Search Results

A method for detecting drivers' intentions is essential to facilitate operating mode transitions between driver and driver assistance systems. We propose a driver behavior recognition method using Hidden Markov Models (HMMs) to characterize and detect driving maneuvers and place it in the framework of a cognitive model of human behavior. HMM-based steering behavior models for emergency and normal lane changes as well as for lane keeping were developed using a moving base driving simulator. Analysis of these models after training and recognition tests showed that driver behavior modeling and recognition of different types of lane changes is possible using HMMs.

The nearly 77 million baby boomers, born between 1946 and 1964, can say that they are the automobile generation. Now turning 60 one every seven seconds, what are the new safety challenges and opportunities posed by the next generation of older adults? This paper presents a modified Haddon matrix to identify key product development, design and liability issues confronting the automobile industry and related stakeholders. The industry is now at a critical juncture to address the development of key technological innovations as well as the changing policy and liability environments being reshaped by an aging population.

Forward collision warning (FCW) systems are intended to provide drivers with crash alerts to help them avoid or mitigate rear-end crashes. To facilitate successful deployment of FCW systems, the Ford-GM Crash Avoidance Metrics Partnership (CAMP) developed preliminary minimum functional requirements for FCW systems implemented on light vehicles (passenger cars, light trucks, and vans). This paper summarizes one aspect of the CAMP results: minimum requirements and recommendations for when to present rear-end crash alerts to the driver. These requirements are valid over a set of kinematic conditions that are described, and assume successful tracking and identification of a legitimate crash threat. The results are based on extensive closed-course human factors testing that studied drivers' last-second braking preferences and capabilities. The paper reviews the human factors testing, modeling of results, and the computation of FCW crash alert timing requirements and recommendations.

Injury Risk Curves are developed from cadaver data for sternal deflections produced by anterior, distributed chest loads for a 25, 45, 55, 65 and 75 year-old Small Female, Mid-Size Male and Large Male based on the variations of bone strengths with age. These curves show that the risk of AIS ≥ 3 thoracic injury increases with the age of the person. This observation is consistent with NASS data of frontal accidents which shows that older unbelted drivers have a higher risk of AIS ≥ 3 chest injury than younger drivers.

This paper presents the new techniques/methods being used for the rapid vehicle development and system level performance assessment. It consists of two parts: the first part presents the automated multilevel substructuring (AMLS) technique, which greatly reduces the computational demands of larger finite element models with millions of degrees of freedom(DOF) and extends the capabilities to higher frequencies and higher level of accuracy; the second part is on the superelement in conjunction with the Component Mode Synthesis (CMS) and also Automated Component Mode Synthesis (ACMS) techniques. In superelement, a full vehicle model is divided into components such as Body-in-white, Front cradle/chassis, Rear cradle/chassis, Exhaust, Engine, Transmission, Driveline, Front suspension, Rear suspension, Brake, Seats, Instrument panel, Steering system, tires, etc. with each piece represented by reduced stiffness, mass, and damping matrices.

Accurately predicting real-world vehicle energy consumption is essential for optimizing vehicle designs, enhancing energy efficiency, and developing effective energy management strategies. This paper presents a data-driven approach that utilizes machine learning techniques and a comprehensive dataset of vehicle parameters and environmental factors to create precise energy consumption prediction models. The methodology involves recording real-world vehicle data using data loggers to extract information from the CAN bus systems for ICE and hybrid electric, as well as hydrogen and battery fuel cell vehicles. Data cleaning and cycle-based analysis are employed to process the dataset for accurate energy consumption prediction. This includes cycle detection and analysis using methods from statistics and signal processing, and then pattern recognition based on these metrics.