Browse Topic: Driving control assistance

Items (267)
Find
EVOLUTION OF 360 DEGREE LOCAL SITUATIONAL AWARENESS (LSA) TO AID THE WARFIGHTER2024-01-345111/15/2024
ABSTRACT Northrop Grumman has developed a software and hardware solution to provide enhanced 360 degree local situational awareness (LSA) to enable the warfighter with an overmatch capability on today’s modern battlefield. The architecture exploits technological gains in cameras, video processing, and video compression. The approach allows rapid comprehension of local and remote situational views presented with operational relevance for a ground combat platform or tactical wheeled platform crew. The 360 Degree LSA approach provides direct visualization of relative positioning of targets, threats, and lines of fire; and additionally offers common situational understanding / operational picture from the dismounted soldier to higher echelon commands. The approach provides prioritized information through LSA software to provide an enhanced view to the warfighter whereas the squad leader becomes an integral part of the crew with a view of the common operating picture (mounted) and additional sensors on tablet or handheld device (dismounted via wireless). The approach uses a platform agnostic form factor with components that can be selected and applied to legacy or new platforms based on their size, weight, power, and mission constraints.
Viscovich, Christopher, Geoghegan, Susan, Worthy, David
Correlation between Sensor Performance, Autonomy Performance and Fuel-Efficiency in Semi-Truck Platoons2021-01-00644/6/2021
Semi-trucks, specifically class-8 trucks, have recently become a platform of interest for autonomy systems. Platooning involves multiple trucks following each other in close proximity, with only the lead truck being manually driven and the rest being controlled autonomously. This approach to semi-truck autonomy is easily integrated on existing platforms, reduces delivery times, and reduces greenhouse gas emissions via fuel economy benefits. Level 1 SAE fuel studies were performed on class-8 trucks operating with the Auburn Cooperative Adaptive Cruise Control (CACC) system, and fuel savings up to 10-12% were seen. Enabling platooning autonomy required the use of radar, global positioning systems (GPS), and wireless vehicle-to-vehicle (V2V) communication. Poor measurements and state estimates can lead to incorrect or missing positioning data, which can lead to unnecessary dynamics and finally wasted fuel. This is especially an issue if deceleration is applied in response to a bad measurement. In this study, a faulty radar was shown to cause a greater than 5% increase in fuel consumption. The mechanism of this fuel consumption increase is investigated and applied to other types of sensor failures to indicate their potential effects on fuel economy. This analysis indicates that poor GPS signals over short time can be largely filtered out, with no real gain or loss of fuel economy. V2V communications were intentionally limited by causing interference, which resulted in dropped communication packets over a small physical area, but not an appreciable impact on fuel economy.
Adam, Cristian, Lakshmanan, Sridhar, Richardson, Paul, Stegner, Evan, Ward, Jacob, Hoffman, Mark, Bevly, David M.
Candidate Improvements to Dedicated Short Range Communications (DSRC) Message Set Dictionary [SAE J2735] Using Systems Engineering MethodsJ3067_202010 (Current)10/6/2020
This document is not a standard, it is a candidate for a standard being submitted to SAE for their consideration as a comment to SAE J2735. The term SAE J2735 SE candidate is used within this document to refer to this submission. This document specifies dialogs, messages, and the data frames and data elements that make up the messages specifically for use by applications intended to utilize the 5.9 GHz Dedicated Short Range Communications for Wireless Access in Vehicular Environments (DSRC/WAVE, referenced in this document simply as “DSRC"), communications systems. Although the scope of this Standard is focused on DSRC, these dialogs, messages, data frames and data elements have been designed, to the extent possible, to be of use for applications that may be deployed in conjunction with other wireless communications technologies. This standard therefore specifies the definitive message structure and provides sufficient background information to allow readers to properly interpret the message definitions from the point of view of an application developer implementing the messages according to the DSRC Standards.
V2X Communications Steering Committee
Development of Design and Engineering Recommendations for In-Vehicle Alphanumeric MessagesJ2831_202007 (Current)7/29/2020
This Information Report provides recommendations for alphanumeric messages that are supplied to the vehicle by external (e.g., RDS, satellite radio) or internal (e.g., infotainment system) sources while the vehicle is in-motion. Information/design recommendations contained in this report apply to OEM (embedded) and aftermarket systems. Ergonomic issues with regard to display characteristics (e.g., viewing angle, brightness, contrast, font design, etc.) should review ISO 15008.
Driver Vehicle Interface (DVI) Committee
Scenario Analysis and Control Comparison for a High Speed Autonomous Vehicle2020-01-07104/14/2020
This paper studies the simulation and control of an autonomous dragster. Four scenarios are provided that are critical to vehicle and driver safety in drag racing. Equations are then created to model the behavior during these safety scenarios. The use of a kinematic bicycle model and a Newtonian wheel stand model are discussed for plane-of-motion and out-of-plane vehicle movement, respectively. A separate controller is designed for each model by comparing different control methods. Proportional-Integral-Derivative (PID) control, optimal control, and model predictive control (MPC) are presented and applied to the models. The models are simulated from a speed of 75 m/s, being the estimated top speed of the research vehicle, up to a top speed of 150.5 m/s which is in alignment with the highest recorded speed of a dragster. The comparison of the control techniques yields MPC as superior for the bicycle model and PID as sufficient for the wheel stand model. Latency of the system is also discussed and accounted for in the system.
Donikian, Vatche, Bell, Joseph, Washington, Gregory
Vehicle Trajectory Prediction Based on Motion Model and Maneuver Model Fusion with Interactive Multiple Models2020-01-01124/14/2020
Safety is the cornerstone for Advanced Driver Assistance Systems (ADAS) and Autonomous Driving Systems (ADS). To assess the safety of a traffic situation, it is essential to predict motion states of traffic participants in the future with mathematic models. Accurate vehicle trajectory prediction is an important prerequisite for reasonable traffic situation risk assessment and appropriate decision making. Vehicle trajectory prediction methods can be generally divided into motion model based methods and maneuver model based methods. Vehicle trajectory prediction based on motion models can be accurate and reliable only in the short term. While vehicle trajectory prediction based on maneuver models present more satisfactory performance in the long term, these maneuver models rely on machine learning methods. Abundant data should be collected to train the maneuver recognition model, which increases complexity and lowers real-time performance. In this paper, a vehicle trajectory prediction method based on motion model and maneuver model fusion with Interactive Multiple Model (IMM) is proposed. Firstly, Constant Turn Rate and Acceleration (CTRA) motion model and Unscented Kalman Filter (UKF) are used to predict vehicle trajectory with uncertainty in the future. Then, vehicle trajectory prediction based on simplified maneuver recognition model is conducted, using temporal and spatial relationship between vehicle historical trajectory and lane lines. After that, vehicle trajectory prediction by integrating motion model and maneuver model with IMM is conducted. Finally, the proposed method is compared with CTRA motion model based vehicle trajectory prediction and lane keeping model (LKM) based vehicle trajectory prediction in two simulation test scenarios. The simulation results indicates that the IMM-based method achieves both excellent prediction accuracy and appropriate prediction uncertainty in the whole prediction horizon. This research can be used to support decision making for Advanced Driver Assistance Systems (ADAS) and Autonomous Driving Systems and leads to improvement of traffic safety.
Xiao, Wei, Zhang, Lijun, Meng, Dejian
Perceptions of Two Unique Lane Centering Systems: An FOT Interview Analysis2020-01-01084/14/2020
The goal of this interview analysis was to explore and document the perceptions of two unique lane centering systems (S90’s Pilot Assist and CT6’s Super Cruise). Both systems offer a similar type of functionality (adaptive cruise control and lane centering), but have significantly different design philosophies and HMI (Human-Machine Interface) implementations. Twenty-four drivers drove one of the two vehicle models for a month as part of a field operational test (FOT) study. Upon vehicle return, drivers took part in a 60-minute semi-structured interview covering their perceptions of the vehicle’s various advanced driver-assistance systems (ADAS). Transcripts of the interviews were coded by two researchers, who tagged each statement with relevant system and perception code labels. For analysis, the perception codes were grouped into larger thematic bins of safety, comfort, driver attention, and system performance. Perceptions of adaptive cruise control (ACC) were similar across vehicles. Almost all participants mentioned benefits of comfort and safety associated with ACC use. Participants cited different benefits between the two vehicle’s implementations of lane centering. A majority of participants (75%) described comfort benefits associated with Super Cruise, while less than half (41%) cited comfort benefits associated with Pilot Assist. Only a few participants (25%) mentioned safety benefits associated with Super Cruise. Half (50%) of the participants mentioned safety benefits associated with Pilot Assist. Almost all participants cited fears of potential misuse of the system in which drivers might pay less attention to the driving task. Results suggest that drivers’ comprehension and expectation of these systems’ behavior are strongly influenced by their design philosophies, specifically in terms of the difference in hands-on versus hands-off-wheel implementation. The perceived role of the driver – as either a fallback driver or as an assisted driver - may be influenced by the design implementation.
Landry, Steven, Seppelt, Bobbie, Russo, Luca, Mehler, Bruce, Angell, Linda, Gershon, Pnina, Reimer, Bryan
A Stability-Guaranteed Time-Delay Range for Feedback Control of Autonomous Vehicles2020-01-00904/14/2020
The vehicles with level-5 autonomy (L5AVs) that have no human driver in the loop are also known as self-driving cars. L5AVs are assumed the next generation of ground transportation, which have growing attention from both industry and academia in most recent years. Most of the work related to feedback strategies of L5AVs are on developing mapping systems through a variety of sensors. These systems can be considered as an analogue to the perception and central nervous system of human drivers. For instance, innovative visualization systems are more powerful when compared to the visual perception system of a person, yet, mapping demands high computation loads. This burden causes delay in the feedback loop and thus, it might have an unfavorable influence on proper and safe control action. This study investigates the effect of time delay occurring in mapping systems on the stability of the controlled vehicle. An algorithm entitled as “Cluster Treatment of Characteristic Roots - CTCR” is used to calculate a safe delay range as a remedy for the time delay caused by mapping systems. The CTCR analysis is applied to a linearized two degree-of-freedom bicycle model for different velocities. The critical time delay values, which determines the boundary between the stability and instability of the controlled vehicle, are calculated based on the vehicle dynamics. Finally, results are drawn for a regular weave test by computer simulations, in which a non-linear vehicle model is used. The proposed approach is validated by exhibiting that a delay value outside the safe range leads the vehicle instability.
Kirli, Ahmet, Arslan, Mehmet Selçuk
Reference Test System for Machine Vision Used for ADAS Functions2020-01-00964/14/2020
Advanced Driver Assistance Systems (ADAS) like Lane Departure Warning (LDW) and Lane Keep Assist (LKA) have been available for several years now but has experienced low customer acceptance and market penetration. These deficiencies can be traced to the inability of many of the perception systems to consistently recognize lane markings and localize the vehicle with respect to the lane markings in the real-world with poor markings, changing weather conditions and occlusions. Currently, there is no available standard or benchmark to evaluate the quality of either the lane markings or the perception algorithms. This work seeks to establish a reference test system that could be used by transportation agencies to evaluate the quality of their markings to support ADAS functions that rely on pavement markings. The test system can also be used by designers as a benchmark for their proprietary systems. To support this development, an extensive video dataset was collected at different times of day and weather conditions on various roads in Central Texas. The videos were evaluated on different state-of-the art lane detection algorithms and their performance was ranked based on a set of metrics specifically developed for evaluating the effectiveness of the lane estimation system. The test scenarios are comprised of a set of roadways and environmental features, as well as the pavement marking presence and luminance variables. A systems approach is presented by correlating the algorithm performance data to the environmental factors, lane marking types, color, material, and the retroreflectivity of pavement markings.
Nayak, Abhishek, Rathinam, Sivakumar, Pike, Adam, Gopalswamy, Swaminathan
Prevention of Snow Accretion on Camera Lenses of Autonomous Vehicles2020-01-01054/14/2020
With the rapid development of artificial intelligence, the autonomous vehicles (AV) have attracted considerable attention in the automotive industry. However, different factors negatively impact the adoption of the AVs, delaying their successful commercialization. Accretion of atmospheric icing, especially wet snow, on AV sensors causes blockage on their lenses, making them prone to lose their sight, in turn, increasing potential chances of accidents. In this study, two different designs are proposed in order to prevent snow accretion on the lenses of AVs via air flow across the lens surface. In both designs, lenses made of plain glass and superhydrophobic coated glass surfaces are tested. While some researchers have shown promise of water repellency on superhydrophobic surfaces, more snow accretion is observed on the superhydrophobic surfaces, when compared to the plain glass lenses. In the experiments, snow is formed using a novel snow gun inside a walk-in cold room connected to a wind tunnel that can reach wind speeds of up to 40 mph. It is observed that the air flow over the lens significantly reduces the accretion of snow on the lens and could maintain the lens clean for up to 20 mph wind velocities. However, at LWC values of approximately 28%, the stickiness of the snowflakes increases, enhancing snow accretion on the lenses and translating to significant loss of sight. The high stickiness of the snowflakes along with high wind speeds leads to increased blockage of the AV lenses.
Mohammadian, Behrouz, Sarayloo, Mehdi, Heil, Jamie, Sojoudi, Hossein, Robertson, Michael, Hong, Haiping, Tran, Tommy, Patil, Sunil, Krishnan, Venkatesh
Robust Sensor Fused Object Detection Using Convolutional Neural Networks for Autonomous Vehicles2020-01-01004/14/2020
Environmental perception is considered an essential module for autonomous driving and Advanced Driver Assistance System (ADAS). Recently, deep Convolutional Neural Networks (CNNs) have become the State-of-the-Art with many different architectures in various object detection problems. However, performances of existing CNNs have been dropping when detecting small objects at a large distance. To deploy any environmental perception system in real world applications, it is important that the system achieves high accuracy regardless of the size of the object, distance, and weather conditions. In this paper, a robust sensor fused object detection system is proposed by utilizing the advantages of both vision and automotive radar sensors. The proposed system consists of three major components: 1) the Coordinate Conversion module, 2) Multi level-Sensor Fusion Detection (MSFD) system, and 3) Temporal Correlation filtering module. The proposed MSFD system employs the principles of artificial intelligence beyond simple comparison of data variance of the sensors. And then, its performance is further improved by using the temporal correlation information with an adaptive threshold scheme. The proposed system is evaluated with the collected video data (6,854 image frames with 18,918 labeled objects). Based on the laboratory testing and in-vehicle validation, the proposed system demonstrates its high accuracy for detecting any size of objects in real-world data.
Park, Jungme, Jayachandran Raguraman, Sriram, Aslam, Aakif, Gotadki, Shruti
GM deploying electricals of the future20AUTP03_083/1/2020
In tandem with its corporate strategy to “skip” vehicle hybridization and focus solely on electric vehicles (EVs) for future propulsion (see cover story), General Motors recently offered media a deeper look at the company's all-new vehicle electrical architecture that was first confirmed in mid-2019, saying the vehicle-wide electrical system is associated with more than 100 new patents. The advanced “digital vehicle platform,” known internally as Global B, debuted with the 2020 Cadillac CT5 sedan. It serves as the electrical foundation for the 2020 Chevrolet Corvette Stingray and the 2021 Chevrolet Tahoe and Suburban, GM Yukon and Cadillac Escalade and will carry into all of the company's future conventionally-powered and EV models.
Visnic, Bill
Research on the Enhanced ADAS Functions with Modular Design Based on 5G-V2X Technology2020-01-50262/24/2020
This paper will mainly discuss the effect of the combination of the 5th generation wireless systems - Vehicle to Everything (5G-V2X) technology an Advanced Driver Assistance Systems (ADAS) functions. With the promotion and popularization of 5G technology with high bandwidth and bottom delay, V2X has been able to quickly and safely transmit more information to target vehicles in need in the field of automatic driving. Traditional ADAS functions development has been carried out for decades, but there are still many unsolvable problems in perception and decision-making. In this paper, V2X technology is introduced into the auxiliary driving functions of L0-L3 stage by using the idea of platform module design. On the basis of not redeveloping the original functions, the existing problems of perception and decision-making are improved. Through the experimental demonstration in this paper, this method can indeed save the development cost and shorten the development cycle.
Pingfan, Jin, Jiayi, Guan, Guoqi, Zhong
Model Predictive Automatic Lane Change Control for Intelligent Vehicles2020-01-50252/24/2020
As a basic link of driving behavior in urban roads, vehicle lane changing has a significant impact on traffic flow characteristics and traffic safety, and the automation of lane change is also a key issue to be solved in the field of intelligent driving. In this paper, the research on the automatic lane change control for intelligent vehicles is carried out. The main work is to build the overall structure of the vehicle's automatic lane change behavior, of which the planning and tracking are focused. The strategy of Constant Time Headway (CTH) is used in the lane change decision. The lane change trajectory adopts the model of constant velocity offset plus sine function, and the longitudinal displacement is determined by the vehicle speed when changing lanes. Model Predictive Control (MPC) theory is used to track the trajectory, which optimizes tracking accuracy and vehicle stability and constrains the range and rate of change of vehicle speed and steering angle. By using weighted quadratic cost function, linearity matrix inequality constraints and upper and lower bound constraints, the multi-objective trajectory tracking problem is eventually transformed into a constrained online convex quadratic programming problem. The results of simulation and HIL test show that the scheme of automatic lane change can make the vehicle smoothly complete the lane changing behavior, and the errors can meet the error requirements of lane change. Compared with other controller, the method shows smaller lateral acceleration, stronger robustness and higher control precision during the test. Moreover, the computational time of the proposed MPC controller, implemented using the PXI, is 47.994ms during one sampling period, which can satisfy the real-time requirement.
Meng, Ren, Guangqiang, Wu, Xunjie, Chen, Xuyang, Liu
Tier 1s tout newest mobility tech at CES 202020AUTP02_091/1/2020
The mammoth annual techfest formerly known as the Consumer Electronics Show has become a must-attend for the mobility industry, with dozens of displays by OEMs and suppliers of all dimensions. At this year's CES, Automotive Engineering was impressed by new developments in ADAS and AV sensing and processing, V2X connectivity, vehicle cabin sensing and related technologies, electrification advances and a number of vehicle introductions. Highlights of our reporting include:
Brooke, Lindsay
Unsettled Topics Concerning Automated Driving Systems and the Transportation EcosystemEPR201900511/5/2019
Over the last 100 years, the automobile has become integrated in a fundamental way into the broader economy. A broad and deep ecosystem has emerged, and critical components of this ecosystem include insurance, after-market services, automobile retail sales, automobile lending, energy suppliers (e.g., gas stations), medical services, advertising, lawyers, banking, public planners, and law enforcement. These components - which together represent almost $2 trillion of the U.S. economy - are in equilibrium based on the current capabilities of automotive technology. However, the advent of autonomous vehicles (AVs) and technologies like electrification have the potential to significantly disrupt the automotive ecosystem. The critical cog governing the rate and pace of this shift is the management of the test and verification of AVs. In this SAE EDGE™ report, six senior industry leaders in the impacted ecosystems essay articles which describe sectors of the current automotive ecosystem and the manner in which AV technology can potentially reshape them - providing a mosaic of the massive infrastructure shifts which will be required to absorb AV technologies. NOTE: SAE EDGE™ Research Reports are intended to identify and illuminate key issues in emerging, but still unsettled, technologies of interest to the mobility industry. The goal of SAE EDGE™ Research Reports is to stimulate discussion and work in the hope of promoting and speeding resolution of identified issues. SAE EDGE™ Research Reports are not intended to resolve the issues they identify or close any topic to further scrutiny. Click here to access the full SAE EDGETM Research Report portfolio.
Razdan, Rahul
Weighted Distance Metrics for Data Association Problem in Multi-Sensor Fusion2019-01-502211/4/2019
Traffic accidents are the world's leading threat to human safety. The majority of traffic accidents are due to human error. Advanced Driver Assist Systems (ADAS) can reduce human error, therefore has the potential to effectively improve the safety of road traffic. The perception module in an ADAS understands the surrounding environment of the subject vehicle and therefore is the prerequisite for planning and control. Due to the limitation of computational constrain of Electronic Control Units, ADAS system commonly uses object-leveled multi-sensor fusion, in which raw data is processed to detect objects at the sensory level. In multi-sensor fusion, the task of assigning new observations to the existing tracks, known as Data Association problem, requires distance metrics to present the similarity between tracks. In the literature, metrics, such as standardized Euclidean distance and Mahalanobis distance has been used. Though accounting for the scale and correlation of the data, the existing metrics cannot account for the importance of each feature in predicting their dissimilarity. As a result, weighting factors are added to the distance metrics and they require extensive manual tuning. In this paper, we propose a data-driven method to obtain the weighting factors automatically using supervised learning. Real-world driving data was acquired to train a logistic regression model which obtains the weighting factors based on the predictivity of features. The new distance metric was evaluated using real-world driving data. Comparing to the existing metrics, it achieves better performance in separating dissimilar tracks and higher matching accuracy.
Zhang, Darui, Bian, Ning, Wang, Daihan, Yang, Hang, Tuo, Xinjuan
Study on Comprehensive Evaluation Index of Front Collision Hazard of Intelligent Vehicle2019-01-504411/4/2019
Collision avoidance technology is one of the key areas in the longitudinal safety research of intelligent vehicles. For the research of collision avoidance system, the existing methods usually use the evaluation index based on time interval or braking process to carry out risk assessment. In order to overcome the shortcomings of the formulas for describing the longitudinal hazard degree established in most studies, such as great differences, inconsistent standards and weak normalization, a comprehensive evaluation method for the longitudinal hazard in front-impact scenarios is established. This method takes into account both the analysis of time interval and braking process, and considers the non-linear variation of the longitudinal hazard degree with the real-time distance and speed of two vehicles. It can describe the longitudinal hazard degree of vehicles in dangerous traffic scenarios. Compared with the existing longitudinal hazard assessment methods, the effectiveness and universality of the pre-collision hazard assessment method proposed in this paper are demonstrated.
Jiaxiang, Qin, Zhang, Sumin, Weiwen, Deng, Rui, He
WHAT WE'RE DRIVING19AUTP11_0811/1/2019
While I'm among the first media to have driven the mid-engine 2020 Stingray, my time in the car (during the North American Car, Truck and Utility of the Year judging) was but 45 minutes. A very invigorating 45 minutes. My Torch Red coupe came with a special feature: Corvette ride-and-handling engineer Mike Hurley, who rode shotgun with me through the Michigan countryside. As we discussed C8 development, Mike schooled me on the magneto-rheological (MR) dampers that underpin the desirable $5,000 Z51 performance package. With three driver-selectable suspension modes - Tour, Sport, Track - the MR dampers deliver a compliant ride in town and plushness on the open road, while transforming the car into a sharp track-day tool. Crossing railroad tracks is no longer torture in a Corvette.
Eco-Driving Strategies for Different Powertrain Types and Scenarios2019-01-260810/22/2019
Connected automated vehicles (CAVs) are quickly becoming a reality, and their potential ability to communicate with each other and the infrastructure around them has big potential impacts on future mobility systems. Perhaps one of the most important impacts could be on network wide energy consumption. A lot of research has already been performed on the topic of eco-driving and the potential fuel and energy consumption benefits for CAVs. However, most of the efforts to date have been based on simulation studies only, and have only considered conventional vehicle powertrains. In this study, experimental data is presented for the potential eco-driving benefits of two specific intersection approach scenarios, for four different powertrain types. The two intersection approach scenarios considered in this study include an approach to a red light where coming to a complete stop is avoidable (short red light) and one where a complete stop is determined necessary (long red light) thanks to advance information from vehicle-to-infrastructure communication (V2I). The four powertrain types tested in this study include an advanced conventional vehicle, a conventional vehicle with idle stop-start capability, a hybrid electric vehicle (HEV), and a battery electric vehicle (BEV). The experimental results are compared to simulation results for the same intersection approach scenarios and eco-driving strategies, and show the difference in benefits for different powertrain types. Based on the eco-approach strategies for these two scenarios, a maximum fuel/energy consumption benefit of almost 8% was observed for the intersection with a short red light and almost 20% for the intersection with a long red light, in both cases by the HEV.
Iliev, Simeon, Rask, Eric, Stutenberg, Kevin, Duoba, Michael
An ADAS Feature Rating System: Proposing a New Industry Standard2019-24-025110/7/2019
More than 90% of new vehicles include Advanced Driving Assistance Systems that offer features such as Lane Keep Assist and Adaptive Cruise Control [1]. These ever-improving vehicle systems present a great opportunity to increase driving safety and reduce the number of roadway deaths and injuries. Indeed, they are already having a positive effect. However, the wide variety of features offered in the marketplace can be confusing to consumers, who may not clearly understand their vehicles’ true capabilities and limitations, or have an easy way of comparing system performance between vehicle models. This lack of information has the potential to reduce the safety gains of ADAS features by increasing the risk of improper use. To encourage transparency in the marketplace and thus engender the maximum positive effect of ADAS technologies, this paper proposes a five-level rating system, which utilizes diamonds to denote significant milestone achievements in vehicle system performance. The rating charts resulting from this system describe gradients of performance within criteria addressed by certain foundational ADAS features. Presented here in its initial stage of development, this rating system will require continued refinement. We therefore encourage the community of automotive safety organizations to take up the mantle by establishing and performing test protocols for assigning standardized ADAS feature performance ratings. We believe that the result of this effort, a common method for understanding and comparing ADAS performance, promises to deliver a beneficial level of clarity to the industry and consumers.
Heeren, David, Gradu, Mircea
Rethinking ADAS materials19AUTP09_039/1/2019
New specialized thermoplastics offer greater design freedom to improve sensor performance and packaging, at reduced cost. Advanced driver assistance system (ADAS) technologies-including automatic emergency braking, collision avoidance, adaptive cruise control and parking assist-are quickly going mainstream. OEMs, regulators and consumers recognize their value in improving driving and preventing accidents. As a global market, ADAS is expected to grow at a CAGR of 19.0% through 2025, according to Grand View Research. The current ADAS sensor suite also is evolving rapidly to respond to market demand for improved performance, more efficient packaging, and lower costs. For example, engineers are exploring the integration of different sensors into a single unit, as well as “fusing” the radar and camera data into a single output to overcome limitations of the individual technologies and provide safety redundancy. Miniaturization of sensor hardware is aimed at reducing its “footprint” at the expense of potentially generating more heat.
Pedrotti, John
A Maneuver-Based Threat Assessment Strategy for Collision Avoidance07-12-01-00038/22/2019
Advanced driver-assistance systems (ADAS) are being developed for more and more complicated application scenarios, which often require more predictive strategies with better understanding of the driving environment. Taking traffic vehicles’ maneuvers into account can greatly expand the beforehand time span for danger awareness. This article presents a maneuver-based strategy to vehicle collision threat assessment. First, a maneuver-based trajectory prediction model (MTPM) is built, in which near-future trajectories of ego vehicle and traffic vehicles are estimated with the combination of vehicle’s maneuvers and kinematic models that correspond to every maneuver. The most probable maneuvers of ego vehicle and each traffic vehicles are modelled and inferred via Hidden Markov Models with mixture of Gaussians outputs (GMHMM). Based on the inferred maneuvers, trajectory sets consisting of vehicles’ position and motion states are predicted by kinematic models. Subsequently, time to collision (TTC) is calculated in a strategy of employing collision detection at every predicted trajectory instance. For this purpose, safe areas via bounding boxes are applied on every vehicle, and Separating Axis Theorem (SAT) is applied for collision prediction so that TTC can be calculated efficiently and accurately. Finally, a threat level index based on reverse TTC is used to quantize the threat degree of every traffic vehicle potential collision to the ego vehicle. Experimental data collected in the field test are used in the model training, and the overall strategy is validated under PanoSim. An example of the application of the proposed strategy in Autonomous Emergency Braking (AEB) is also shown. Simulation results show that MTPM can accurately identify maneuvers such that the effective prediction on trajectories can be generated. TTC and threat index can be calculated timely. The proposed threat assessment strategy can not only assist collision avoidance systems to foresee dangerous situations but also eliminate false alarm to a certain extent.
Li, Yaxin, Deng, Weiwen, Sun, Bohua, Wang, Jinsong, Zhao, Jian, Zhu, Bing
The Sense-itive Side of Autonomous Vehicles19AVEP07_077/1/2019
BASF is exploring how specific materials-and even paint colors and finishes-can improve the capabilities of AV sensors. The sensing technologies needed for automated-driving vehicles are evolving as the industry moves toward high-level (SAE Level 4-5) automation. Sophisticated sensors already enable advanced driver-assistance systems (ADAS) features such as adaptive cruise control, park assist, lane-centering and others. But in order to meet the needs of high-level and conditional autonomy, sensors themselves need a technology-assist. Materials-science specialist BASF is enhancing the understanding of what materials may aid the sensing equation.
Buchholz, Kami
Cooperative Ramp Merging System: Agent-Based Modeling and Simulation Using Game Engine12-02-02-00085/16/2019
Agent-based modeling and simulation (ABMS) has been a popular approach for modeling autonomous and interacting agents in a multi-agent system. Specifically, ABMS can be applied to connected and automated vehicles (CAVs) since CAVs can operate autonomously with the help of onboard sensors, and cooperate with each other through vehicle-to-everything (V2X) communications. In order to improve energy efficiency and mobility of traffic, we have developed an online feedforward/feedback longitudinal controller for CAVs to cooperatively merge at ramps. Agent-based CAV models were built in the Unity3D environment, where vehicles are given connectivity and autonomy through C#-based scripting application programming interface (API). Agent-based infrastructure model is also built as a Unity3D simulation network based on the city of Mountain View, California. A simulation of cooperative on-ramp merging is carried out with a distributed consensus-based protocol, and then compared with the human-in-the-loop simulation where the on-ramp merging vehicle is driven by four different human drivers on a driving simulator. The benefits of introducing the proposed protocol are evaluated in terms of travel time, energy consumption, and pollutant emissions. The results show that the proposed cooperative on-ramp merging protocol can reduce average travel time, energy consumption, and pollutant emissions by 7%, 8%, and 58%, respectively, when compared to the human-in-the-loop scenario.
Wang, Ziran, Wu, Guoyuan, Boriboonsomsin, Kanok, Barth, Matthew J., Han, Kyungtae, Kim, BaekGyu, Tiwari, Prashant
Situational Awareness, Driver’s Trust in Automated Driving Systems and Secondary Task Performance12-02-02-00095/16/2019
Driver assistance systems, also called automated driving systems, allow drivers to immerse themselves in non-driving-related tasks. Unfortunately, drivers may not trust the automated driving system, which prevents either handing over the driving task or fully focusing on the secondary task. We assert that enhancing situational awareness (SA) can increase a driver’s trust in automation. SA should increase a driver’s trust and lead to better secondary task performance. This study manipulated drivers’ SA by providing them with different types of information: the control condition provided no information to the driver, the low condition provided a status update, while the high condition provided a status update and a suggested course of action. Data collected included measures of trust, trusting behavior, and task performance through surveys, eye-tracking, and heart rate data. Results show that SA both promoted and moderated the impact of trust in the automated vehicle (AV), leading to better secondary task performance. This result was evident in measures of self-reported trust and trusting behavior.
Petersen, Luke, Robert, Lionel, Yang, Xi Jessie, Tilbury, Dawn
Vehicle Distance Measurement Algorithm Based on Monocular Vision and License Plate Width2019-01-08824/2/2019
In order to avoid the influence of the change of the camera pitch angle and the variation of the height of the ground on the ranging accuracy, improve the real-time performance of the algorithm by substituting the current widely-used monocular vision ranging algorithm which builds the optical model based on the shadow of the vehicle floor and the lane line, as well as avoid the classification of vehicle detection, a vehicle distance measurement algorithm based on monocular vision and license plate width is established. Firstly, the target image acquisition and preprocessing are studied. Then the paper studies the license plate image location segmentation method based on accelerated template matching. On this basis, the algorithm for obtaining the ratio of license plate width to image width is studied, and the function of vehicle distance and license plate ratio width is established. The actual vehicle test shows that the relative average deviation of the algorithm is 0.5% and the standard deviation of 10 repetitive experiments is 0.000216. The accuracy, repeatability and robustness of the algorithm are good.
Zhong, Jian, Chen, Xinbo, Peng, Yibing, Li, Yan
An Immersive Vehicle-in-the-Loop VR Platform for Evaluating Human-to-Autonomous Vehicle Interactions2019-01-01434/2/2019
The deployment of autonomous vehicles in real-world scenarios requires thorough testing to ensure sufficient safety levels. Driving simulators have proven to be useful testbeds for assisted and autonomous driving functionalities but may fail to capture all the nuances of real-world conditions. In this paper, we present a snapshot of the design and evaluation using a Cooperative Adaptive Cruise Control application of virtual reality platform currently in development at our institution. The platform is designed so to: allow for incorporating live real-world driving data into the simulation, enabling Vehicle-in-the-Loop testing of autonomous driving behaviors and providing us with a useful mean to evaluate the human factor in the autonomous vehicle context.
Rastogi, Vibhor, Merco, Roberto, Kaur, Manveen, Rayamajhi, Anjan, Gavelli, Marco, Papa, Gianluca, Pisu, Pierluigi, Babu, Sabarish, Robb, Andrew, Martin, Jim
Automated Vehicle Disengagement Reaction Time Compared to Human Brake Reaction Time in Both Automobile and Motorcycle Operation2019-01-10104/2/2019
Autonomous Vehicle Disengagement Reports have been published by the California Department of Motor Vehicles since 2015. The State of California autonomous vehicle testing regulations require every manufacturer authorized to test autonomous vehicles on public roads to submit an annual report summarizing disengagements. In early versions of the annual report, automated vehicle manufacturers were required to provide the time that it took for a human driver to take manual control of the vehicle when reporting vehicle disengagements. This study analyzes reported automated vehicle disengagement reaction times from 2015 through 2017 for various manufacturers that provided information to the California Department of Motor Vehicles while operating vehicles in autonomous mode. This study compares the reported automated vehicle operation disengagement reaction time to field literature in testing and experimentation on human brake reaction times for both automobile and motorcycle operation.
Dinges, Jeffrey T., Durisek, Nicholas J.
GNSS Based Lane Keeping Assist System via Model Predictive Control2019-01-06854/2/2019
Recently, the field of autonomous driving has been dramatically expanding, and some of the key technologies like the Lane Keeping Assist (LKA) system have begun to be applied to mass production vehicles. In general, mass-produced LKA systems use a lane detection camera as a means of keeping the lane. One of the common limitations of camera-based LKA systems is that the lane keeping performance significantly decreases when the camera cannot detect lane markings for various reasons such as snow coverage and sunlight. To overcome this limitation, we have developed a Global Navigation Satellite System (GNSS) based LKA system, which is not affected by the surrounding environment such as weather and lighting. Our LKA system uses centimeter-level augmentation service and high-definition maps, whereby the LKA system can accurately estimate its own position. This feature potentially enables our LKA system to show higher lane-keeping performance than camera-based LKA systems even when lane markings are undetectable. In our previous study, we proposed a GNSS based LKA system in which the target steering angle was calculated by means of a PID controller based on a look-ahead model. Although there were a few problems such as oscillation of steering, the proposed system enabled a real vehicle to keep the lane even under conditions in which camera based LKA systems would probably not work well. In this paper, to aim at improving lane keeping performance, we proposed a GNSS based LKA system that calculates target steering angle via Model Predictive Control (MPC). We then validated the lane keeping performance of the LKA system using MPC in both a simulation and in real vehicle tests.
Tominaga, Kenta, Takeuchi, Yu, Tomoki, Uno, Kameoka, Shota, Kitano, Hiroaki, Quirynen, Rien, Berntorp, Karl, Cairano, Stefano
Coupling Safety Distance Model for Vehicle Active Collision Avoidance System2019-01-01304/2/2019
As an important part of the active collision avoidance system of the vehicle, the safety distance model determines the safety of the vehicle and the utilization of the road. The safety distance is too large to affect the traffic flow of the road. If it is too small, it will cause traffic accidents. Therefore, the design of the safety distance model depends on whether it can adapt to the complex and changing traffic environment, and effectively balance the safety of the driving process, the car following and the utilization of the road. According to the actual requirements of system security alarm and system false alarm reduction, three safety distance models and one constraint condition are established. The safety distance model maintained by the vehicle spacing, the safety distance model reflecting the characteristics of the driver, and the longitudinal minimum safety distance model when steering the lane change. When the pre-crash time is equal to the driver response time, the distance at this time is the minimum constraint condition of the warning distance. Based on these, a coupled safety distance model is established. The correctness of the coupled safety distance model is verified by the joint simulation of MATLAB/Simulink and CarSim. The simulation results show that the coupled safety distance model can achieve the system safety warning and the safety active braking function. The false alarm rate and the emergency braking false trigger rate of the active collision avoidance system are low. It can well eliminate the false alarm when the car turns to change lanes.
Dong, Jie, Chu, Liang
Cooperative Adaptive Cruise Control Design and Implementation2019-01-04964/2/2019
In this manuscript a design and implementation of CACC on an autonomous vehicle platform (2017 Ford Fusion) is presented. The developed CACC controls the intervehicle distance between the target vehicle and ego vehicle using a feedforward PD controller. In this design the feedforward information is the acceleration of the target vehicle which is communicated through Dedicated Short-Range Communication (DSRC) modem. The manuscript explains the detailed architecture of the designed CACC with used hardware and methods for the both simulation and experiments. Also, an approach to overcome detection failures at the curved roads is presented to improve overall quality of the designed CACC system. As a result, the initial simulation and experimental results with the designed CACC system is presented in the paper. The presented results indicate that CACC improves the car following performance of the ego vehicle as compared to the classical Adaptive Cruise Controller.
Cantas, Mustafa Ridvan, Gelbal, Sukru Yaren, Guvenc, Levent, Aksun Guvenc, Bilin
Analysis of Driver’s Behavior under Following-Go Scenario2019-01-10184/2/2019
The driver’s behavior under following-go scenario, which has been involved in little research so far, is an important part of the driver's following behavior. Analysis of driver's behaviour under following-go scenario is important for improving the performance and the adaptability of ACC (Adaptive Cruise Control) systems in urban traffic environment. In this paper driver’s behavior under following-go scenario in real traffic is studied based on naturalistic driving data. Starting reaction time and starting distance from the target vehicle are used to evaluate driver’s starting timing under following-go scenario. Starting acceleration is used to evaluate the effect of driver’s acceleration operation under following-go scenario. The naturalistic driving data collected in china is screened and classified and the following-go scenario is obtained. The driver’s behaviour parameters under following-go scenario are extracted and the statistical characteristics are obtained. Influence factors are analyzed with univariate ANOVA (Analysis of Variance) and regression analysis. The results show that the starting reaction time and the starting distance from the target vehicle approximately obey the lognormal probability distribution and the starting acceleration approximately obeys the normal probability distribution. Environmental factors such as road type, target vehicle type and lighting condition don’t have obvious influence on the driver's behaviour under following-go scenario. The starting distance from the target vehicle is mainly affected by the stopping distance from the target vehicle and increases with it while the starting reaction time and the starting acceleration are mainly affected by the starting acceleration of the target vehicle. As the starting acceleration of the target vehicle increases, the starting reaction time is shorter and the starting acceleration is larger.
Xia, Lan, Zhu, Xichan, Ma, Zhixiong
Tracking of Extended Objects with Multiple Three-Dimensional High-Resolution Automotive Millimeter Wave Radar2019-01-01224/2/2019
Estimating the motion state of peripheral targets is a very important part in the environment perception of intelligent vehicles. The accurate estimation of the motion state of the peripheral targets can provide more information for the intelligent vehicle planning module which means the intelligent vehicle is able to anticipate hazards ahead of time. To get the motion state of the target accurately, the target’s range, velocity, orientation angle and yaw rate need to be estimated. Three-dimensional high-resolution automotive millimeter wave radar can measure radial range, radial velocity, azimuth angle and elevation angle about multiple reflections of an extended target. Thus, the three-dimensional range information and three-dimensional velocity information can be obtained. With multiple three-dimensional high-resolution automotive millimeter-wave radar, it is possible to measure information in various directions of a target. For tracking of extended objects with multiple three-dimensional high-resolution automotive millimeter wave radar, firstly, the information of one target in different radar is obtained by the clustering algorithm, and then it is fused by an unscented Kalman filter, and the tracking algorithm needs to consider the information of different scattering points of the target, and the speed information component of the target needs to be considered as the tracking feature. Thus, a motion model with target’s range, velocity, orientation angle and yaw rate are established for the tracking algorithm. The results show that the tracking algorithm is able to estimating the target information with acceptable error.
Bai, Jie, Tan, Bin, Bi, Xin, Huang, Libo
An Investigation of the Influence of Close-Proximity Traffic on the Aerodynamic Drag Experienced by Tractor-Trailer Combinations2019-01-06484/2/2019
Recent research to investigate the aerodynamic-drag reduction associated with truck platooning systems has begun to reveal that surrounding traffic has a measurable impact on the aerodynamic performance of heavy trucks. A 1/15-scale wind-tunnel study was undertaken to measure changes to the aerodynamic drag experienced by heavy trucks in the presence of upstream traffic. The results, which are based on traffic conditions with up to 5 surrounding vehicles in a 2-lane configuration and consisting of 3 vehicle shapes (compact sedans, SUVs, and a medium-duty truck), show drag reductions of 1% to 16% for the heavy truck model, with the largest reductions of the same order as those experienced in a truck-platooning scenario. The data also reveal that the performance of drag-reduction technologies applied to the heavy-truck model (trailer side-skirts and a boat-tail) demonstrate different performance when applied to an isolated vehicle than to conditions with surrounding traffic. The results suggest that vehicle shape optimization strategies may differ if the influence of wake effects from surrounding traffic is included in product development cycles. Additionally, truck-platooning benefits should be taken in the context of typical traffic scenarios for which trucks are already experiencing a background-platooning effect and therefore may not be expected to attain the benefits relative to isolate-vehicle conditions.
McAuliffe, Brian, Ahmadi-Baloutaki, Mojtaba
Honda fills a gap with 2019 Passport19AUTP04_164/1/2019
You may think that by now, just about all full-line automakers have every crossover/SUV segment covered. Small, medium and large, just like it used to be with sedans. Honda didn't see it that way, though. The best-selling CR-V is the company's “small” crossover (assuming you don't altogether consider the smaller HR-V a crossover) and the 3-row Pilot is the large entry-with nothing in between.
Visnic, Bill
Two Simple Requirements for Deterrence of Traffic Jam and Its Verification and Practical Use2019-01-14373/25/2019
This paper tries to give a new point of view that shows what should be controlled to avoid or reduce or possibly eliminate the traffic jam. First, it is shown that 1) Keeping appropriate distance between cars even when they are in low speed or stopping condition, 2) All cars should start with no delay, are 2 requirements for avoiding traffic jam and these ideas would not be provided by AI only with vast scale learning of general traffic. Next, 2 requirements for avoiding traffic jam are verified by experiments on the test course with using 10 cars in various conditions of distance between cars by 3 measurement methods complemented each other. Then, as a practice, it is reported how it can be explained and how it should be solved the problem of the place where traffic jam occurs frequently in Japan being applied the 2 simple requirements. And finally, it is suggested that all cars should be equipped the device that warns less distance and start timing to the following car that is easily implemented to safety cars, and vast reservation system should be adopted to expressway to limit numbers of cars on safe ground that is theoretically derived from the 2 simple requirement for deterrence of traffic jam discussed on this paper.
Oku, Hideaki
Safety Testing for AVs is Just Beginning19AVEP03_093/1/2019
There is much work to be done in creating accurate, reliable tests for occupant crashworthiness tailored to new AV designs and seating configurations. NHTSA's plan to eventually update its New Car Assessment Program (NCAP) with new crash-test protocols is good news for both consumers and the mobility safety-systems industry. A revised NCAP will likely feature enhanced occupant safety testing as well as testing of active-safety features such as adaptive cruise control and automatic braking. It's also a positive step for autonomous vehicle (AV) developers. Studies show U.S. consumers are still resistant to the idea of self-driving cars, and such testing will provide the public with assurances that these vehicles are safe. This should serve to “warm up” consumers to the idea of a world with AVs, boosting demand and paving the way for an increasingly safer mobility future.
O'Connor, Christopher
Detroit auto show 2019: Cadillac finally gets its 3-row crossover19AUTP02_152/1/2019
Cadillac has added another SUV to its lineup with the global debut of the all-new, three-row XT6 at the 2019 Detroit auto show. The XT6 joins the two-row XT4 and XT5 in Caddy's lineup and is a unibody alterative to Cadillac's other three-row SUV, the truck-based Escalade. The 6- or 7-passenger XT6 will be available in two trims-Premium Luxury and Sport-with each offering distinct interior and exterior styling. The XT6 provides a host of available safety technology and should compete directly with Lincoln's new 2020 Aviator three-row SUV. The 2020 XT6 will be powered by GM's 3.6L V6 (310 hp/231 kW). Active fuel management permits V4 operation in lower-load scenarios. All models will feature a 9-speed automatic and four selectable drive modes, with AWD available on the Premium Luxury model and standard on the XT6 Sport. The Sport model will also feature a “twin-clutch” AWD setup with active yaw control, a quicker steering ratio and active dampers. The Sport model will be available with 21-in (533-mm) wheels, a first for a Cadillac SUV.
Seredynski, Paul
Detroit auto show 2019: Next-gen Ford Explorer goes rear-drive19AUTP02_142/1/2019
The 6th-generation Ford Explorer looks to retain its all-time best-selling-SUV in America status by adding driver assist and other technologies, while dropping its former front-drive/all-wheel-drive (AWD) platform in favor of Ford's new “corporate” CD6 rear-wheel-drive/AWD architecture first revealed for the 2020 Lincoln Aviator. The 2020 Ford Explorer and its Lincoln Aviator sibling are the first midsize SUVs arriving in the marketplace after the automaker's 2018 downshift from nine global platforms to five flexible vehicle architectures. “This is a pretty significant change for us,” Hau Thai Tang, Ford Motor Company's executive VP of product development and purchasing told reporters at the 2020 Explorer's January 9 global debut at Detroit's Ford Field.
Buchholz, Kami
Emotion Analytics for Advanced Driver Monitoring System2019-26-00251/9/2019
From the recent advances in Driver Monitoring Systems (DMS) from automotive domain, research on Human Computer Interaction (HCI) based on emotion analytics has gained good interest from the research circles. Distraction and drowsiness will be causing more percentage of traffic accidents, but with the use of advanced DMS technology, we can significantly reduce these distractions and can make the driving a safer activity. Our proposed solution/approach with disguised emotion detection with analytics is enabled by machine learning and image processing algorithms to ensure that the detection of drowsiness or distraction is very accurate. The proposed method will inform the HMI system to provide an alert to wake up the driver if he or she is in drowsy state or take the proactive/necessary actions with the help of active safety systems. Emotion analytics is a technique which is used to analyze the emotion of an individual. It is used to recognize the change in the emotion. Deep Learning is used for the implementation of computer vision techniques which is implemented with the help of Convolutional Neural Network (CNN). In recent times, CNN has been successfully applied in analyzing visual images for many automotive applications. CNN model can be applied to recognize the emotion. We have trained CNN model with different depth using grayscale images. Emotions can be classified into following six categories i.e. Happy, Sad, Surprise, Angry, Neutral and Fear. After recognition, emotions are continuously analyzed. We recorded the emotion in particular time frame like how many times a person is Happy, Sad, Surprised etc. Standard & Tata Elxsi’s proprietary database is used for training the Emotion Recognition System. Proposed system is tested in Raspberry pi board and results found satisfactory. This analysis will help us to monitor the activity of driver. In case of any abnormal behavior we can take corrective measure to control the situation.
Nandyala, Sivaprasad, K, Gayathri, Bhushan, Chandra, Gandi, Varaprasad, Manalikandy, Mithun
Florida's Babcock Ranch and the Future of Autonomous Communities19AVEP01_111/1/2019
An 18,000-acre development in southwest Florida seeks to be the model for short-range autonomous mobility and sustainable power for it all. A population boom over the last century has transformed the landscape of southwestern Florida, adapting it to the automobile. Thousands of square miles of palm groves, wetlands and scrub have given way to highways, driveways and parking lots. Isolated from this tangle of pavement between Port Charlotte and Ft. Myers is Babcock Ranch, which has remained stubbornly green. On an 18,000-acre tract within this green patch, a developer named Syd Kitson is pioneering a new and sustainable model for development in Florida and stepping past the century-old order of the automobile age. His mobility strategy features a fleet of autonomous cars shuttling residents on demand. While widespread use of such electric pods is still years away, Kitson predicts that within a decade at Babcock Ranch, “people will go from two cars to one. And soon after that, to none.”
Baker, Stephen
Predicting the Road to Efficiency19AVEP01_091/1/2019
Leveraging the building blocks of automated driving, Delphi's Intelligent Driving technology is designed to improve the efficiency and driving range of any vehicle. Delphi Technologies isn't coming right out to say most of us aren't very good at driving efficiently, but there's no getting around that's what's implied by the company's new Intelligent Driving technology, which its engineers said can improve the fuel economy of just about any vehicle by 10% or more when the system is engaged. The Intelligent Driving system, slated as the centerpiece of Delphi's presence at the 2019 CES in Las Vegas, mixes cutting-edge Delphi propulsion-system components with enabling technology for automated driving to deliver a system that uses autonomous functionality to “predict” the road ahead. If the vehicle-and its propulsion system-know what's coming up, it can avoid using fuel that the driver, without knowledge of the road ahead, would unknowingly waste.
Visnic, Bill
Movement Prediction Hypotheses for Pedestrians and Trajectory Planning for Cooperative Driving Systems12-02-01-000212/19/2018
It is a challenge to find a safe trajectory for automated vehicles in urban environments with pedestrians. The prediction of future movements with 100% certainty is impossible, if the intention is unknown. A Gaussian process approach is used to formulate future movement hypotheses of the pedestrian based on historical movements. A mixed integer linear programming (MILP) optimization approach is used for the trajectory planning of the vehicle. The collision probability between the ego-vehicle and pedestrian is used as constraints in the optimization. This approach is useful for cooperative vehicle systems, with historical movement data in a fixed urban environment (e.g., intersection) and the premise that pedestrians follow typical movement data.
Hartmann, Michael, Stolz, Michael, Watzenig, Daniel
Lexus soups-up seventh-generation ES sedan18AUTP11_1011/1/2018
Sedans and any configuration of a “car” might be a tough sell at the moment, but Toyota's Lexus division certainly wasn't going to let that stop it from launching a new, seventh generation of the ES midsize sedan, which by a large margin just happens to be the brand's best-selling car (51,398 last year in a shrinking U.S. market for sedan bodystyles). The ES typically accounts for nearly half of Lexus' total car sales. Considering that kind of sales critical mass, it's tough to say the ES has been injured by its reputation as being the softer “cruiser” of the Lexus car lineup, but the company seems to continually strive to inject more sporting character into the midsize sedan. Such is the case with the new 2019 ES-there are two variants, the ES350 with a 3.5-L V6 and the ES300h hybrid that went on sale in the U.S. in September-although refinement and isolation remain at the expected high levels.
Visnic, Bill
Toyota ‘hatches’ new Corolla variant18AUTP10_1510/1/2018
There are three good reasons why Toyota's compact Corolla overtook the original VW Beetle, the VW Golf and even the Ford F-Series to become the top-selling vehicle nameplate ever built: It's sold virtually around the globe and it owns a reputation as being affordable, reliable and efficient. But in those 52 years of Corolla history, very few iterations of the car have been sexy or exciting. Yet this new five-door hatchback variant of the 12th-generation E170 Corolla borders on both. Launched in Japan earlier this year as the Corolla Sport, it replaces the iM hatch in the U.S. that donned a Toyota badge when the Scion brand was waxxed in 2016. Except for its gaping bottom-feeder mouth, it actually looks pretty sporty. And the underpinnings are engineered for improved dynamic performance: the new hatch rides on a lighter, stiffer TNGA ‘modular’ platform with a sport-tuned suspension.
Witzenberg, Gary
Research on the Development Trend of Brain Controlled Cars2018-01-15878/7/2018
This paper studies the development trend of the brain controlled cars. A brain controlled car is a new application of the brain-computer interface (BCI) to the on-road motor vehicles. As a new frontier science, the relevant studies are exploratory and still at an early stage. The prospect of the brain controlled cars is also unclear. In this paper, we summarizes the research status of the brain controlled cars based on both the academic articles and publicly released demo cars. The research history, the achievable control functions, the vehicle types that implemented on, the testing scenarios and the technology roadmaps are elaborated. According to the development traces of both the intelligent connected vehicle (ICV) and the artificial intelligence (AI) technologies, we predicted the development trend of the brain controlled cars. This paper is from a novel angel that considering BCI technology as one of the driver assistance methods to make the driving experience more intelligent, more safe and reliable, more comfortable, and more compliant to the driver’s intention. The main finding of this paper is that human-computer collaborative driving by the hybrid-augmented intelligence is the irresistible trend of the brain controlled cars. The hybrid-augmented intelligence will mainly act on the environment perception module, the decision-making & planning module and the control & execution module of an autonomous driving car to achieve the full autonomous driving in the open traffic and maximally ensure the driving safety. Additionally, applying BCI technology to the human-computer interface (HMI) in a car makes the driving experiences more “people oriented”. This paper plays a positive role in promoting the applications of BCI technology to the on-road motor vehicles, accelerating the development of ICV, as well as improving our future driving experiences.
Bie, Weiwei, Li, Kai, Zhang, RuiLin, Huang, Yi, Fang, Qiang, Hu, Jin, Qian, Jianshu
Application Oriented Testcase Generation for Validation of Environment Perception Sensor in Automated Driving Systems2018-01-16148/7/2018
Validation is one of the main challenges in development of automated driving systems (ADS). Due to the complexity of these systems and the various influence factors on their functional safety, current testcase generation methods can hardly guarantee the completeness and effectivity of the validation on system level. Separate validation of system components is a way to make system approval possible. In this paper, an approach is presented to generate deductively testcases for the validation of the environment perception sensors, which are the most essential components of ADS. This approach is originated from the model-based testing method, which is commonly used to validate software-based systems and extended by considering various external influence factors as follows: By modeling and analyzing applications in ADS, application oriented usecases of perception sensors are first derived. Based on a classification of perception sensor errors, the sensor error types that are critical for each usecase are identified. Meanwhile, based on sensor working principle, the correspondence between external influence factors and each sensor error type are summarized in a morphological box. By combining the factors, which can “stimulate” a certain sensor error type that is critical for usecases, testcases can be generated. As an example, adaptive cruise control (ACC) system is analyzed as application in level 3 system instead of level 1 function in reality. This paper presents a structured deduction of testcases to make a complete validation of perception sensor for ADS possible. Some possibilities of testcase reduction and an outlook for further development and utilization are presented as well.
Cao, Peng, Huang, Libo
Research on the Radiated Immunity Test Methods of ADAS Functions in Intelligent Vehicles2018-01-16368/7/2018
According to the ISO 11451-2 [1], the immunity performance of passenger cars and commercial vehicle shall be validated to electrical disturbances from off-vehicle radiation sources. Typical vehicle electrical or electronic systems such as double flash, monitor, or audio and entertainments systems have been validated through a standardized immunity test process. As the development of ADAS (Automated Driver Assistance System) functions in the vehicle technology, the reliability and accuracy of these functions in the complex electromagnetic fields must be validated. Radar and Camera or Lidar sensor based functions of AEB (Automated Emerge Brake), ACC (Automated Cruise Control) or LDW (Lane Departure Warning) might be invalid, especially when these sensors were illuminated by electrical disturbances in the real word. This work presents a novel test methodology of whole-vehicle immunity to off-board electrical disturbances, considering the main ADAS functions. Target simulator and virtue driving-environment are designed to trigger AEB, ACC and LDW functions in an anechoic chamber. Under standardized off-board radiated sources, the reliability of ADAS functions in a real vehicle are invested.
Jia, Jin, Li, Biao, Li, Xu
Personalized Eco-Driving for Intelligent Electric Vehicles2018-01-16258/7/2018
Minimum energy consumption with maximum comfort driving experience define the ideal human mobility. Recent technological advances in most Advanced Driver Assistance Systems (ADAS) on electric vehicles not only present a significant opportunity for automated eco-driving but also enhance the safety and comfort level. Understanding driving styles that make the systems more human-like or personalized for ADAS is the key to improve the system comfort. This research focuses on the personalized and green adaptive cruise control for intelligent electric vehicle, which is also known to be MyEco-ACC. MyEco-ACC is based on the optimization of regenerative braking and typical driving styles. Firstly, a driving style model is abstracted as a Hammerstein model and its key parameters vary with different driving styles. Secondly, the regenerative braking system characteristics for the electric vehicle equipped with 4-wheel hub motors are analyzed and braking force distribution strategy is designed. Finally, MyEco-ACC is constructed and optimized via theory of Nonlinear Model Prediction Control (NMPC). Regenerated energy is taken as the indicator for energy consumption and the key parameter in driving style model is taken as the comfort indicator. Samples with 80 drivers obtained from the field test with both RT3000 family and RT-Range are used for analysis and further employed for the identification of driving style model. A co-simulation environment consisting of Carsim2016.1-RT ® and Mathwork Simulink® is established to verify the proposed personalized eco-driving strategy. Test results show that driving styles can be identified effectively and the driving style model has a high fidelity. Furthermore, simulation results show that the root mean square of ego vehicle acceleration aw,0.49Hz based on MyEco-ACC are close to those of the human drivers. The values of energy recycling efficiency based on MyEco-ACC range from 35.9% to 37.6% and close to that based on Eco-ACC but apparently higher than that based on ACC in the same simulation conditions.
Sun, Bohua, Deng, Weiwen, He, Rui, Wu, Jian, Li, Yaxin
Items per page:
1 – 50 of 267