Criteria

Text:
Display:

Results

Viewing 271 to 300 of 110594
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
2017-01-2008
Xingwei Wang
One of the biggest Challenge of Full Automated Driving Vehicle mass production is the Cyber Security of Connectivity. This paper describes the different Cyber Security requirement and related solution of Onboard Network and V2X. For Onboard Network ready for SOTA, one kind of Micro-processor with hardware based Cyber Security module is necessary. It guarantees the integrity, authenticity, and freshness based on acceptable data load. For V2X communication with vehicles and cloud, one kind of public and private key based Security ASSP is needed. It uses strong cryptography to protect the wireless communication data of C2C (Car to Car) and C2I (Car to Infrastructure).This paper also describes design the system and solution with both functional safety and cyber security method.
2017-09-23
Technical Paper
2017-01-1953
Manfei Bai, Lu Xiong, Zhiqiang Fu, Renxie Zhang
Abstract In this paper, a speed tracking controller is designed for the All-terrain vehicles. The method of feedforward with state variable feedback based on conditional integrators is adopted by the proposed control algorithm. The feedforward is designed considering the influence of the road slope on the longitudinal dynamics, which makes the All-terrain vehicles satisfy the acceleration demand of the upper controller when it tracks the desired speed on the road with slope varying greatly. The road slope is estimated based on a combined kinematic and dynamic model. This method solves the problem that road slope estimation requires an accurate vehicle dynamic model and are susceptible to acceleration sensor bias. Based on the vehicle dynamic model and the nonlinear tire model, the method of conditional integration is used in the state variable feedback, which considers the saturation constraint of the actuator with the intention of preventing the divergent integral operation.
2017-09-23
Technical Paper
2017-01-1955
Yandong Ruan, Hui Chen, Jiancong Li
Abstract An integrated automatic driving system consists of perception, planning and control. As one of the key components of an autonomous driving system, the longitudinal planning module guides the vehicle to accelerate or decelerate automatically on the roads. A complete longitudinal planning module is supposed to consider the flexibility to various scenarios and multi-objective optimization including safety, comfort and efficiency. However, most of the current longitudinal planning methods can not meet all the requirements above. In order to satisfy the demands mentioned above, a new Potential Field (PF) based longitudinal planning method is presented in this paper. Firstly, a PF model is constructed to depict the potential risk of surrounding traffic entities, including obstacles and roads. The shape of each potential field is closely related to the property of the corresponding traffic entity.
2017-09-23
Journal Article
2017-01-1960
Xiaopeng Zong, Guoyan Xu, Guizhen Yu, Hongjie Su, Chaowei Hu
Abstract Obstacle avoidance is an important function in self-driving vehicle control. When the vehicle move from any arbitrary start positions to any target positions in environment, a proper path must avoid both static obstacles and moving obstacles of arbitrary shape. There are many possible scenarios, manually tackling all possible cases will likely yield a too simplistic policy. In this paper reinforcement learning is applied to the problem to form effective strategies. There are two major challenges that make self-driving vehicle different from other robotic tasks. Firstly, in order to control the vehicle precisely, the action space must be continuous which can’t be dealt with by traditional Q-learning. Secondly, self-driving vehicle must satisfy various constraints including vehicle dynamics constraints and traffic rules constraints. Three contributions are made in this paper.
2017-09-23
Technical Paper
2017-01-1958
Abstract With the increasing complexity, dynamicity and uncertainty of traffic, motion planning of automatic driving is getting more difficult and challenging. This paper focuses on the real-time motion planning problem of CAVs (connected and automated vehicles) in complex traffic scenarios. To effectively solve this problem, a general driving risk model is presented, which contains the following two essential parts: i) collision risk, i.e., the collision risk between the SV (subject vehicle) and other surrounding vehicles, pedestrians, buildings etc.; ii) non-collision risk, such as violation of traffic regulations, the deviation from the intention of driver, etc. To achieve the real time collision detection, the SV is approximated to a point and its shape is considered by extending the dimension of obstacles considering their relative position and velocity.
2017-09-23
Technical Paper
2017-01-1963
Yuande Jiang, Weiwen Deng, Rui He, Shun Yang, Shanshan Wang, Ning Bian
Abstract Adaptive cruise control (ACC), as one of the advanced driver assistance systems (ADAS), has become increasingly popular in improving both driving safety and comfort. Since the objectives of ACC can be multi-dimensional, and often conflict with each other, it is a challenging task in its control design. The research presented in this paper takes ACC control design as a constrained optimization problem with multiple objectives. A hierarchical framework for ACC control is introduced, aimed to achieve optimal performance on driving safety and comfort, speed and/or distance tracking, and fuel economy whenever possible. Under the hierarchical framework, the operational mode is determined in the upper layer, in which a model predictive control (MPC) based spacing controller is employed to deal with the multiple control objectives. On the other hand, the lower layer is for actuator control, such as braking and driving control for vehicle longitudinal dynamics.
2017-09-23
Technical Paper
2017-01-1962
Hongluo Li, Yutao Luo
Abstract The trajectory planning and the accurate path tracking are the two key technologies to realize the intelligent driving. The research of the steering wheel angle plays an important role in the path tracking. The purpose of this study is to optimize the steering wheel angle input during the automated lane changing. A dynamic programming approach to trajectory planning is proposed in this study, which is expected to not only achieve a quick reaction to the changing driving environment, but also optimize the balance between vehicle performance and driving efficiency. First of all, the lane changing trajectory is planned based on the positive and negative trapezoidal lateral acceleration method. In addition, the multi-objective optimization function is built which includes such indexes: lateral acceleration, lateral acceleration rate, yaw rate, lane changing time and lane changing distance.
2017-09-23
Technical Paper
2017-01-1964
Xiangkun He, Xuewu Ji, Kaiming Yang, Yulong Liu, Jian WU, Yahui Liu
Abstract Highway traffic safety has been the most serious problem in current society, statistics show that about 70% to 90% of accidents are caused by driver operational errors. The autonomous emergency braking (AEB) is one of important vehicle intelligent safety technologies to avoid or mitigate collision. The AEB system applies the vehicle brakes when a collision is eminent in spite of any reaction by the driver. In some technologies, the system forewarns the driver with an acoustic signal when a collision is still avoidable, but subsequently applies the brakes automatically if the driver fails to respond. This paper presents the development and implementation of a rear-end collision avoidance system based on hierarchical control framework which consists of threat assessment layer, wheel slip ratio control layer and integrated-electro-hydraulic brake (IEHB) actuator control layer.
2017-09-23
Technical Paper
2017-01-1984
Jun Ma, Junyi Li, Zaiyan Gong, Jihong Yu
Abstract Given the wide adoption of touchscreens in vehicles, an interesting debate is taking place regarding the good screen size, length-width ratio and whether the usability of in-vehicle information system (IVIS) would be decreased by a larger screen, especially. Moreover, the lack of scientific evidence about the concrete impact of touch screen size on usability raises questions to practitioners. In this paper, we investigated the impact of in-vehicle touch screen size on users’ visual behavior and usability as measured using eye tracker and questionnaire. Two experiments were conducted on 30 participants. In the first experiment, participants were asked to seek same information on four different in-vehicle screens based on simulated driving environment, while eye movement was recorded for analyzing efficiency of visual behavior.
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
2017-01-1977
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
2017-01-1990
Xiangyu huang, Hao Zhou
Abstract The most important role of V2X technology is to significantly enhance driving safety. This paper proposes an Omni-directional collision warning method based on vehicle to vehicle communication. With the Basic Safety Message (BSM), the driving states of vehicles which communicate with host vehicle can be obtained. The warnings are divided into two categories based on the Lateral Offset calculation: forward collision warning (FCW) for vehicles moving in the same direction and cross collision warning (CCW) for vehicles moving in different directions. For vehicles which moves in the same direction, the lateral offset of the two vehicles, the time to collision (TTC) and time headway (THW) are used to estimate forward collision risk. For vehicles which moves in different directions, time to the closest point approach (TCPA) model and the separating axis theorem (SAT) are used for cross collision detection.
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
2017-01-1992
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
2017-01-1991
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
2017-01-1993
Daoyuan Sun, Xiaofei Pei, Xu Hu, Hao Pan, Bo Yang
Abstract This paper presents a Driver-In-the-Loop (DIL) bench test system for development of ESC controller. The real-time platform is built-up based on NI/PXI system and the real steering/throttle/braking actuator. In addition, the CarSim provides the vehicle model and the animator for virtual driving environment. A hierarchical ESC controller is proposed in MATLAB/Simulink then download into PXI. In the upper motion controller, the sliding mode theory is adopted and the logic threshold algorithm is used in the lower slip controller. Finally, ESC test is implemented under typical conditions by DIL and Model-In-the-Loop (MIL). The results show that, DIL could make up the shortage of driver model which can’t accurately simulate the emergency response of real driver. Therefore, DIL test could verify the ESC controller more accurately and effectively with considering the human-vehicle-road environment.
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
2017-01-1996
Zhichao Lin, Xuexun Guo, Xiaofei Pei, Bo Yang, Yanggang Zhang
Abstract Dynamic modeling and state estimation are significant in the trajectory tracking and stability control of the intelligent vehicle. In order to meet the requirement of the stability control of the eight-in-wheel-motor-driven intelligent vehicle, a full vehicle dynamics model with 12 degrees of freedom, including the longitudinal, lateral, yaw and roll motion of the body, and rotational motion of 8 wheels, is established for the research of the intelligent vehicle in this paper. By simulation with MATLAB/SIMULINK and by comparison with the TruckSim software, the reliability and practicality of the dynamics model are verified. Based on the established dynamics model, an extended Kalman filter (EKF) state observer is proposed to estimate the vehicle sideslip angle, roll angle and yaw rate, which are the key parameters to the stability control of the intelligent vehicle.
2017-09-23
Technical Paper
2017-01-2000
Jianping Li, Jian Wu, Hao Sun, Yuyao Jiang, Weiwen Deng, Bing Zhu
Abstract Simulation has been considered as one of the key enablers on the development and testing for autonomous driving systems as in-vehicle and field testing can be very time-consuming, costly and often impossible due to safety concerns. Accurately modeling traffic, therefore, is critically important for autonomous driving simulation on threat assessment, trajectory planning, etc. Traditionally when modeling traffic, the motion of traffic vehicles is often considered to be deterministic and modeled based on its governing physics. However, the sensed or perceived motion of traffic vehicles can be full of errors or inaccuracy due to the inaccurate and/or incomplete sensing information. In addition, it is naturally true that any future trajectories are unknown. This paper proposes a novel modeling method on traffic considering its motion uncertainties, based on Gaussian process (GP).
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
2017-01-2002
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
2017-01-2001
Xin Li, Lixin Situ, Yongqiang Yu, Feng Chen
Abstract Research and development of autonomous functions for a road vehicle become increasingly active in recent years. However, the vehicle driving dynamics performance and safety are the big challenge for the development of autonomous vehicles especially in severe environments. The optimum driving dynamics can only be achieved when the traction torque on all wheels can be influenced and controlled precisely. In this study, we present a novel approach to this problem by designing an advanced torque vectoring controller for an autonomous vehicle with four direct-drive in-wheel motors to generate and control the traction torque and speed quickly and precisely, thus to improve the stability and safety of the autonomous vehicle. A four in-wheel motored autonomous vehicle equipped with Radar and camera is modelled in PanoSim software environment. Vehicle-to-Vehicle (V2V) communication is used in this software platform to avoid collision.
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
2017-01-2003
Zhang Wei, 1Lt Xidaodong Tang
Active safety has grown to significant popularity in the recent years in the Chinese automotive market. So far the active safety devices such as radars, cameras and AEB are installed as the "bright spots " for the sales purpose. For some companies the devices also serve as the "point getter " in E-NCAP safety assessment. There has been no practical means for quantitative assessment of the real safety benefits from these devices. In this paper a CAE method is proposed not only to assess the safety performance of each device in each single standard setups, but also analyze the total safety performance of the integration of all the active safety devices. By utilizing a database of the past traffic accidents and reverse-constructing the road environments, the method makes it possible to quantitatively estimate the number of lives the active safety system could save.
2017-09-23
Technical Paper
2017-01-2009
Kuiyuan Guo, Yan Yan, Juan Shi, Runqing Guo, Yuguang Liu
Abstract In order to speed up the development of vehicle active safety technology in China, C-NCAP plans to add AEB and AEB VRU system as assessment items in 2018. With the purpose of studying the assessment protocol of AEB system, we have carried out 400,000 km road information collection and then we acquired the statistics of the operation conditions of dangerous situations. Combined with the traffic accident data collected by CIDAS, we found that the dangerous situations that we usually met were mainly three types, that was CCRs, CCRm and CCRb. Based on what we mentioned above, we analyzed the three kinds of working conditions and gave the corresponding evaluation method. In addition, combined with the actual situation of China, we added two tests of error function. And then we took the actual road experiment of many models of vehicles.
2017-09-19
Technical Paper
2017-01-2059
Enrico Cestino, Giacomo Frulla, Renzo Duella, Paolo Piana, Francesco Pennella, Francesco Danzi
Future generations of civil aircrafts and unconventional unmanned configurations demand for innovative structural concepts to obtain the structural performance, and thus reduce the structural weight. For instance, one of the method to improve structural component is the material coupling used to alter static and dynamic aeroelastic stabilities. It is therefore useful to use an accurate and computationally efficient beam model during the preliminary design phase. In the present work, a numerical validation of equivalent homogeneous orthotropic material procedure, described in [1] and [2], is performed by the application of structural topology optimization technique [3] on a box beam made of isotropic material. The overall equivalent bending, torsional and coupled stiffness is derived by means of homogenization of the shell skin and of the stiffener plate stiffness. The optimum theoretical conditions of bending-torsion coupling was obtained when stiffeners were oriented at about 27°.
2017-09-19
Technical Paper
2017-01-2058
Francesco Noziglia, Paolo Rigato, Enrico Cestino, Giacomo Frulla, Alfredo Arias-Montano
Innovative aircraft design studies have noted that uncertainty effects could become significant and greatly emphasized during the conceptual design phases due to the scarcity of information about the new aero-structure being designed. The introduction of these effects in design methodologies are strongly recommended in order to perform a consistent evaluation of structural integrity . The benefit to run a Robust Optimization is the opportunity to take into account uncertainties inside the optimization process obtaining a set of robust solutions. A major drawback of performing Robust Multi-Objective Optimization is the computational time required. The proposed research focus on the reduction of the computational time using mathematic and computational techniques. In the paper, a generalized approach to operate a Robust Multi-Objective Optimization (RMOO) for Aerospace structure using MSC software Patran/Nastran to evaluate the Objectives Function, is proposed.
Viewing 271 to 300 of 110594