Adaptive Driver Assistance Systems Research Articles

Formation of the law of steering angle control to maintain a trajectory of the vehicle movement

The object of the study is a control system for changing and maintaining the trajectory of the vehicle. Methods of maintaining a trajectory of the vehicle are the subject of research. Multi-body dynamics (MBD) methods are used to solve this problem. The purpose of the study is development of management model change the trajectory of the vehicle. On the example of a two-axle four-wheel drive truck, a mathematical model of the vehicle includes subsystems-transmission, springing system and steering. The study of the influence of the transmission and suspension to change the trajectory of the car is not considered. The paper deals with the formation of the steering angle control law to maintain a given trajectory. A detailed description of the developed control model and analytical dependencies for setting the parameters of the model. An example of selection of coefficients for its setting is shown, recommendations for other types of calculation modes are offered. In this paper, the calculation of one calculation case corresponding to the rearrangement of the car, followed by a return to the original lane. This example proves the adequacy of the model. The developed mathematical model can be used in the systems of calculation of solid body dynamos in the simulation of driver-driven cars, unmanned vehicles and adaptive driver assistance systems. The vehicle was described as a system of solid bodies connected by hinges and force interactions from the library of typical elements of the software package. According to this description of the system, the software package automatically formed a system of equations of motion and connections. The equations were solved using an implicit numerical method with variable pitch and automatic accuracy control.

Analysis of Traffic Related Factors and Vehicle Environment in Monitoring Driver’s Driveability

In case of driver-driven vehicles, the Adaptive Driver Assistance Systems (ADAS) typically focus on providing different driving assistance to the drivers, thereby reducing the load of the drivers. An important aspect that needs to be considered in this design is the real-time assessment of the state of the driver at the time of driving. This is extremely critical for safe driving environment. The common factors for driver’s driveability include measuring driver’s fatigue and distraction level, while driving in different vehicle and traffic environment. In this paper, the state-of-the-art techniques on driver’s driveability is explored through Face and Eye-tracking; while also giving equal importance to the vehicular traffic and the road environment. This paper surveys the advantages and disadvantages of the existing eye and face tracking mechanisms and their integration with the driving performance measures (driveability). Further, a beyond state-of-the-art proposal for head-pose estimation and eye-tracking patterns under controlled environment is presented. The paper throws pen many observations and also opens-up several challenges to further explore in this domain.

Recognizing Frustration of Drivers From Face Video Recordings and Brain Activation Measurements With Functional Near-Infrared Spectroscopy.

Experiencing frustration while driving can harm cognitive processing, result in aggressive behavior and hence negatively influence driving performance and traffic safety. Being able to automatically detect frustration would allow adaptive driver assistance and automation systems to adequately react to a driver’s frustration and mitigate potential negative consequences. To identify reliable and valid indicators of driver’s frustration, we conducted two driving simulator experiments. In the first experiment, we aimed to reveal facial expressions that indicate frustration in continuous video recordings of the driver’s face taken while driving highly realistic simulator scenarios in which frustrated or non-frustrated emotional states were experienced. An automated analysis of facial expressions combined with multivariate logistic regression classification revealed that frustrated time intervals can be discriminated from non-frustrated ones with accuracy of 62.0% (mean over 30 participants). A further analysis of the facial expressions revealed that frustrated drivers tend to activate muscles in the mouth region (chin raiser, lip pucker, lip pressor). In the second experiment, we measured cortical activation with almost whole-head functional near-infrared spectroscopy (fNIRS) while participants experienced frustrating and non-frustrating driving simulator scenarios. Multivariate logistic regression applied to the fNIRS measurements allowed us to discriminate between frustrated and non-frustrated driving intervals with higher accuracy of 78.1% (mean over 12 participants). Frustrated driving intervals were indicated by increased activation in the inferior frontal, putative premotor and occipito-temporal cortices. Our results show that facial and cortical markers of frustration can be informative for time resolved driver state identification in complex realistic driving situations. The markers derived here can potentially be used as an input for future adaptive driver assistance and automation systems that detect driver frustration and adaptively react to mitigate it.

Re-configuration in SOA-based adaptive driver assistance systems

Unlike state-of-the-art Driver Assistance Systems (DAS) upcoming technologies may not base on a static software and system architecture. This is especially true for DAS for truck and trailer combinations were the components needed are distributed over both parts of the articulated vehicle. As a truck might be connected to different trailers changes are very common. In order to handle these changes at runtime the usage of Service-oriented Architecture (SOA) is a promising approach. Hereby the functionalities are encapsulated into Services which are re-composed whenever the system architecture changes. As the Services in such a system run on small embedded units traditional approaches to process the re-composition as known for example from the Web Services domain cannot be adopted directly. This paper discusses the different composition approaches published in recent years and suggests an algorithm suited for this class of systems.

Formal verification of service-oriented adaptive driver assistance systems

Many future Driver-Assistance-Systems (DAS) will use components not permanently mounted to the vehicle. Unlike state-of-the-art DAS with static configurations, the system and software architecture changes at runtime. To handle configuration changes, Service Oriented Architecture (SOA) and automatic orchestration is a promising approach. Whenever systems are set up automatically, they have to be validated. This paper presents an approach based on formal methods. Existing component models are annotated with Quality-of-Service parameters and transformed automatically to Hybrid Automata. These automata are then composed to an overall system model and model checking is used to check safety properties. The complete transformation-orchestration-validation process is executed without user interaction and thus can be performed at runtime.

Monitoring Driver's Authority: Simulator Study

In this paper, a multimodal adaptive driver assistance system is studied on a simulator setup. The main goal is to determine human driver's attention and authority level in a cognitive model and to trigger timely warnings according to his/her driving intents and driving skills with respect to the possible driving situation and hazard scenarios. In the previous studies, a fairly restrictive vision-based driver assistance system has been deployed to detect lane departure, blind-spot and to monitor following distance, headway time. The presented system models driving task in a cognitive architecture and assesses the cognition of the human driver by modeling the situation awareness of the driver by using fuzzy sets. Each fuzzy set simply represents the expert driver's perception in both of the longitudinal and lateral traffic. The presented system evaluates the driver's driving skills and attention level by comparing the expert and human driver's reactions suited in a finite set of decision and maneuvering task. In case of hazard analysis, the system triggers timely warnings pointing the driver's attention at the lateral or longitudinal maneuvering tasks depending on the interpreted situation. Introductory experiments are performed with a limited number of participants, the test driving data including the driver's perception and reaction to the surrounding vehicles and traffic situations are collected by the use of vehicle simulator. And the presented multimodal adaptive driver assistance system is evaluated by the simulator. The preliminary results seem to be promising.

Continuous subjective strain measurement

Driver assistance and information systems are gaining more and more importance in modern vehicles. In addition to their specific functionalities, these systems also aim to optimise drivers' current strain, because overload as well as underload can increase errors, lead to critical situations and can create furthermore unpleasant experiences for the driver. As workload changes in a highly dynamic way, these systems have to react in a similarly dynamic manner. This requires a fast and dynamically changing estimation of the driver's strain. In recent studies, the author described the relationship among strain changes, driving manoeuvres and environmental factors. In order to further examine this dependency, a simulator study was conducted where traffic densities were varied and strain was measured continuously with the aim to analyse the level and time course of drivers' current strain. Implications for workload adaptive advanced driver assistance systems are discussed.