Search Results

This paper presents an empirical approach for estimating driver's cognitive workload using driving performance, especially lateral control ability through readily available sensors such as lane position and steering wheel angle. To develop a real-time approach for detecting cognitive distraction, radial basis probabilistic neural networks (RBPNN) were applied. Data for training and testing the RBPNN models were collected in a simulator experiment in which fifteen participants drove through a highway and were asked to complete auditory recall tasks. The best performing model could detect cognitive workload at the accuracy rate of 73.3%. The results demonstrated that the standard deviation of lane position and steering wheel reversal rate can be used to detect driver's cognitive distraction in real time.

This paper aims to investigate the relationship between driving style and fuel consumption through on-road assessment in highway driving. In order to find prominent measures in driving style which affect the fuel consumption, 15 younger drivers were asked to drive approximately 36Km of highway, and driving data, including real-time fuel consumption, vehicle speed, gear selection, brake/acceleration pedal usage and steering angle, were collected. The correlation analysis results suggested that the fuel efficiency was significantly affected by the average depth of acceleration pedal in highway driving in which the highest gear was engaged. Another interesting finding in this analysis was that the fuel consumption can be estimated by observing the variations in steering wheel because the standard deviation of steering wheel angle and the fuel consumption were highly correlated.

Model-based approaches can improve quality and reduce cycle time by simulating the models to perform early validation of requirements. These approaches can provide automated validation techniques by generating test cases from the model. This paper describes model-based automated test techniques in all phases of the product life cycle to maximize the early validation capabilities of model-based development processes. The paper proposes a model-based test process framework for all modeling phases including system modeling, architectural modeling and auto-generated software. The test automation technique consists of automatic test generation, execution and analysis. A Test Management System, which enables the automatic generation of requirement-based test cases, analysis of the test results and test database management, is developed through this study.

This paper aims for a seamless development process for automotive body network system development with model-based approach. It also describes a generic software architecture that provides clear-boundaries between the software components and that can also act as a guide for each development phase. The CASE tool Statemate is used for feature behavioral modeling and verification. NodeAllocator builds the ECU models by mapping the behavioral model and physical network architecture. The virtual prototypes and the basic bus communication information are created and validated using software in loop simulation. The validated functional models are refined for implementation models and MicroC is used for application task code, OS design and software integration.