ITC/USA 2006 Conference Proceedings / The Forty-Second Annual International Telemetering Conference and Technical Exhibition / October 23-26, 2006 / Town and Country Resort & Convention Center, San Diego, California / Drivers’ visibility is an area of automobile safety that has seen very limited improvement over the past several decades. Limited visibility is responsible for many car accidents all across America. Mirrors require constant readjustment, and are easily blocked. There is currently a lot of interest in ways to reduce or eliminate all mirrors on a car, and one such method is through a wide-angle network of cameras mounted on the vehicle’s rear. Using real-time video processing, the data from several cameras can be spliced together, and displayed on a vehicle’s dashboard in an intuitive, easy to understand fashion that a driver can quickly see without having to turn away from the road. This has extensive application to light armored vehicles in the military, as well as to automotive designers today.

Our thesis is made in collaboration with Autoliv Sweden and the department Global Development Seatbelt in Vårgårda. Autoliv was founded in 1953 by two brothers from Vårgårda. Since then, they have become world leading in automotive safety and cooperates with several major automotive companies.   The aim of the project was to evaluate a concept that Adrian Bud for Global Development Seatbelt department in Vårgårda had come up with. The concept aims to simplify the design and reduce the number of parts in an adaptive load limiter (LLA). With a reduction in the number of parts, the price for the LLA would decrease and also make assembly easier.   An LLA adjusts the chest compression from the seatbelt in a crash sequence. This helps reducing the injury that might result from such chest compressions in a crash. The load limiter ensures that the slowdown of the body is done in a smooth manner by adjusting the amount of belt released.   Our concept evaluation has included conceptual design, primary design, visualization of design in Catia V5 and FEM analysis. Finally prototypes were built with the help of Autolivs central workshop and tests were performed at Autoliv. The report also includes analyzes of the results, recommendations for the continuation of work and development and a critical review of the evaluation.

This thesis' work has been conducted at and made possible by Autoliv Sverige AB in Vårgårda. The aim of this thesis is to study how the occupant experience of the belt changes when it is moved from a traditional installation point in the car's B-pillar, to the seat. This shall be studied in terms of how the perceived comfort is influenced by a belt in seat in an upright and a reclined seat back position of 20 and 45 degrees, for different sizes of occupants. Also how the ability to reach a belt in seat is affected by the size and mobility of the occupant. Based on this new knowledge, an optimal outlet position for a belt in seat shall be proposed, from a comfort perspective. The work has used a cross-sectional research approach to achieve its purpose. Through the cross-sectional approach, several different qualitative and quantitative methods have been used. Initially, a literature study where subjects relevant to the forthcoming study was studied. Meanwhile, a competitive analysis of existing belt in seat installations in new cars available on the market was planned and carried out. In the main element of this work, a two-part comfort and mobility study with a belt in seat was performed. The study combined the methods interview, survey and observation. Through the interview, qualitative questions were asked as a complement to the quantitative responses given by the test subjects on scales in the survey. Observations were used to observe the subjects' behavior and difficulties regarding the belt in seat. A major limitation of the results of the study is the deficient distribution of sitting heights and genders in the group of test subjects, which founded a certain bias in the results. This has been the reason why it has not been possible to draw any certain conclusions from the results, however, some trends have been seen. The comfort study revealed several different assessments of the belt that contributed to discomfort, including the perception of the belt being too close to the neck or too far out on the shoulder. Additionally, the discomfort significantly impaired when the seat was reclined to the relaxed state. The mobility study showed that more subjects felt limited by their own bodies in the movement than by the belt. In addition did the reversed belt geometry create large discomfort issues at the neck. An important conclusion of this thesis is that the seat's design is as important to the customer experience of discomfort of the belt as the positioning of the outlet. It has also become clear that the accessibility of a belt in seat is strongly limited, as it was tested in this study.

Platelets made of slit and chopped unidirectional, carbon-fiber prepreg are becoming a popular option for use as a high performance molding compound because of their high fiber volume fraction and increased ability to flow compared to continuous fiber systems. As this molding compound is newly introduced to industry, increasing amounts of research have gone into understanding how platelets flow during molding and how components perform mechanically based on the final orientation state of platelets. This work investigates the performance of prepreg platelet molding compound (PPMC) as a viable alternative to continuous fiber systems for use with geometrically complex structural members on vehicles subjected to collisions. In doing so, the crash performance, energy absorption, and failure morphology of crush tubes made with PPMC are investigated and quantified. Then, a simulation methodology is developed to obtain manufacturing-informed performance models to predict the effect of platelet orientation state on mechanical behavior of PPMC components. This methodology uses a building block approach where each block in modeling is verified against closed-form solution (when available) and validated against experimental results. Once confidence is developed in a modeling block, the complexity of the simulation is increased until a component with full platelet orientation distribution is captured. The result is PPMC component models that are capable of predicting mechanical performance in orientation regimes that are not investigated experimentally.

Software has emerged as a significant part of many domains, including financial service platforms, social networks, medical devices and vehicle control. In critical domains, standards organizations have responded to this by creating regulations to address issues such as safety, security and privacy. In this context, compliance of software with standards has emerged as a key issue. For companies, compliance is a complex and costly goal to achieve and is often accomplished by producing so-called assurance cases, which demonstrate that the system indeed satisfies the property imposed by a standard (e.g., safety, security, privacy) by linking evidence to support claims made about the system. However, as systems undergo evolution for a variety of reasons, including fixing bugs, adding functionality or improving system quality, maintaining assurance cases multiplies the effort. Increasingly, models and model-driven engineering are being used as a means to facilitate communication and collaboration between the stakeholders in the compliance value chain and, further, to introduce automation into regulatory compliance tasks. A complexity problem also exists with the proliferation of software models in model-based software development, and the field of Model Management has emerged to address this challenge. Model Management focuses on a high-level view in which entire models and their relationships (i.e., mappings between models) can be manipulated using specialized operators to achieve useful outcomes. In this thesis, we exploit this connection between model driven engineering and regulatory compliance, and explore how to use Model Management techniques to address software compliance management issues, focusing on assurance case change impact assessment, evolution and reuse. We support the presented approach with tooling and a case study. Although the main contributions of this thesis are not domain specific, for validation, we ground our approaches in the automotive domain and the ISO 26262 standard for functional safety of road vehicles. / Thesis / Doctor of Philosophy (PhD)

<p>EfficientNet is designed to achieve top accuracy while utilizing fewer parameters, in addition to less computational resources compared to previous models. </p> <p><br></p> <p>In this paper, we are presenting compound scaling method that re-weight the network's width (w), depth (d), and resolution (r), which leads to better performance than traditional methods that scale only one or two of these dimensions by adjusting the hyperparameters of the model. Additionally, we are presenting an enhanced EfficientNet Backbone architecture. </p> <p><br></p> <p>We show that EfficientNet achieves top accuracy on the ImageNet dataset, while being up to 8.4x smaller and up to 6.1x faster than previous top performing models. The effectiveness demonstrated in EfficientNet on transfer learning and object detection tasks, where it achieves higher accuracy with fewer parameters and less computation. Henceforward, the proposed enhanced architecture will be discussed in detail and compared to the original architecture.</p> <p><br></p> <p>Our approach provides a scalable and efficient solution for both academic research and practical applications, where resource constraints are often a limiting factor.</p> <p><br></p>

No description available.

This thesis presents significant advancements in the field of driver’s chest localization and breathing detection using FMCW radar. It introduces a neural network model for predicting the 3D location of the driver’s chest and a novel algorithm for detecting breathing patterns and localizing the chest position. These scientific breakthroughs contribute to the development of an adaptive safety system for level 3 and above autonomous driving within the IFAS project (FKZ 19A19009E).

In this thesis, methods for radar-based environment perception from the vehicle safety point of view are presented. The proposed methods comprise advanced topics of radar-based target detection and tracking in dynamic pre-crash scenarios, as well as ghost object identification. The problem of a wandering dominant scatter point on the target surface and corresponding challenge for accurate target tracking in low-range configurations is considered. The proposed method presents a procedure to estimate target wheel positions and corresponding bulk velocities to serve as fixed scatter points on the target surface. Input to this method are raw radar data. The technique spatially resolves the micro-Doppler signals, generated by the rotating wheels of the target vehicle, to determine characteristic scatter points on the target surface. A micro-Doppler parameter is defined to quantify detections that are with high probability generated by the rotating target wheels. This group of detections is processed to estimate the wheel position and corresponding bulk velocities of the target, referred to as wheel hypotheses. The proposed method is evaluated in dynamic driving scenarios, where the driver performs an emergency evading action to avoid a collision. Subsequently, the detected wheel hypotheses serve as input to a developed tracking framework, which is used to estimate the target object static and dynamic states. Since the number of detected wheel hypotheses varies, a random-finite-set-based measurement model is used to incorporate multiple wheel hypotheses detected for one extended target object. The tracking performance is evaluated in critical evading scenarios using real vehicles as the target object. In addition, the thesis emphasized the problem of ghost object generation due to multipath propagation in pre-crash scenarios. Radar sensors, perceiving the immediate vehicle environment, show an elevated ghost object presence due to a higher probability illuminating potential reflection surfaces, e.g., road boundaries or buildings. At times, these ghost objects appear to be on a collision trajectory with the ego vehicle, whereas the vehicles are in uncritical driving scenarios, e.g., an urban intersection. In real-world driving scenarios, one target object may generate multiple false-positive targets. Based on the propagation and reflection behavior of electromagnetic waves, a geometric multipath model is derived, illustrating the occurring multipath reflections on real-world surfaces, e.g., buildings or road-bounding barriers. The proposed geometric propagation model describes the relative positions of the false-positive reflections and is validated with extensive real radar data. A custom reflector target mounted on a platform, creating deterministic point targets as dominant backscatter centers of a vehicle body, validated the different multipath reflections and the overall accuracy of the model. Moreover, radar measurements of a vehicle during an intersection scenario proved relevance to multipath reflection behavior and confirmed the model assumptions. Third, the relevance of skid scenarios with high magnitudes of side slip angles in pre-crash phases is highlighted. A novel test methodology, to non-destructively transfer vehicles with mounted surround sensors in skid situations, is developed and a survey analyzing a state-of-the-art radar sensor revealed the potential to improve object tracking performance. A test vehicle, equipped with a state-of-the-art automotive radar sensor and a reference sensor, was tested in real skid situations using a kick plate and a standardized radar target. The test method utilizes the side slip angle as a criticality criterion, which may be adjusted by the kick plate. Subsequently, a novel, modified motion model is derived, estimating side slip angles in these skid driving situations. The contribution emphasizes the estimation of horizontal vehicle motion using the proposed model considering an additional lateral force applied to the vehicle rear axle. Based on these results, an Extended-Kalman filter is designed to estimate the target object relative position and velocity in skid scenarios. The evaluation includes both the tracking and side slip angle estimations in real car tests using the above-mentioned test method.

<p><a>Proactive evaluation of road safety is one of the most important objectives of transportation engineers. While current practice typically relies on crash-based analysis after the fact to diagnose safety problems and provide corrective countermeasures on roads, surrogate measures of safety are emerging as a complementary evaluation that can allow engineers to proactively respond to safety issues. These surrogate measures attempt to address the primary limitations of crash data, which include underreporting, lack of reliable insight into the events leading to the crash, and long data collection times. </a></p> <p>Traffic conflicts are one of the most widely adopted surrogate measures of safety because they meet the following two conditions for crash surrogacy: (1) they are non-crash events that can be physically related in a predictable and reliable way to crashes, and (2) there is a potential for bridging crash frequency and severity with traffic conflicts. However, three primary issues were identified in the literature that need to be resolved for the practical application of conflicts: (1) the lack of consistency in the definition of traffic conflict, (2) the predictive validity from such events, and (3) the adequacy of traffic conflict observations.</p> <p>Tarko (2018) developed a theoretical framework in response to the first two issues and defined traffic conflicts using counterfactual theory as events where the lack of timely responses from drivers or road users can produce crashes if there is no evasive action. The author further introduced a failure-based definition to emphasize conflicts as an undesirable condition that needs to be corrected to avoid a crash. In this case, the probability of a crash, given failure, depends on the response delay. The distribution of this delay is adjusted, and the probability is estimated using the fitted distribution. As this formal theory addresses the first two issues, a complete framework for the proper identification of conflicts needs to be investigated in line with the failure mechanism proposed in this theory.</p> <p>The objective of this dissertation, in response to the third issue, is to provide a generalized framework for proper identification of traffic conflicts by considering the failure-based definition of traffic conflicts. The framework introduced in this dissertation is built upon an empirical evaluation of the methods applied to identify traffic conflicts from naturalistic driving studies and video-based tracking systems. This dissertation aimed to prove the practicality of the framework for proactive safety evaluation using emerging technologies from in-vehicle and roadside instrumentation.</p> <p>Two conditions must be met to properly claim observed traffic events as traffic conflicts: (1) analysis of longitudinal and lateral acceleration profiles for identification of response due to failure and (2) estimation of the time-to-collision as the period between the end of the evasion and the hypothetical collision. Extrapolating user behavior in the counterfactual scenario of no evasion is applied for identifying the hypothetical collision point.</p> <p>The results from the SHRP2 study were particularly encouraging, where the appropriate identification of traffic conflicts resulted in the estimation of an expected number of crashes similar to the number reported in the study. The results also met the theoretical postulates including stabilization of the estimated crashes at lower proximity values and Lomax-distributed response delays. In terms of area-wide tracking systems, the framework was successful in identifying and removing failure-free encounters from the In-Depth understanding of accident causation for Vulnerable road users (InDeV) program.</p> <p>This dissertation also extended the application of traffic conflicts technique by considering estimation of the severity of a hypothetical crash given that a conflict occurs. This component is important in order for conflicts to resemble the practical applications of crashes, including the diagnostics of hazardous locations and evaluating the effectiveness of the countermeasures. Countermeasures should not only reduce the number of conflicts but also the risk of crash given the conflict. Severity analysis identifies the environmental, road, driver, and pre-crash conditions that increase the likelihood of severe impacts. Using dynamic characterization of crash events, this dissertation structured a probability model to evaluate crash reporting and its associated severity. Multinomial logistic models were applied in the estimation; and quasi-complete separation in logistic regression was addressed by providing a Bayesian estimation of these models.</p>