Search Results

With economic development and the increasing number of vehicles in cities, urban transport systems have become an important issue in urban development. Efficient traffic signal control is a key part of achieving intelligent transport. Reinforcement learning methods show great potential in solving complex traffic signal control problems with multidimensional states and actions. Most of the existing work has applied reinforcement learning algorithms to intelligently control traffic signals. In this paper, we investigate the agent-based reinforcement learning approach for the intelligent control of ramp entrances and exits of urban arterial roads, and propose the Proximal Policy Optimization (PPO) algorithm for traffic signal control. We compare the method controlled by the improved PPO algorithm with the no-control method.

A special spot weld element (SWE) is presented for simplified representation of spot joints in complex structures for structural durability evaluation using the mesh-insensitive structural stress method. The SWE is formulated using rigorous linear four-node Mindlin shell elements with consideration of weld region kinematic constraints and force/moments equilibrium conditions. The SWEs are capable of capturing all major deformation modes around weld region such that rather coarse finite element mesh can be used in durability modeling of complex vehicle structures without losing any accuracy. With the SWEs, all relevant traction structural stress components around a spot weld nugget can be fully captured in a mesh-insensitive manner for evaluation of multiaxial fatigue failure.

Level 2 (L2) partial driving automation systems are rapidly emerging in the marketplace. L2 systems provide sustained automatic longitudinal and lateral vehicle motion control, reducing the need for drivers to continuously brake, accelerate and steer. Drivers, however, remain critically responsible for safely detecting and responding to objects and events. This paper summarizes variations of L2 systems (hands-on and/or hands-free) and considers human drivers’ roles when using L2 systems and for designing Human-Machine Interfaces (HMIs), including Driver Monitoring Systems (DMSs). In addition, approaches for examining potential unintended consequences of L2 usage and evaluating L2 HMIs, including field safety effect examination, are reviewed. The aim of this paper is to guide L2 system HMI development and L2 system evaluations, especially in the field, to support safe L2 deployment, promote L2 system improvements, and ensure well-informed L2 policy decision-making.

Self-piercing riveting (SPR) are one of most important joining approaches in lightweight vehicle design for Body-in-white (BIW) manufacturing. Numerical simulation of the riveting process could significantly boost design efficiency by reducing trial-and-error experiments. The traditional Finite Element Method (FEM) with element erosion is hard to capture the large plastic deformation and complex failure behaviors in the SPR process. The smoothed Particle Galerkin Method (SPG) is a genuine meshless method based on Galerkin's weak form, which uses a novel bond-based failure mechanism to keep the conservation of mass and momentum during the material failure process. This study utilizes a combined FEM and SPG approach to join Aluminum sheet 5754 using a full three-dimensional (3D) model in LS-DYNA/explicit.

Often, when assessing the distraction or ease of use of an in-vehicle task (such as entering a destination using the street address method), the first question is “How long does the task take on average?” Engineers routinely resolve this question using computational models. For in-vehicle tasks, “how long” is estimated by summing times for the included task elements (e.g., decide what to do, press a button) from SAE Recommended Practice J2365 or now using new static (while parked) data presented here. Times for the occlusion conditions in J2365 and the NHTSA Distraction Guidelines can be determined using static data and Pettitt’s Method or Purucker’s Method. These first approximations are reasonable and can be determined quickly. The next question usually is “How likely is it that the task will exceed some limit?”

With the development of vehicles equipped with automated driving systems, the need for systematic evaluation of AV performance has grown increasingly imperative. According to ISO 34502, one of the safety test objectives is to learn the minimum performance levels required for diverse scenarios. To address this need, this paper combines two essential methodologies - scenario-based testing procedures and scoring systems - to systematically evaluate the behavioral competence of AVs. In this study, we conduct comprehensive testing across diverse scenarios within a simulator environment following Mcity AV Driver Licensing Test procedure. These scenarios span several common real-world driving situations, including BV Cut-in, BV Lane Departure into VUT Path from Opposite Direction, BV Left Turn Across VUT Path, and BV Right Turn into VUT Path scenarios.

This paper proposes a detection algorithm based on deep learning for Vulnerable Road Users such as pedestrians and cyclists, which is improved on the basis of YOLOv5 network model. (1) Aiming at the problems of low resolution and insufficient information for small targets, a multi-scale feature fusion method is adopted to integrate shallow features with deep features.

Automated vehicles, in the form we see today, started off-road. Ideas, technologies, and engineers came from agriculture, aerospace, and other off-road domains. While there are cases when only on-road experience will provide the necessary learning to advance automated driving systems, there is much relevant activity in off-road domains that receives less attention. Implications of Off-road Automation for On-road Automated Driving Systems argues that one way to accelerate on-road ADS development is to look at similar experiences off-road. There are plenty of people who see this connection, but there is no formalized system for exchanging knowledge. Click here to access the full SAE EDGETM Research Report portfolio.

Compared with traditional welding, self-piercing riveting technology has unique advantages and is widely used in automobile lightweight technology. The riveting quality of self-piercing riveting is closely related to the safety and durability of automobiles. The detection of riveting quality has gradually become an important part of the automobile manufacturing process. The generation of surface cracks under self-piercing riveting will affect the riveting strength, which in turn affects the riveting quality. Therefore, the detection of riveting external quality is transformed into the detection of riveting surface cracks. The existing artificial vision-based riveting lower surface crack recognition technology is inefficient, subjective and cannot be applied on a large scale. Therefore, this paper will propose a local-overall strategy based on image processing and computer vision.

The use of lightweight materials is one of the important means to reduce the quality of the vehicle, which involves the connection of dissimilar materials, such as the combination of lightweight materials and traditional steel materials. The riveting quality of self-piercing riveting (SPR) technology will directly affect the safety and durability of automobiles. Therefore, in the initial joint development process, the quality of self-piercing riveting should be inspected and classified to meet safety standards. Based on this, this paper divides the self-piercing riveting quality into riveting appearance quality and riveting section quality. Aiming at the appearance quality of riveting, the generation of cracks on the lower surface of riveting will seriously affect the riveting strength. The existing method of identifying cracks on the lower surface of riveting based on artificial vision has strong subjectivity, low efficiency and cannot be applied on a large scale.

The Lane Change Task (LCT) provides a simple, scorable simulation of driving, and serves as a primary task in studies of driver distraction. It is widely accepted, but somewhat limited in functionality, a problem this project partially overcomes. In the Lane Change Task, subjects drive along a road with 3 lanes in the same direction. Periodically, signs appear, indicating in which of the 3 lanes the subject should drive, which changes from sign to sign. The software is plug-and-play for a current Windows computer with a Logitech steering/pedal assembly, even though the software was written 18 years ago. For each timestamp in a trial, the software records the steering wheel angle, speed, and x and y coordinates of the subject. A limitation of the LCT is that few characteristics of this useful software can be readily modified as only the executable code is available (on the ISO 26022 website), not the source code.

Making manned and remotely-controlled wheeled and tracked vehicles easier to drive, especially off-road, is of great interest to the U.S. Army. If vehicles are easier to drive (especially closed hatch) or if they are driven autonomously, then drivers could perform additional tasks (e.g., operating weapons or communication systems), leading to reduced crew sizes. Further, poorly driven vehicles are more likely to get stuck, roll over, or encounter mines or improvised explosive devices, whereby the vehicle can no longer perform its mission and crew member safety is jeopardized. HMI technology and systems to support human drivers (e.g., autonomous driving systems, in-vehicle monitors or head-mounted displays, various control devices (including game controllers), navigation and route-planning systems) need to be evaluated, which traditionally occurs in mission-specific (and incomparable) evaluations.

Engaging in visual-manual tasks such as selecting a radio station, adjusting the interior temperature, or setting an automation function can be distracting to drivers. Additionally, if setting the automation fails, driver takeover can be delayed. Traditionally, assessing the usability of driver interfaces and determining if they are unacceptably distracting (per the NHTSA driver distraction guidelines and SAE J2364) involves human subject testing, which is expensive and time-consuming. However, most vehicle engineering decisions are based on computational analyses, such as the task time predictions in SAE J2365. Unfortunately, J2365 was developed before touch screens were common in motor vehicles.

Automated driving is considered a key technology for reducing traffic accidents, improving road utilization, and enhancing transportation economy and thus has received extensive attention from academia and industry in recent years. Although recent improvements in artificial intelligence are beginning to be integrated into vehicles, current AD technology is still far from matching or exceeding the level of human driving ability. The key technologies that need to be developed include achieving a deep understanding and cognition of traffic scenarios and highly intelligent decision-making. Automated Vehicles, the Driving Brain, and Artificial Intelligenceaddresses brain-inspired driving and learning from the human brain's cognitive, thinking, reasoning, and memory abilities. This report presents a few unaddressed issues related to brain-inspired driving, including the cognitive mechanism, architecture implementation, scenario cognition, policy learning, testing, and validation.

Automated vehicles (AVs)—and the automated driving systems (ADSs) that enable them—are increasing in prevalence but remain far from ubiquitous. Progress has occurred in spurts, followed by lulls, while the motor transportation system learns to design, deploy, and regulate AVs. Automated Vehicles: A Human/Machine Co-learning Experience focuses on how engineers, regulators, and road users are all learning about a technology that has the potential to transform society. Those engaged in the design of ADSs and AVs may find it useful to consider that the spurts and lulls and stakeholder tussles are a normal part of technology transformations; however, this report will provide suggestions for effective stakeholder engagement. Click here to access the full SAE EDGETM Research Report portfolio.

Mobility in the automotive and transportation sectors has been experiencing a period of unprecedented evolution. A growing need for efficient, clean and safe mobility has increased momentum toward sustainable technologies in these sectors. Toward this end, battery electric vehicles have drawn keen interest and their market share is expected to grow significantly in the coming years, especially in light-duty applications such as passenger cars. Although the battery electric vehicles feature high performance and zero tailpipe emission characteristics, economic and technical issues such as battery cost, driving range, recharging time and infrastructure remain main hurdles that need to be fully addressed. In particular, the low power density of the battery limits its broad adoption in heavy-duty applications such as class 8 semi-trailer trucks due to the required size and weight of the battery and electric motor.

Developing pure electric powertrains have become an important way to reduce reliance on crude oil in recent years. This paper concerns energy management of dual motor-driven electric vehicles. In order to obtain a predictive energy management strategy with good performance in computation and energy efficiency, we propose a hybrid algorithm that combines model predictive control (MPC) and convex programming to minimize electrical energy use in real time control. First, few changes are occurred in original component models in order to convert the original optimal control problem into convex programming problem. Then convex optimization algorithm is used in the prediction horizon to optimize torque allocation between two electric motors with different size. To verify the effectiveness of the hybrid algorithm, a real city driving cycle is simulated. Furthermore, different predictive horizons are performed to illustrate the robustness and time efficiency of the proposed method.

In partly autonomous driving such as level 2 or level 3 automatic driving from SAE international classification, the switching of the driving right between the human driver and the machine plays an important role in the driving process of vehicle [1]. In this paper, the data collected from vehicle states and the driving behavior of drivers is completed via a simulator and self-report questionnaires. A fuzzy analytic network process (Fuzzy-ANP) model is developed to evaluate the driving capability of the drivers in real time from vehicle states due to its direct inherent link to the change of the driving state of drivers Moreover, in this model, the idea of group decision and multi-index fusion is adopted. The questionnaire is required to identify the experimental results from the simulator. The results show that the proposed Fuzzy-ANP model can evaluate the driving capability of the participants in real time accurately.