Search Results

Objection detection using a camera sensor is essential for developing Advanced Driver Assistance Systems (ADAS) and Autonomous Driving (AD) vehicles. Due to the recent advancement in deep Convolution Neural Networks (CNNs), object detection based on CNNs has achieved state-of-the-art performance during daytime. However, using an RGB camera alone in object detection under poor lighting conditions, such as sun flare, snow, and foggy nights, causes the system's performance to drop and increases the likelihood of a crash. In addition, the object detection system based on an RGB camera performs poorly during nighttime because the camera sensors are susceptible to lighting conditions. This paper explores different pedestrian detection systems at low-lighting conditions and proposes a sensor-fused pedestrian detection system under low-lighting conditions, including nighttime. The proposed system fuses RGB and infrared (IR) thermal camera information.

A DMS (Driver Monitoring System) is one of the most important safety features that assist in the monitoring functions and alert drivers when distraction or drowsiness is detected. The system is based in a DSMC (Driver Status Monitoring Camera) mounted in the vehicle's dash, which has a predefined set of operational requirements that must be fulfilled to guarantee the correct operation of the system. These conditions represent a trade space analysis challenge for each vehicle since both the DSMC and the underlying vehicle’s requirements must be satisfied. Relying upon the camera’s manufacturer evaluation for every iteration of the vehicle’s design has proven to be time-consuming, resources-intensive, and ineffective from the decision-making standpoint.

Fretting fatigue was observed in standard cylindrical fatigue samples at the regions in contact with the grips of the test frames during fatigue testing for AlSi10Mg aluminum alloy produced by laser powder bed fusion process (L-PBF). The failure of the fatigue sample grips occurs much earlier than the failure of the gauge section. This results in a damaged sample and the sample cannot be reused to continue the test. This type of failure is rarely seen in materials produced by traditional manufacturing processes. In this study, X-ray residual stress analysis was performed to understand the cause of failure for L-PBF AlSi10Mg with the as-built surface condition. The result indicates that the fretting fatigue failure was caused by the strong tensile residual stress in the as-built state combining with the fretting wear between the sample and the grip. A few potential solutions to avoid the fretting fatigue failure were investigated.

Object avoidance for autonomous driving is a vital factor in safe driving. When a vehicle travels from any random start places to any target positions in the milieu, an appropriate route must prevent static and moving obstacles. Having the accurate depth of each barrier in the scene can contribute to obstacle prevention. In recent years, precise depth estimation systems can be attributed to notable advances in Deep Neural Networks and hardware facilities/equipment. Several depth estimation methods for autonomous vehicles usually utilize lasers, structured light, and other reflections on the object surface to capture depth point clouds, complete surface modeling, and estimate scene depth maps. However, estimating precise depth maps is still challenging due to the computational complexity and time-consuming process issues. On the contrary, image-based depth estimation approaches have recently come to attention and can be applied for a broad range of applications.

The Composite Hybrid Automotive Suspension System Innovative Structures (CHASSIS) is a project that developed structural commercial vehicle suspension components in high volume utilising hybrid materials and joining techniques to offer a viable lightweight production alternative to steel. Three components were selected for the project:- Front Subframe Front Lower Control Arm (FLCA) Rear Deadbeam Axle

Laser welding of the magnesium-bearing AA5xxx aluminum alloys is often beset by keyhole instability, especially in the lap through joint configuration. This phenomenon is characterized by periodic collapse of the keyhole leaving large voids in the weld zone. In addition, the top surface can exhibit undercut and roughness. In full penetration welds, keyhole instability can also produce a spikey root and severe top surface concavity. These discontinuities could prevent a weld from achieving engineering specification compliance, pose a craftsmanship concern, or reduce the strength and fatigue performance of the weld. In the case of a full penetration weld, a spikey root could compromise part fit-up and corrosion protection, or damage adjacent sheet metal, wiring, interior components, or trim.

A cast magnesium subframe was designed and manufactured for a C Class sedan to reduce weight and improve vehicle fuel economy. The magnesium subframe achieved 5 kg (32%) weight reduction from the equivalent steel subframe and met all the required structural performance targets. All the joints of the magnesium subframe were tested for bolt load retention. The tests were conducted with a temperature profile of 100°C to -30°C designed to investigate the creep behavior of the selected magnesium alloy AE44 under high stress.

This study reports the corrosion performance of three different coating strategies tested on an AE44 high performance magnesium strut tower brace used on the 2020 Ford Mustang Shelby GT500. The alloy was selected due to its improved structural performance at higher temperatures over conventional AM60B magnesium die castings. The first coating strategy used no pretreatment, conversion coating, or topcoat to gage the baseline corrosion performance of the uncoated alloy. The second coating strategy used a conventional pretreatment commonly used on AM60B alloy. The third used a ceramic-based conversion coating. A textured (stipple) powder coat was then applied to the two non-baseline parts over the pretreatment. All three coating strategies were then evaluated by comparing the corrosion performance after cyclic corrosion testing for 12 weeks using the Ford L-467 test.

A wet clutch model is required in automotive propulsion system simulations for enabling robust design and control development. It commonly assumes Coulomb friction for simplicity, even though it does not represent the physics of hydrodynamic torque transfer. In practice, the Coulomb friction coefficient is treated as a tuning parameter in simulations to match vehicle data for targeted conditions. The simulations tend to deviate from actual behaviors for different drive conditions unless the friction coefficient is adjusted repeatedly. Alternatively, a complex hydrodynamic model, coupled with a surface contact model, is utilized to enhance the fidelity of system simulations for broader conditions. The theory of elastic asperity deformation is conventionally employed to model clutch surface contact. However, recent examination of friction material shows that the elastic modulus of surface fibers significantly exceeds the contact load, implying no deformation of fibers.

This paper focuses on finding and analyzing the relevant parameters affecting traffic flow when autonomous vehicles are introduced for ride hailing applications and autonomous shuttles are introduced for circulator applications in geo-fenced urban areas. For this purpose, different scenarios have been created in traffic simulation software that model the different levels of autonomy, traffic density, routes, and other traffic elements. Similarly, software that specializes in vehicle dynamics, physical limitations, and vehicle control has been used to closely simulate realistic autonomous vehicle behavior under such scenarios. Different simulation tools for realistic autonomous vehicle simulation and traffic simulation have been merged together in this paper, creating a realistic simulator with Hardware-in-the-Loop (HiL), Traffic-in-the-Loop (TiL), and Software in-the-Loop (SiL) simulation capabilities.

The Composite Hybrid Automotive Suspension System Innovative Structures (CHASSIS) is a project to develop structural commercial vehicle suspension components in high volume utilising hybrid materials and joining techniques to offer a viable lightweight production alternative to steel. Three components are in scope for the project:- Front Subframe Front Lower Control Arm (FLCA) Rear Deadbeam Axle

To evaluate vehicle crash performance in the early design stages, a reliable fracture model is needed in crash simulations to predict material fracture initiation and propagation. In this paper, a generalized incremental stress state dependent damage model (GISSMO) in LS-DYNA® was calibrated and validated for a 780-MPa third generation advanced high strength steels (AHSS), namely 780 XG3TM steel that combines high strength and ductility. The fracture locus of the 780 XG3TM steel was experimentally characterized under various stress states including uniaxial tension, shear, plane strain and equi-biaxial stretch conditions. A process to calibrate the parameters in the GISSMO model was developed and successfully applied to the 780 XG3TM steel using the fracture test data for these stress states.

Autonomous Vehicles (AVs) operate based on image information and 3D maps generated by sensors like cameras, LIDARs and RADARs. This information is processed by the on-board processing units to provide the right actuation signals to drive the vehicle. For safe operation, these sensors should provide continuous high quality data to the processing units without interruption in all driving conditions like dust, rain, snow and any other adverse driving conditions. Any contamination on the sensor surface/lens due to rain droplets, snow, and other debris would result in adverse impact to the quality of data provided for sensor fusion and this could result in error states for autonomous driving. In particular, snow is a common contamination condition during driving that might block a sensor surface or camera lens. Predicting and preventing snow accumulation over the sensor surface of an AV is important to overcome this challenge.

Autonomous ground vehicles can use a variety of techniques to navigate the environment and deduce their motion and location from sensory inputs. Visual Odometry can provide a means for an autonomous vehicle to gain orientation and position information from camera images recording frames as the vehicle moves. This is especially useful when global positioning system (GPS) information is unavailable, or wheel encoder measurements are unreliable. Feature-based visual odometry algorithms extract corner points from image frames, thus detecting patterns of feature point movement over time. From this information, it is possible to estimate the camera, i.e., the vehicle’s motion. Visual odometry has its own set of challenges, such as detecting an insufficient number of points, poor camera setup, and fast passing objects interrupting the scene. This paper investigates the effects of various disturbances on visual odometry.

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.

As an alternative lightweight material, chopped carbon fiber reinforced Sheet Molding Compound (SMC) composites, formed by compression molding, provide a new material for automotive applications. In the present study, the monotonic and fatigue behavior of chopped carbon fiber reinforced SMC is investigated. Tensile tests were conducted on coupons with three different gauge length, and size effect was observed on the fracture strength. Since the fiber bundle is randomly distributed in the SMC plaques, a digital image correlation (DIC) system was used to obtain the local modulus distribution along the gauge section for each coupon. It was found that there is a relationship between the local modulus distribution and the final fracture location under tensile loading. The fatigue behavior under tension-tension (R=0.1) and tension-compression (R=-1) has also been evaluated.

Self-piercing rivet (SPR) joints are a key joining technology for lightweight materials, and they have been widely used in automobile manufacturing. Manual visual crack inspection of SPR joints could be time-consuming and relies on high-level training for engineers to distinguish features subjectively. This paper presents a novel machine learning-based crack detection method for SPR joint button images. Firstly, sub-images are cropped from the button images and preprocessed into three categories (i.e., cracks, edges and smooth regions) as training samples. Then, the Artificial Neural Network (ANN) is chosen as the classification algorithm for sub-images. In the training of ANN, three pattern descriptors are proposed as feature extractors of sub-images, and compared with validation samples. Lastly, a search algorithm is developed to extend the application of the learned model from sub-images into the original button images.

Stress and strain measurement of high density polyethylene (HDPE) fuel tanks under dynamic loading is challenging. Motion tracking combined with computer vision was employed to evaluate the strain in an HDPE fuel tank being dynamically loaded with a crash pulse. Traditional testing methods such as strain gages are limited to the small strain elastic region and HDPE testing may exceed the range of the strain gage. In addition, strain gages are limited to a localized area and are not able to measure the deformation and strain across a discontinuity such as a pinch seam. Other methods such as shape tape may not have the response time needed for a dynamic event. Motion tracking data analysis was performed by tracking the motion of specified points on a fuel tank during a dynamic test. An HDPE fuel tank was mounted to a vehicle section and a sled test was performed using a Seattle sled to simulate a high deltaV crash. Multiple target markers were placed on the fuel tank.

Automakers looking to remake their traditional vehicle line-up into autonomous vehicles, Noise, Vibration, and Harshness (NVH) considerations for autonomous vehicles are soon to follow. While traditional NVH considerations still must be applied to carry-over systems, additional components are required for an autonomous vehicle to operate. These additional components needed for autonomy also require NVH analysis and optimization. Autonomous vehicles rely on a suite of sensors, including Light Detection and Ranging (LiDAR) and cameras placed at optimal points on the vehicle for maximum coverage and utilization. In this study, the NVH considerations of autonomous vehicles are examined, focusing on the additional perception equipment installed in autonomous vehicles.

Lane marks are an important aspect for autonomous driving. Autonomous vehicles rely on lane mark information to determine a safe and legal path to drive. In this paper an approach to estimate lane lines on straight or slightly curved roads using a LiDAR unit for autonomous vehicles is presented. By comparing the difference in elevation of LiDAR channels, a drivable region is defined. The presented approach used in this paper differs from previous LiDAR lane line detection methods by reducing the drivable region from three to two dimensions exploring only the x-y trace. In addition, potential lane markings are extracted by filtering a range of intensity values as opposed to the traditional approach of comparing neighboring intensity values. Further, by calculating the standard deviation of the potential lane markings in the y-axis, the data can be further refined to specific points of interest.