The problem investigated in this paper is that of driving a car-like robot along a race track and the use of reinforcement learning to find a good control function. The reinforcement learner uses a case-based function approximator to extend the reinforcement learning paradigm to handle continuous states. The learned controller performs similar to the best control functions in both simulation an...

Several factors are considered in car accident analysis. Human factors research has shown that different perceptual and cognitive factors influence driving performance, leading to improvements in vehicle and road design. This case study provides a deeper understanding of the potential influence of major perceptual and cognitive variables on driving performance in general, including (a) driver e...

Driving is a complex behavior that requires the integration of multiple cognitive functions. While many studies have investigated brain activity related to driving simulation under distinct conditions, little is known about the brain morphological and functional architecture in professional competitive driving, which requires exceptional motor and navigational skills. Here, 11 professional raci...

In this paper, we uncover a new potential application for multi-media technologies: affective intelligent car interfaces for enhanced driving safety. We also describe the experiment we conducted in order to map certain physiological signals (galvanic skin response, heart beat, and temperature) to certain driving-related emotions and states (Frustration/Anger, Panic/Fear, and Boredom/Sleepiness)...

OBJECTIVE To assess the effects of antidepressants on driving performance from a different methodological viewpoint in light of the recent traffic accidents. METHODS In this double-blinded, 3-way crossover trial, 17 healthy males received acute doses of 10 mg paroxetine, 25 mg amitriptyline, and placebo. The subjects were administered three driving tasks--road tracking, car following, and har...

Emerging in-vehicle systems have turned the contemporary car into a human-computer interaction context that has its own set of rules and challenges. Interacting with in-vehicle systems while driving a car can greatly affect the driving performance and have been shown to be the cause of many road accidents. Evaluation of in-vehicle systems is a subject of much interest to developers and research...

Modern autonomous driving algorithms often rely on learning the mapping from visual inputs to steering actions from human driving data in a variety of scenarios and visual scenes. The required data collection is not only labor intensive, but such data are often noisy, inconsistent, and inflexible, as there is no differentiation between good and bad drivers, or between different driving intentio...

In this paper, we present the design and implementation of DrIveSCOVER, a recommender system for places and events in case of an in-car use, where the driving conditions such as weather and local traffic are taken into account. We integrate multiple data sources using semantic technologies and we devise recommending functions that are presented in a web-based application. Data is organized acco...

Nonintrusive monitoring of a driver's physiological signals was introduced and evaluated in a car as a test of extending the concept of ubiquitous healthcare to vehicles. Electrocardiogram, photoplethysmogram, galvanic skin response, and respiration were measured in the ubiquitous healthcare car (U-car) using nonintrusively installed sensors on the steering wheel, driver's seat, and seat belt. ...

Background A major proportion of fatally injured traffic accident victims are car drivers; in Norway in 1999 car drivers made up 47% of such victims (1). Several of the accidents involving these car drivers cannot be explained by the traffic environment (road, weather conditions etc), technical defects on cars or by risk taking behaviour (reckless driving, high speed etc). Impairment of the dri...