sadamasa Sawada, Gladys Acervo, Marius Ichim
Abstract A Rear Cross Traffic Auto Brake (RCTAB) system has been developed that uses radar sensors to detect vehicles approaching from the right or left at the rear of the driver’s vehicle, and then performs braking control if the system judges that a collision may occur. This system predicts the intersecting course of approaching vehicles and uses the calculated time-to-collision (TTC) to control the timing of automatic braking with the aim of helping prevent unnecessary operation while ensuring system performance.
2017-03-28
Technical Paper
2017-01-1555
Mirosław Jan Gidlewski, Krystof JANKOWSKI, Andrzej MUSZYŃSKI, Dariusz ŻARDECKI
Abstract Lane change automation appears to be a fundamental problem of vehicle automated control, especially when the vehicle is driven at high speed. Selected relevant parts of the recent research project are reported in this paper, including literature review, the developed models and control systems, as well as crucial simulation results. In the project, two original models describing the dynamics of the controlled motion of the vehicle were used, verified during the road tests and in the laboratory environment. The first model - fully developed (multi-body, 3D, nonlinear) - was used in simulations as a virtual plant to be controlled. The second model - a simplified reference model of the lateral dynamics of the vehicle (single-body, 2D, linearized) - formed the basis for theoretical analysis, including the synthesis of the algorithm for automatic control. That algorithm was based on the optimal control theory.
2017-03-28
Technical Paper
2017-01-1581
Jianbo Lu, Hassen Hammoud, Todd Clark, Otto Hofmann, Mohsen Lakehal-ayat, Shweta Farmer, Jason Shomsky, Roland Schaefer
Abstract This paper presents two brake control functions which are initiated when there is an impact force applied to a host vehicle. The impact force is generated due to the host vehicle being collided with or by another vehicle or object. The first function - called the post-impact braking assist - initiates emergency brake assistance if the driver is braking during or right after the collision. The second function - called the post-impact braking - initiates autonomous braking up to the level of the anti-lock-brake system if the driver is not braking during or right after the collision. Both functions intend to enhance the current driver assistance features such as emergency brake assistance, electronic stability control, anti-brake-lock system, collision mitigation system, etc.
2017-03-28
Technical Paper
2017-01-1622
Ronald Brombach, Anup Gadkari
Abstract The Body Control Module (BCM) is a very large integration site for vehicle features and functions (e.g., Locking, Alarms, interior lighting, exterior lighting, etc…). Every few years the demand to add more feature/functions and integrate more vehicle content increases. The expectation of the 2013 MY (model year) BCM, was to double the feature content and use it globally. The growth in 3 years of feature/function content was huge number that grew from 150 to over 300. This posed a major challenge to the software development team based on the methods and process that were deployed at the time. This paper cites the cultural and technology changes that were overcome when Ford Motor Company partnered with Tata Consultancy Services to help manage and define this new software engineering development methodology. The process of getting from a vague description of a new body module feature to a saleable product, presents several very challenging problems.
2017-03-28
Technical Paper
2017-01-0045
Guirong Zhuo, Cheng Wu, Fengbo Zhang
Abstract Vehicle active collision avoidance includes collision avoidance by braking and by steering. However, both of these two methods have their limitations. Therefore, it is significant to establish the feasible region of active collision avoidance to choose the optimal way to avoid traffic accidents. This paper focuses on the steering control of an autonomous vehicle to track the planned trajectory and to perform an emergency collision avoidance maneuver. Meanwhile, the collision avoidance effect of steering control is compared with that of braking control. The path tracking controller is designed by hierarchical control structure. The upper controller includes model predictive control allocation and speed controller, and the lower is designed by weighted least-squares control allocation for torque allocation. Besides, seven order polynomial is used for path planning.
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
2017-01-0063
John Botham, Gunwant Dhadyalla, Antony Powell, Peter Miller, Olivier Haas, David McGeoch, Arun Chakrapani Rao, Colin O'Halloran, Jaroslaw Kiec, Asif Farooq, Saman Poushpas, Nick Tudor
Abstract PICASSOS was a UK government funded programme to improve the ability of automotive supply chains to develop complex software-intensive systems with high safety assurance and at an acceptable cost. This was executed by a consortium of three universities and five companies including an automotive OEM and suppliers. Three major elements of the PICASSOS project were: use of automated model based verification technology utilising formal methods; application of this technology in the context of ISO 26262; and evaluation to measure the impact of this approach to inform key management decisions on the costs, benefits and risks of applying this technology on live projects. The project spanned system level design and software development. This was achieved by using a unified model based process incorporating SysML at the system level and using Simulink and Stateflow auto-coded into C at the software level.
2017-03-28
Technical Paper
2017-01-0096
Valentin Soloiu, Bernard Ibru, Thomas Beyerl, Tyler Naes, Charvi Popat, Cassandra Sommer, Brittany Williams
Abstract An important aspect of an autonomous vehicle system, aside from the crucial features of path following and obstacle detection, is the ability to accurately and effectively recognize visual cues present on the roads, such as traffic lanes, signs and lights. This ability is important because very few vehicles are autonomously driven, and must integrate with conventionally operated vehicles. An enhanced infrastructure has yet to be available solely for autonomous vehicles to more easily navigate lanes and intersections non-visually. Recognizing these cues efficiently can be a complicated task as it not only involves constantly gathering visual information from the vehicle’s surroundings, but also requires accurate real time processing. Ambiguity of traffic control signals challenges even the most advanced computer decision making algorithms. The vehicle then must keep a predetermined position within its travel lane based on its interpretation of its surroundings.
2017-03-28
Technical Paper
2017-01-0060
Heiko Doerr, Thomas End, Lena Kaland
Abstract The release of the ISO 26262 in November 2011 was a major milestone for the safeguarding of safety-related systems that include one or more electrical and / or electronic (E/E) systems and that are installed in series production passenger cars. Although no specific requirements exist for a model-based software development process, ISO 26262 compiles general requirements and recommendations that need to be applied to model-based development. The second edition of the ISO 26262 has been distributed for review with a final publication scheduled for 2018. This revised edition not only integrates the experiences of the last few years but also extends the overall scope of safety-related systems. In order to determine the necessary adaptions for already existing software development processes, a detailed analysis of this revision is necessary. In this work, we focus on an analysis and the impact on model-based software development of safety-related systems.
2017-03-28
Technical Paper
2017-01-0107
Arvind Jayaraman, Ashley Micks, Ethan Gross
Abstract Recreating traffic scenarios for testing autonomous driving in the real world requires significant time, resources and expense, and can present a safety risk if hazardous scenarios are tested. Using a 3D virtual environment to enable testing of many of these traffic scenarios on the desktop or cluster significantly reduces the amount of required road tests. In order to facilitate the development of perception and control algorithms for level 4 autonomy, a shared memory interface between MATLAB, Simulink, and Unreal Engine 4 can send information (such as vehicle control signals) back to the virtual environment. The shared memory interface conveys arbitrary numerical data, RGB image data, and point cloud data for the simulation of LiDAR sensors.
2017-03-28
Technical Paper
2017-01-0104
Maryam Moosaei, Yi Zhang, Ashley Micks, Simon Smith, Madeline J. Goh, Vidya Nariyambut Murali
Abstract In this work, we outline a process for traffic light detection in the context of autonomous vehicles and driver assistance technology features. For our approach, we leverage the automatic annotations from virtually generated data of road scenes. Using the automatically generated bounding boxes around the illuminated traffic lights themselves, we trained an 8-layer deep neural network, without pre-training, for classification of traffic light signals (green, amber, red). After training on virtual data, we tested the network on real world data collected from a forward facing camera on a vehicle. Our new region proposal technique uses color space conversion and contour extraction to identify candidate regions to feed to the deep neural network classifier. Depending on time of day, we convert our RGB images in order to more accurately extract the appropriate regions of interest and filter them based on color, shape and size.
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
2017-01-0102
Mahdi Heydari, Feng Dang, Ankit Goila, Yang Wang, Hanlong Yang
In this paper, a sensor fusion approach is introduced to estimate lane departure. The proposed algorithm combines the camera, inertial navigation sensor, and GPS data with the vehicle dynamics to estimate the vehicle path and the lane departure time. The lane path and vehicle path are estimated by using Kalman filters. This algorithm can be used to provide early warning for lane departure in order to increase driving safety. By integrating inertial navigation sensor and GPS data, the inertial sensor biases can be estimated and the vehicle path can be estimated where the GPS data is not available or is poor. Additionally, the algorithm can be used to reduce the latency of information embedded in the controls, so that the vehicle lateral control performance can be significantly improved during lane keeping in Advanced Driver Assistance Systems (ADAS) or autonomous vehicles. Furthermore, it improves lane detection reliability in situations when camera fails to detect lanes.
2017-03-28
Technical Paper
2017-01-0109
Yi Zhang, Madeline J. Goh, Vidya Nariyambut Murali
Abstract This work describes a single camera based object distance estimation system. As technology on vehicles is constantly advancing on the road to autonomy, it is critical to know the locations of objects in 3D space for safe behavior of the vehicle. Though significant progress has been made on object detection in 2D sensor space from a single camera, this work additionally estimates the distance to said object without requiring stereo vision or absolute knowledge of vehicle motion. Specifically, our proposed system is comprised of three modules: vision based ego-motion estimation, object-detection, and distance estimation. In particular, we compensate for the vehicle ego-motion by using pin-hole camera model to increase the accuracy of the object distance estimation.
2017-03-28
Technical Paper
2017-01-0137
Akira Ando, Koichi Hamashima, Shinji Kato, Noriyuki Tomita, Takahiro Uejima
Abstract In respect to the present large refrigerator trucks, sub-engine type is the main product, but the basic structure does not change greatly since the introduction for around 50 years. A sub-engine type uses an industrial engine to drive the compressor, and the environmental correspondence such as the fuel consumption, the emission is late remarkably. In addition, most of trucks carry the truck equipment including the refrigerator which consumes fuel about 20% of whole vehicle. Focusing on this point, the following are the reports about the system development plan for fuel consumption reduction of the large size refrigerator truck. New concept is to utilize electrical power from HV system to power the electric-driven refrigerator. We have developed a fully electric-driven refrigerator system, which uses regenerated energy that is dedicated for our refrigerator system.
2017-03-28
Technical Paper
2017-01-0108
Zaydounr Y. Rawashdeh, Trong-Duy Nguyen, Anoop Pottammal, Rajesh Malhan
Abstract In this work, Dedicated Short Range Communication (DSRC) capabilities combined with classical autonomous vehicles’ on-board sensors (Camera) are used to trigger a Comfortable Emergency Brake (CEB) for urban traffic light intersection scenario. The system is designed to achieve CEB in two phases, the Automated Comfortable Brake (ACB) and the full stop Automated Emergency Brake (AEB). The ACB is triggered first based on the content of the Signal Phase and Timing (SPaT) / Map data (MAP) messages received from the Road Side Unit (RSU) at larger distances. And, once the traffic light becomes in the detection field of view of the camera, the output of the Camera-based Traffic Light Detection (TLD) and recognition software is fused with the SPaT/MAP content to decide on triggering the full stop AEB. In the automated vehicle, the current traffic light color and duration received in the SPaT message is parsed; and compared with the TLD output for color matching.
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
2017-01-0116
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
2017-01-0117
Raja Sekhar Dheekonda, Sampad Panda, Md Nazmuzzaman khan, Mohammad Hasan, Sohel Anwar
Accuracy in detecting a moving object is critical to autonomous driving or advanced driver assistance systems (ADAS). By including the object classification from multiple sensor detections, the model of the object or environment can be identified more accurately. The critical parameters involved in improving the accuracy are the size and the speed of the moving object. All sensor data are to be used in defining a composite object representation so that it could be used for the class information in the core object’s description. This composite data can then be used by a deep learning network for complete perception fusion in order to solve the detection and tracking of moving objects problem. Camera image data from subsequent frames along the time axis in conjunction with the speed and size of the object will further contribute in developing better recognition algorithms.
2017-03-28
Technical Paper
2017-01-1726
Sameer Shah, Aayoush Sharma, Raghav Angra, Nitin Singh, Khalique Ahmed
Abstract In an unavoidable event of a suspect being chased by police, there is high probability for the criminal to evade the police while driving his vehicle. At many instances, criminal escapes without leaving a trail behind and becomes untraceable. A new concept of Vigilance Assistance System Network (VASN) has been developed, which is spread across the city and helps in catching the escaping criminals. At every junction, the traffic-signals are installed with a microcontroller chip and these connected traffic signals form a network with distinct city areas demarcated on the map. The vehicle is installed with GPS and a RFID module on their ECU when it approaches any intersection or junction; they receive wireless signals from traffic-signals and transmit another registering signal to the traffic-light wirelessly through RFID.
Viewing 211 to 240 of 16442