Driver Performance Model Research Articles

Investigation the Influence of Risk Factors on the Occurrence of Road Accidents Using the Driver Performance Model

Investigation the Influence of Risk Factors on the Occurrence of Road Accidents Using the Driver Performance Model

A Benchmarking of the Integrated Train Driver Performance Model

Human factors / ergonomics (HFE) focuses on the interaction of human with the environment. The traditionally concept of HFE has always focused on the interrelationship between three main elements of human-machine-environment. Therefore, significant to this research was that an integrated Malaysian train driver performance model has been successfully developed for identifying the significant factors that influence train driver performance, highlighting the interaction between human factors, human activities and its context. There are a number of models and frameworks in existence, designed to fulfil the various contexts of particular research. This newly developed model was compared with past models from the previous researches. Through this benchmarking approach, this study has looked at the significant factors in holistic and comprehensive perspective without ignoring other potential domains of factors. In conclusion, the previous referred models mostly from the UK and Australia addressed similar arising issues of their train drivers. Fatigue, driving activity and sleepiness were among factors mostly investigated. Yet, the characteristics of the performance were similar between Malaysia, UK and Australia. However, this integrated model provides better and more complete model evaluating human performance.

A Novel Driver Performance Model Based on Machine Learning

Models of road vehicle driver behaviour are widely used in several disciplines, like driver distraction and autonomous driving. In this paper, a novel driver performance model, which is unique for every driver, is introduced. The driver is modelled with machine learning algorithms, namely artificial neural network and adaptive neuro-fuzzy inference system. Every model is trained and validated with the data collected during the real-time driver-in-the-loop experiment on a vehicle simulator for each driver separately. In total, 18 participants contributed to the experiment. Although the prediction accuracy of the models depends on the algorithm specifications, the artificial neural network was slightly more accurate in driver performance prediction comparing to the adaptive neuro-fuzzy inference system. The driver models may be used in detection of driver distraction induced by in-vehicle information system.

Validity and Reliability Testing on Train Driver Performance Model Using a PLS Approach

The purpose of this paper is to explain the assessment of validity and reliability of measured items used in survey research. The structural equation modeling techniques and Partial Least Square (PLS) will be adopted to assess the goodness of measures of constructs used in a model to examine the performance of the Malaysian train drivers. The measurement process involves assessment of construct validity of the items and followed by convergent validity. Then, the composite reliability was assessed with internal consistency measure of Cronbachs alpha. Lastly, discriminant validity was tested to assess the validity of the measurement. The constructs are not supposed to measure other constructs or overlapping constructs.

Modeling the effect of driving experience on lane keeping performance using ACT-R cognitive architecture

ACT-R (adaptive control of thought-rational) is a computational cognitive architecture that consists of multiple modules for perception and attention (e.g., a visual module), response making (e.g., a motor module), and mental information processing (e.g., a goal module, declarative memory module, and procedural memory module). The output of an ACT-R model is a time course that shows the coordination of the activation of these modules in solving a cognitive task. The research reported in this paper used a driver performance model developed in ACT-R to examine the effect of driving experience on driversperformance of vehicle lateral position control. First, we compared the lane keeping performance between novice and experienced drivers in a simulated driving experiment with different road, speed, and driving conditions. Behavioral data collected from both groups of drivers were then modeled in the ACT-R driving model to analyze the cognitive mechanisms of the behaviors. The modeling results were similar to the human results. There were two main findings. (1) Novice drivers had poor lateral control skills evidenced by significantly greater lateral deviation compared with experienced drivers. The lack of control was more evident on curved roads than on straight roads. On curved roads, the novice driversdriving paths significantly shifted to the outside of the curve, whereas there was no such shift for experienced drivers. (2) The cognitive-architecture-based modeling in ACT-R revealed the mental processes including parallel processing between modules and serial processing between sub-tasks. One of the factors responsible for the difference in curved-road driving paths between the two groups of drivers may be the location of visual attention focus. Our model showed that the behavioral difference in curved-road driving paths can be modeled by assigning a visual attention focus point to the novice-driver model that is closer than that assigned to the experienced-driver model. The method and results of this study can be used to provide cognitive-psychological bases for improving the effectiveness and efficiency of driver training courses and developing intelligent driving assistance systems. This research also provides an application example and a successful experience of computational cognitive modeling using cognitive architectures such as ACT-R.

Queueing Network-Model Human Processor (QN-MHP)

Queueing Network-Model Human Processor (QN-MHP) is a computational architecture that integrates two complementary approaches to cognitive modeling: the queueing network approach and the symbolic approach (exemplified by the MHP/GOMS family of models, ACT-R, EPIC, and SOAR). Queueing networks are particularly suited for modeling parallel activities and complex structures. Symbolic models have particular strength in generating a person's actions in specific task situations. By integrating the two approaches, QN-MHP offers an architecture for mathematical modeling and real-time generation of concurrent activities in a truly concurrent manner. QN-MHP expands the three discrete serial stages of MHP, of perceptual, cognitive, and motor processing, into three continuous-transmission subnetworks of servers, each performing distinct psychological functions specified with a GOMS-style language. Multitask performance emerges as the behavior of multiple streams of information flowing through a network, with no need to devise complex, task-specific procedures to either interleave production rules into a serial program (ACT-R), or for an executive process to interactively control task processes (EPIC). Using QN-MHP, a driver performance model was created and interfaced with a driving simulator to perform a vehicle steering, and a map reading task concurrently and in real time. The performance data of the model are similar to human subjects performing the same tasks.

Driver Performance Model: I. Conceptual Framework

A comprehensive model that combines the necessary aspects of vehicle characteristics, manual control theory, and human sensory and cognitive capabilities (and limitations) is needed to efficiently and effectively guide experiments, and to predict or assess overall driver performance. Such a model would enable Army program managers to rank competing workload configurations and scenarios in proposed vehicles, and to focus resources on the most promising. Ultimately such a model would replace or significantly reduce reliance on the current costly process: multiple hardware iterations of “design-test-fix.” Currently no such comprehensive model exists. This paper discusses a conceptual framework designed to encompass the relationships, conditions and constraints related to direct, indirect and teleoperated modes of driving, and so provides a guide or “road-map” for the construction and creation of a comprehensive driver performance model.

On-Road Versus Simulator Data in Driver Model Development Driver Performance Model Experience

Driver Performance Model (DPM) development has provided results reflecting on the debate between on-road and driving-simulator data in driving research. Developed for FHWA, DPM is a computational micro-process model of driver behavior that has been designed to simulate—in detail—the driver’s perceptual, cognitive, and control processes to generate steering, braking, and acceleration inputs to the vehicle. The requirement to develop driver data for prediction of absolute on-road performance—versus typical interest in ordinal findings to be later validated via on-road studies—led to the collection of comparable on-road and simulator data and their subsequent comparison. Comparisons of corresponding curve-entry speeds and speed profiles revealed a profound divergence between the on-road and simulator results ( t = 9.39, p < .005). Compared with simulator drivers, on-road drivers tended to have higher curve-entry speeds for the more difficult (sharper) curves and lower speeds for the less difficult curves. This trend, though reduced in magnitude, was apparent even after statistical adjustments for differences in respective tangent speeds ( t = 2.67, p < .01). These results are discussed in light of emerging on-road and simulator capabilities. The discussion and earlier results altogether supported two conclusions: ( a) debate concerning on-road versus simulator research studies is likely to continue with their rapidly emerging individual capabilities, and ( b) on-road research currently provides the best basis for driver model development where one-to-one real-world predictions are required (e.g., DPM).

Computational Techniques Used in the Driver Performance Model of the Interactive Highway Safety Design Model

The Interactive Highway Safety Design Model (IHSDM) is a high-priority research area for FHWA. IHSDM is a software system for evaluating the safety of alternative highway designs in a computer-aided design environment. The initial phase of this research program is to develop IHSDM for use in the design of two-lane rural highways. IHSDM includes a driver-vehicle module that simulates the moment-to-moment actions of a single driver-vehicle unit. Reviewed are the computational approaches that have guided the implementation of the driver performance model (DPM) that along with a vehicle model and other components constitute the driver-vehicle module. Five major computational functions of DPM are reviewed: perception, speed decision, path decision, speed control, and path control. Comparison of model results with data from a driving simulator demonstrates the ability of DPM to account for the horizontal curve deflection angle on the speed profile.

Attention-Based Model of Driver Performance in Rear-End Collisions

Several driver-performance factors contribute to rear-end collisions—driver inattention, perception-reaction time, and limitations of the human visual system. Although many evaluations have examined driver response to various rear-end collision avoidance systems (RECAS) display and algorithm alternatives, little research has been directed at creating a quantitative model of driver performance to evaluate these alternatives. Current considerations of driver behavior in developing warning algorithms tend to ignore the fundamental problem of driver inattention and assume a fixed driver reaction time with no further adjustment after the initial response. A more refined model of driver response to rear-end crash scenarios can identify more appropriate and timely information to be displayed to the driver. An attention-based rear-end collision avoidance model (ARCAM) is introduced that describes the driver’s attention distribution, information extraction and judgment process, and the reaction process. ARCAM predicts the closed-loop nature of collision response performance and explains how the driver might use RECAS warnings.

The Development of a Computer Simulation Model of Driver Performance to Predict Accident Probability

The National Highway Traffic Safety Administration (NHTSA) is sponsoring the development of a computer simulation model of driver/vehicle system performance in various accidently likely traffic scenarios. Its acronym is DRIVEM ( Driver Vehicle Effectiveness Model). By modeling driver detection of critical events (e.g., lead car deceleration), evasive maneuver decision making, control inputs, and the subsequent vehicle trajectory, DRIVEM can translate the diverse research data on driver performance into quantitative predictions of accident probability. When the model is fully developed, NHTSA will have an analytic tool to permit it to quickly and inexpensively compare alternative crash avoidance measures. This paper summarizes the development of DRIVEM, its submodels, its limitations, and needed refinements.