Wolfgang Stolzmann

An Algorithmic Description of ACS2

The various modifications and extensions of the anticipatory classifier system (ACS) recently led to the introduction of ACS2, an enhanced and modified version of ACS. This chapter provides an overview over the system including all parameters as well as framework, structure, and environmental interaction. Moreover, a precise description of all algorithms in ACS2 is provided.

Learning classifier systems: New models, successful applications

Abstract Rules are an accepted means of representing knowledge for virtually every domain. Traditional machine learning methods derive rules by exploring sets of examples using statistical or information theoretic techniques. Alternatively, rules can be discovered through methods of Evolutionary Computation such as genetic algorithms and learning classifier systems. In recent years, new models of learning classifier systems have been developed which have resulted in successful applications in a wide variety of domains (e.g., autonomous robotics, classification, knowledge discovery, modeling). These models have led to a resurgence of this area which for a certain period appeared almost at a dead end. This paper overviews the recent developments in learning classifier systems research, the new models, and the most interesting applications, suggesting some of the most relevant future research directions.

Driver-Activity Recognition in the Context of Conditionally Autonomous Driving

This paper presents a novel approach to automated recognition of the drivers activity, which is a crucial factor for determining the take-over readiness in conditionally autonomous driving scenarios. Therefore, an architecture based on head-and eye-tracking data is introduced in this study and several features are analyzed. The proposed approach is evaluated on data recorded during a driving simulator study with 73 subjects performing different secondary tasks while driving in an autonomous setting. The proposed architecture shows promising results towards in-vehicle driver-activity recognition. Furthermore, a significant improvement in the classification performance is demonstrated due to the consideration of novel features derived especially for the autonomous driving context.

Latent Learning and Action Planning in Robots with Anticipatory Classifier Systems

Two applications of Anticipatory Classifier Systems (ACS) in robotics are discussed. The first one is a simulation of an experiment about latent learning in rats with a mobile robot. It shows that an ACS is able to learn latently, i.e. in the absence of environmental reward and that ACS can do action planning. The second one is about learning of the hand-eye coordination of a robot arm in conjunction with a camera. Goal-directed learning will be introduced. This combination of action planning and latent learning leads to a substantial reduction of the number of trials which are required to learn a complete model of a prototypical environment.

YACS: a new learning classifier system using anticipation

Abstract A new and original trend in the learning classifier system (LCS) framework is focussed on latent learning. These new LCSs call upon classifiers with a (condition), an (action) and an (effect) part. In psychology, latent learning is defined as learning without getting any kind of reward. In the LCS framework, this process is in charge of discovering classifiers which are able to anticipate accurately the consequences of actions under some conditions. Accordingly, the latent learning process builds a model of the dynamics of the environment. This model can be used to improve the policy learning process. This paper describes YACS, a new LCS performing latent learning, and compares it with ACS.

Investigating Generalization in the Anticipatory Classifier System

Recently, a genetic algorithm (GA) was introduced to the Anticipatory Classifier System (ACS) which surmounted the occasional problem of over-specialization of rules. This paper investigates the resulting generalization capabilities further by monitoring the performance of the ACS in the highly challenging multiplexer task in detail. Moreover, by comparing the ACS to the XCS classifier system in this task it is shown that the ACS generates accurate, maximally general rules and its population converges to those rules. Besides the observed ability of latent learning and the formation of an internal environmental representation, this ability of generalization adds a new advantage to the ACS in comparison with similar approaches.

Eye Movement Detection for Assessing Driver Drowsiness by Electrooculography

Many studies show that driver drowsiness is one of the main reasons for road accidents. To prevent such car crashes, systems are needed to monitor and characterize the driver based on the driving information. In order to have highly reliable assistant systems, reference drowsiness measurements are required. Among different physiological measures, previous studies have introduced driver eye movements, particularly blinking, as a measure with high correlation to drowsiness. Hence, in this study, eye movements of 14 drivers have been observed using electrooculography (EOG) at the moving-base driving simulator of Mercedes Benz to assess driver drowsiness. Based on the measured signals, an adaptive detection approach is introduced to simultaneously detect not only eye blinks, but also other driving-relevant eye movements such as saccades and micro sleep events. Moreover, in spite of the fact that drowsiness influences eye movement patterns, the proposed algorithm distinguishes between the often-confused driving-related saccades and decreased amplitude blinks of a drowsy driver. The evaluation of results shows that the presented detection algorithm outperforms common methods so that eye movements are detected correctly during both awake and drowsy phases.

Exploiting the potential of eye movements analysis in the driving context

Driving is a complex and highly visual task. With the development of high-end eyetracking devices, numerous studies over the last two decades have investigated eye movements of the driver to identify deficits in visual search patterns and to derive assistive, informative, and entertainment systems. However, little is known about the visual behavior during autonomous driving, where the driver can be involved in other tasks but still has to remain attentive in order to be able to resume control of the vehicle. This work aims at exploiting the potential of eye movement analysis in the autonomous driving context. In a pilot study, we investigated whether the type of the secondary task in which the driver is involved, can be recognized solely from the eye movement parameters of the driver. Furthermore, we will discuss several applications of eye movement analysis to future autonomous driving approaches, e.g., to automatically detect whether the driver is being attentive and – when required – to guide her visual attention towards the driving task.

Road dependent driver eye movements under real driving conditions by electrooculography

Electrooculography (EOG) as a tool to measure the driver eye movements allows us to distinguish between drowsiness- or distraction-related and driving situation dependent eye movements. Thus, an experiment under fully controlled conditions is carried out to study the relationship between driver eye movements and different real driving scenarios. In this experiment, unwanted head vibrations within EOG signals and the sawtooth pattern (optokinetic nystagmus, OKN) of eyes are realized as situation dependent eye movements. The former occurs due to ground excitation and the latter during small radius (50m) curve negotiation. The statistical investigation expresses a significant variation of EOG due to unwanted head vibrations. Moreover, an analytical model is developed to explain the possible relationship of OKN and tangent point of the curve. The developed model is validated against the real data on a high curvature track.

Eye blink detection for different driver states in conditionally automated driving and manual driving using EOG and a driver camera

In this article, we examine the performance of different eye blink detection algorithms under various constraints. The goal of the present study was to evaluate the performance of an electrooculogram- and camera-based blink detection process in both manually and conditionally automated driving phases. A further comparison between alert and drowsy drivers was performed in order to evaluate the impact of drowsiness on the performance of blink detection algorithms in both driving modes. Data snippets from 14 monotonous manually driven sessions (mean 2 h 46 min) and 16 monotonous conditionally automated driven sessions (mean 2 h 45 min) were used. In addition to comparing two data-sampling frequencies for the electrooculogram measures (50 vs. 25 Hz) and four different signal-processing algorithms for the camera videos, we compared the blink detection performance of 24 reference groups. The analysis of the videos was based on very detailed definitions of eyelid closure events. The correct detection rates for the alert and manual driving phases (maximum 94%) decreased significantly in the drowsy (minus 2% or more) and conditionally automated (minus 9% or more) phases. Blinking behavior is therefore significantly impacted by drowsiness as well as by automated driving, resulting in less accurate blink detection.