Search

Deficit irrigation approaches have been applied in mitigation of pressure on global freshwater availability. Data from growth of plants under different water stress conditions allows the development of growth models taking into account irrigation scheduling. In this work, a model predictive control approach combined with a modified trellis decoding algorithm is applied to control growth of maize plants under deficit irrigation conditions by specifying the irrigation schedule required to achieve specific total leaf length at the end of a specified growth period. The brute force-based algorithm allows the control of growth to within 8.5 % of the desired final total leaf length over a growth period of seven days. The designed control algorithm is an adaptable solution that can be applied to different optimization goals related to plant growth and water consumption, and allows the user to evaluate best-case and worst-case scenarios in advance, which supports decision making with regard to irrigation decisions.

OA Förderung 2022 With a rapidly expanding global population placing an ever growing demand on freshwater resources, an increased focus on irrigation techniques tailored to the specific needs of plant appears as one solution to minimize overall freshwater consumption. Precision irrigation methods seek to realize an acceptable compromise between yield and irrigation water consumption through control of the timing and quantity of water supplied to plants. The goal is to maintain the water content of the soil, achieve specific water use efficiency with regard to yield or maintain the physiological response of the plant to water stress within predetermined limits. Reliance on soil moisture measurements to establish irrigation water demand inadequately addresses heterogenous distribution of water in soil. Growing research interest is observed detailing the determination of plant water status directly from physiological responses. This paper reviews irrigation control approaches based on different plant water status assessment techniques. A distinct focus is made on application scale of the discussed control approaches, an aspect that has not been considered intensively enough in previous discussions of irrigation control approaches. A discussion of the observed strengths and shortcomings and technological advances supporting the various methods used to quantify plant water status extends the review. Emerging trends that are likely to have an impact on plant water status determination and optimal timing and quantification of irrigation water requirements are integrated to show latest results. A peek into the future of precision irrigation foresees greater reliance on plant-based signals, both in characterization of the control variable, namely the plant water status, and in generation of controller outputs in terms of quantity and timing.

The use of ultrasonic waves in the context of SHM offers methods to analyze materials and systems. Both Acoustic Emission-based approaches (passive, active) are limited by the propagation characteristics of ultrasonic waves, especially in inhomogeneous materials like carbon fiber reinforced polymers (CFRP). The use of the piezoelectric and inverse piezoelectric effect is a very accurate method of sensing and exciting ultrasonic waves. However, the transducers resonance characteristics affect the waveforms. For illustration in this contribution different excitation signals are experimentally compared in frequency domain by fast Fourier transform (FFT) and in time-frequency domain by continuous wavelet transform (CWT). Then transducers effects along the propagation path of the wave are investigated. Frequency and fiber direction dependent damping factors of ultrasonic waves in CFRP as well as the influence of the transducers are determined. The distance between sensors in a sensor network is limited by attenuation, so fiber direction must be considered. Finally, by analyzing the frequency response of the transducer, a filtering method is developed to compensate for the resonance characteristics of the transducers. Finally, a more accurate estimate of the energy released and therefore a more accurate estimate of the severity of damages/failures is proposed.

Within human-machine systems the monitoring of human behavior contributes to the safety of the overall system. Detecting critical situations or observing human errors will allow to take over the guidance of systems by automation or to warn to affect the interaction operator/human. In the project FernBin beside others the supervision of the captain’s actions in inland shipping is addressed. The focus is to detect human errors and also non- optimal behaviors. Additionally a reliability-based analysis of the captain’s actions will also enable a safer driving behavior and the reduction of accidents and dangerous situations due to suitable warning and interaction strategies of the supervision system. In this contribution a Situation-Operator-Modeling (SOM) approach is used to describe the captain-vessel-interaction and to illustrate the captain’s behavior as a graph-based-model. As example a ‘Turn-around’ maneuver is considered. A SOM-based action space consisting of possible captain’s behaviors leading to a meaningful desired final situation is developed and applied to a ‘Turn-around’ maneuver. Using this approach a manifold of sequences can be generated describing the human interaction options. Subsequently and online a modified CREAM approach (cognitive reliability and error analysis method) is used allowing the calculation of the human reliability performance score (HPRS), resulting to static reliability measures. The HPRS can be also assigned directly to the SOM-action space. In difference to previous developments this allows beside the deterministic supervision (SOM) also the individualized definition of the safest/most reliable action sequence as well as the opposite. Therefore an event-discretized behavior model situated supervision performance of the captain’s driving behavior with human reliability score numbers is established for the first time. As example the behavior of remotely operating captains of inland vessels is used as experimental example.

Metalworking fluid (MWF) differentiating is of important significance as their additives affect metalworking process extremely so the evaluation of MWF should be suitable conducted. Acoustic Emission (AE) measurements can be easily taken as process-close measures for evaluating cutting and forming processes as well as MWFs performance. In thread forming process, AE measurements from different kinds of MWFs could be – related to the position of the tool - divided into different process phases: air, forward, and reverse phases. From physical view, forward part contains most useful AE data. Therefore, extracting forward part data from the overall signal is significant for MWFs classification. Because boundaries among different parts in time domain of AE signals are not clear, in this contribution, a new data processing method is proposed to abstract the forward part data from non-related parts of the whole measurement signal. For the first time, scalogram is applied to find the boundaries in time domain as an aid. Firstly, the intact measurement signal is transformed from time domain to time-frequency domain by continuous wavelet transform (CWT) and scalogram is acquired. As boundaries among different phases are obvious in scalogram, by reverse calculation, boundaries’ location in time domain could be defined and forward part data of each measurement are picked out. Afterwards, data in forward phase are divided into different samples and each sample contains data of one round. Finally, samples’ features are extracted and classified by convolutional neural network (CNN). By adjusting CNN structure and hyperparameters with cross validation method, features in time domain could be distinguished well. For five kinds of testing MWF, the classification accuracy is as high as 98.11 %. For reference, oil-based, and water-based MWF classification, the results can reach to 98.94 %. Accuracy for water-based MWF distinction is 97.55 % while for oil-based MWF distinction is 98.29 %. Comparing with results using the whole AE measurements, these results improve significantly. Good results show that the proposed data processing method could extract most useful information from the whole AE measurements in time domain for MWF distinction. Besides, the proposed method also provides an effective way for data analysis in the future.

OA Förderung 2021 In turbomachines, dry friction resulting from stator–rotor contacts is a severe problem that may degrade lifetime of the machine or even lead to complete failure. Knowledge about the system states and contact forces is beneficial for system monitoring or to prevent contacts through, e.g., active magnetic bearings. In this paper, a nonlinear model is derived that describes the lateral rotor vibrations in the case of contact and no contact. The elastic behavior of the shaft is modeled based on the finite-element method. The contact is described by a dry friction model. An augmented system description is formulated that allows estimation of rotor displacements and contact forces by means of nonlinear filtering approaches like an extended Kalman filter. A simulation study was conducted that explicitly considered the hazardous backward whirl. The suggested approach shows suitable estimation performance related to both state and contact force estimation.

8. INTERDISZIPLINÄRER WORKSHOP KOGNITIVE SYSTEME Verstehen, Beschreiben und Gestalten Kognitiver (Technischer) Systeme Duisburg, 26.-28. März 2019

Research in understanding human behavior is a growing field within the development of Advanced Driving Assistance Systems (ADASs). In this contribution, a state machine approach is proposed to develop a driving behavior recognition model. The state machine approach is a behavior model based on the current state and a given set of inputs. Transitions to different states occur or we remain in the same state producing outputs. The transition between states depends on a set of environmental and driving variables. Based on a heuristic understanding of driving situations modeled as states, as well as one of the related actions modeling the state, using an assumed relation between them as the state machine topology, in this paper, a crisp approach is applied to adapt the model to real behaviors. An important aspect of the contribution is to introduce a trainable state machine-based model to describe drivers&rsquo, lane changing behavior. Three driving maneuvers are defined as states. The training of the model is related to the definition/tuning of transition variables (and state definitions). Here, driving data are used as the input for training. The non-dominated sorting genetic algorithm II is used to generate the optimized transition threshold. Comparing the data of actual human driving behaviors collected using driving simulator experiments and the calculated driving behaviors, this approach is able to develop a personalized behavior recognition model. The newly established algorithm presents an easy to apply, reliable, and interpretable AI approach.

This paper presents a novel (Extended/Unscented) Kalman Filter by augmenting the event handling procedure of Ordinary Differential Equation (ODE) solvers with the predictor-corrector scheme of Extended/Unscented discrete Kalman Filter (EKF/UKF) introducing a variable step size Kalman Filter. This innovation allows a new quality of precision while operating Kalman Filters. The original Kalman Filter is based on a time-discrete predictor-corrector scheme considering fixed step size. The main new idea is to introduce and control step size handling not introduced before. Step size control of EKF/UKF will increase the performance when applied to switching/stiff systems. The step size is controlled based on the current performance (EKF/UKF innovation) and is adapted during the estimation procedure based on an event handling algorithm. The proposed event handling algorithm consists of two parts: relaxing sample time and restricting sample time (ST). Relaxing procedure is used to avoid high computational time when no rapid change exists in system dynamics. Restricting procedure is considered to improve the estimation performance by decreasing the EKF/UKF step size in the case of fast dynamical behavior (switching/stiff behavior). Effectiveness of the proposed approach is verified considering the well-known Van der Pol oscillator as a common example of stiff systems.

Germination paper (GP) is used as a growth substrate in plant development studies. Current studies bear two limitations: (1) The actual GP water content and variations in GP water content are neglected. (2) Existing irrigation methods either maintain the GP water content at fully sufficient or at a constant deficit. Variation of the intensity of water deficit over time for plants grown on GP is not directly achievable using these methods. In this contribution, a new measurement and control approach was presented. As a first step, a more precise measurement of water content was realized by employing the discharging process of capacitors to determine the electrical resistance of GP, which is related to the water content. A Kalman filter using an evapotranspiration model in combination with experimental data was used to refine the measurements, serving as the input for a model predictive controller (MPC). The MPC was used to improve the dynamics of the irrigation amount to more precisely achieve the required water content for regulated water uptake in plant studies. This is important in studies involving deficit irrigation. The novel method described was capable of increasing the accuracy of GP water content control. As a first step, the measurement system achieved an improved accuracy of 0.22 g/g. The application of a MPC for water content control based on the improved measurement results in an overall control accuracy was 0.09 g/g. This method offers a new approach, allowing the use of GP for studies with varying water content. This addressed the limitations of existing plant growth studies and allowed the prospection of dependencies between dynamic water deficit and plant development using GP as a growth substrate for research studies. OA Förderung 2019

In this study, different standard frequency analysis (FA) methods are applied to measured leaf temperature data of maize plants (developmental stages EC13&ndash, 15). These FA methods are used to identify specific behaviors, regularities, and sudden changes in frequencies/amplitudes of data, e.g., in control engineering. The thorough application of different FA methods in plant studies is novel. The aim of this paper is to analyze features of the measured data and to explore the explanatory power of different methods for the detection of plant dynamic behavioral changes. The basic assumption is an expected relation between plant water stress and resulting changes in leaf temperature oscillations caused by stress-induced changes in stomatal behavior. Therefore, an irrigation experiment (laboratory, controlled environmental conditions) was implemented to compare leaf temperature behavior of stressed and unstressed plants. Leaf temperature time series are processed and the results are compared as functions of time showing the behavioral changes in terms of the different methods applied. The analysis of results is explained, conclusions, which can be made based on different methods, are given. The study confirms the applicability of FA methods and provides new insights into leaf temperature behavioral patterns. Results are discussed regarding the hypothesized incipience of leaf temperature oscillations due to water stress.

The reliability of complex or safety critical systems is of increasing importance in several application fields. In many cases, decisions evaluating situations or conditions are made. To ensure the high accuracy of these decisions, the assignments from different classifiers can be fused to one final decision to improve the decision performance in terms of given measures like accuracy or false alarm rate. Recent research results show that fusion methods not always outperform individual classifiers trained and optimized for a specific situation. Nevertheless fusion helps to ensure reliability and redundancy by combining the advantages of individual classifiers, even if some classifiers are not performing well for specific situations. Especially in unexpected (untrained) situations, fusion of more than one classifier allows to get a suitable decision, because of different behavior of classifiers in this case. Nevertheless, there are several examples, where fusion not always improves the overall accuracy of a decision. In this contribution fusion options are discussed to overcome the problem to overcome the aforementioned problem and to define influencing factors on overall fusion accuracy. As a results requirements for good or guaranteed or possibly increased fusion performance and also suggestions denoting those options not leading to any kind of improvement are given. For illustrating the effects a practical example based on three characteristics of fusion methods (type of classifier output, use of these outputs and necessity of training) and four data properties (number of classes, number of samples, entropy of classes and entropy of attributes) are considered and analyzed with 15 different benchmark data sets, which are classified with eight classification methods. The classification results are fused using seven fusion methods. From the discussion of the results it can be concluded, which fusion method performs best/worst for all data sets as well as which fusion method characteristic or data property has more or less positive/negative influence on the fusion performance in comparison to the best base classifier.Using this information, suitable fusion methods can be selected or data sets can be adapted to improve the reliability of decisions made in complex or safety critical systems. OA Förderung 2019

Driving behavior prediction at roundabouts is an important challenge to improve driving safety by supporting drivers with intelligent assistance systems. To predict the driving behavior effciently steering wheel status was proven to have robust predictability based on a Support Vector Machine algorithm. Previous research has not considered potential effects of roundabout layout and surrounding traffic on driving behavior, but that consideration can certainly improve the prediction results. Therefore, this study investigated how roundabout layout and surrounding traffic impact driving behavior of an ego car. A simulator study was conducted to collect driving behavior data with different roundabout layout settings and different surrounding cyclist position settings. The local minima/maxima of the steering angle was found to have a logarithmic relationship with the roundabout geometric feature. The impact of the surrounding traffic on the ego driver behavior was also found: When there were surrounding cyclists, the recognition rate of ego driver behavior patterns reached 100% later than when there was no surrounding traffic. In conclusion, driving behavior at roundabouts is effected by both roundabout layout and surrounding traffic, and the relationship can be expressed in a quantitative way.

Driving behavior prediction at roundabouts is an important challenge to improve driving safety by supporting drivers with intelligent assistance systems. To predict the driving behavior efficiently steering wheel status was proven to have robust predictability based on a Support Vector Machine algorithm. Previous research has not considered potential effects of surrounding traffic on driving behavior, but that consideration can certainly improve the prediction results. Therefore, this study investigated how different surrounding cyclists impact driving behavior of an ego car. A simulator study was conducted to collect driving behavior data of ego car drivers in the scenarios with different surrounding cyclist position settings. The impact of the surrounding cyclists on the ego driver behavior was found: When there were surrounding cyclists, the recognition rate of ego driver behavior patterns reached 100% later than when there was no surrounding traffic. In conclusion, driving behavior pattern recognition at roundabouts is impacted by surrounding cyclists, and the impact can be expressed in a quantitative way.

A method to integrate uncertainty in human performance models based on Coloured Petri Nets is proposed in this contribution. The method allows to predict human performance more realistically. As decisions often have to be made under uncertainty and existing models of human cognitive performance use if-then rules, the arising questions are about the combination of uncertainty with these rules. Uncertainty is present, if the environment is not exactly known or cannot be predicted precisely. As discrete uncertainty can be well integrated into Petri Nets, but continuous uncertainty is at least of equal importance, this contribution extends Coloured Petri Nets to represent continuous uncertainty as well which was not realized before. First, a probability distribution is selected and subsequently implemented in Coloured Petri Nets. Finally, the integration into an application example is shown. An experiment demonstrated that a planning model including prediction uncertainty is able to describe the performance of human operators during interaction scenarios more realistically.

Der Begriff Situationsbewusstsein hat aktuell in vielen Forschungsbereichen stark an Bedeutung gewonnen. Die Interaktion des Menschen mit der Umwelt in komplexen dynamischen Situationen und besonders in Hochrisikobereichen erfordert das Vorhandensein eines optimalen und fehlerfreien Situationsbewusstseins. Eine fehlerhafte Entscheidung und daraus resultierende Konsequenzen können zu hohen Kosten oder erheblichem Schaden führen; in gravierenden Fällen Menschenleben gef¨ahrden. Eine verlässliche Verhaltensweise/Interaktion in kognitiven Systemen mit damit verbundener Handlungsautonomie erfordert Fähigkeiten wie Planen, Vorhersehen, Handeln und somit das Vorhandensein eines optimalen Situationsbewusstseins. In diesem Beitrag werden die zu einer technischen Realisierung des Situationsbewusstseins notwendigen Anforderungen und Methoden vorgestellt. Im Falle einer korrekten technischen Umsetzung des Situationsbewusstseins sollte ein System in der Lage sein, Planungen und Handlungen hinsichtlich vorhandener Ziele zu realisieren sowie die Konsequenzen der Handlung bzw. Handlungsalternativen abzuschätzen. An Beispielen wird aufgezeigt in welcher Form dies bereits heute möglich ist.

This contribution is focused on the development of the interface between the human driver and hybrid vehicle. By analyzing the state of art regarding the functional design of the displays from existing hybrid vehicles, it can be observed that only the actual state and history of relevant variables like fuel consumption, state of charge, and distance to empty are displayed. This information is important for the human driver to analyze the realized previous behavior, but what exactly the driver should or could do in next minutes to improve the driving behavior during driving is usually not displayed. In order to improve upcoming behavior and related consequences and therefore to solve the task for further eciency improvement, a new interface has been developed to help the human driver to drive more eciently. By applying the new interface, the human driver can perceive the actual driving situation and predicted corresponding consequences. In comparison, the suggested optimal driving behavior and its consequences will be displayed as well. With the help of the new interface, the human driver can decide which behavior should be taken to improve the actual driving behavior.

Diagnostic and monitoring approaches, able to detect and classify the damage and wear process, are becoming of increasing importance. Especially for friction wear-related phenomena which are difficult to measure directly during the operation and their diagnostic has been usually restrained to offline examinations. Permanent contact and repetitive sliding motions between two surfaces lead to material changes. Due to different wear mechanisms, sudden structural changes appear, emitting energy in form of elastic waves known as Acoustic Emission (AE). Therefore, a correlation between the emitted AE and damage level can give important information about the process state and the related knowledge can be used for automated supervision. This contribution introduces an advanced method for wear states identification and classification by means of AE technique and fuzzy-based multi-class classification approach. Compared to the previous publications, here the sequential effect of the motion trajectory is investigated. To establish a relationship between wear mechanism and AE signals, frequency-based feature selection using Continuous Wavelet Transform (CWT) was performed. Five wear process stages were detected during experiments. Results show that the behavior of individual frequency components changes when the wear-related effect changes. Using the CWT transformed signals, statespecific pattern are generated to classify signal features related to specific states. Results show that the introduced method can be used as an online monitoring method for material detection and characterization.

In this contribution a recently developed new modeling and classification approach to be used with streamed measurement data of industrial processes is applied. This briefly repeated approach can be used for condition-based maintenance or structural health monitoring. The approach is based on a fuzzy-like modeling using statistical features from training data. Based on the trained model classification can be realized allowing to distinguish unknown data sets to the given number of data classes each related to states. Beside the detailed illustration of the approaches to be used, the results applying the automated classification using the AFFCA approach are shown. As data, complex and problem-specific Acoustic Emission (AE) signals and also signals taken from the operating level (called hydraulic pressure data) are used and compared. The results show that based on the AE-based and also on the hydraulic pressure based AFFCA system's health state classification, the changes of the system can be detected very early and detailed.

Reliability and availability of technical complex and safety-critical systems are of increasing importance. The degree of wear as well as the quality of mechatronic systems are significant for the system reliability. To classify the machines state using easy-to-measure signals, two issues are important: filtering and interpretation of the data [1]. Core of this contribution is the development and first application of a simple, easy to use, easy to apply, and easy to handle algorithm to be used directly with industrial data or measurements from technical systems during operation. In this contribution a hydraulically driven machine part sliding over another is used as example. A connection between measured hydraulic data to the degree of wear of the lubricated surface is established to calculate information about the state of a sliding surface. As experimental data the time behavior of hydraulic pressure data is taken and filtered for better evaluation. To the further generation of suitably defined characteristics, the data are edited and analyzed. The results based on four measurements with two different operating conditions show that the developed approach allows a detailed judgment of wear-oriented state of health as part of a new structural health monitoring system.

In existing production plants, sensor systems and other sources provide information about the plant condition. This paper presents methods for how data can be conveniently summarized, treated, and evaluated to retain characteristic features and allocate them to certain faults respectively to use them for monitoring purposes. This work details the development of a method to be applied to selected data sets, and which then can be expanded for use in the real environment. This paper details a procedure developed for automated selection and processing to reduce the time exposure of qualified personnel. A number of possible methods of analysis were tested for their ability to point out conspicuous events, especially Wavelet Transformation for feature extraction and Support Vector Machines for classification. Data sets that are correlated to the different conditions of the system are used for training and testing. After training, the algorithm will be able to detect different faults in time. In todayÕs practice, faults are analyzed after they have occurred. Applying the method, a major failure can be prevented by detecting contingency faults. Using real industrial data from the hot strip mill of ThyssenKrupp Steel Europe (TKSE), the developed approach will be tested offline for practical relevance.

Zur Kooperation von an verschiedenen Orten verteilten, gemeinsam arbeitenden, Nutzerinnen und Nutzern von Mensch-Maschine Systemen, sind geeignete technischinformatorische Module zu entwickeln. Die kooperative, online- und echtzeitfahige Regelung eines Drei-Tank-Systems, welche als Praktikumsversuch fur Studierende zum Einsatz kommt, soll minimalprototypisch die Gesamtfunktionalitat abbilden. Die Versuchsstandsdaten sollen an die bedienenden Personen in Echtzeit ubermittelt werden und so die Kommunikation mit den durchfuhrenden Studierenden ermoglichen. Hierzu mussen geeignete Werkzeuge entwickelt werden. Das Konzept sieht vor, das Drei-Tank System mit einem PC zu verbinden, welcher die Software NI LabVIEW nutzt. Der PC ist gleichzeitig mit dem Internet verbunden und es wird eine HTML-Seite als Interface zur Verfugung gestellt. Die Datenaus- und eingabe und Kommunikation, in Form einer Chat Funktion, werden entsprechend ermoglicht. Zusatzlich werden Warnungen und Hinweise im Sinne der Assistenz und Uberwachung integriert.

Neu entwickelte oder geanderte Mensch-Maschine-Systeme werden besonders beim Einsatz in sicherheitskritischen Bereichen vorab in Simulationen getestet. In diesen Simulationen sollen mogliche Ursachen fur fehlerhafte bzw. nichtoptimale Verhaltensweisen aufgedeckt werden, um diese aufbauend auf der analytischen Bewertung zu verbessern. Hierzu ist auch das Verhalten von Bedienerinnen und Bedienern zu bewerten. Die Bewertung einer Bedienhandlung setzt in der Regel aber die Kenntnis von real existierenden Alternativen bzw. der optimalen oder besten Verhaltensweise voraus. In vorangegangenen Arbeiten konnte gezeigt werden, dass Zustandsraummethoden zur Berechnung der Handlungsalternativen verwendet werden konnen. Aufgrund vorhandener Einschrankungen hinsichtlich der Vorgabe fester Handlungssequenzen, wird in diesem Beitrag ein Verfahren vorgeschlagen, mit dem die Alternativen situationsabhangig bestimmt werden und ist somit im Gegensatz zu fruheren Ansatzen nicht auf vorgegebene Handlungssequenzen beschrankt. Der zentrale Aspekt dieses Beitrags liegt auf der Verwendung eines Suchalgorithmus, der aufgabenspezisches Wissen verwendet, um die Handlungssequenz zu bestimmen. Diese wird zuerst nur fur Teilsysteme bestimmt und in einer ubergeordneten Suche wird dann die Reihenfolge der Betrachtung der Teilsysteme ermittelt. Der Algorithmus soll fur eine Flugfuhrungsaufgabe verwendet werden, fur die das erforderliche aufgabenspezische Wissen in Form von Regeln dargestellt wird.

In vielen Fällen müssen Bedienerinnen und Bediener komplexer dynamischer Systeme geeignete Maßnahmen planen, um zukünftige Systemzustände in gewünschter Weise beeinflussen zu können. Der menschliche Bediener kann dabei verschiedene Methoden anwenden, um mit Unsicherheiten umzugehen. Eine Übertragung dieser Methode auf technische Systeme könnte zu Assistenzsystemen führen, die besser mit Unsicherheit umgehen und besser mit dem Menschen kooperieren können. In diesem Beitrag wird für in der Literatur beschriebenen Eigenschaften mentaler Pläne eine Modellierung vorgeschlagen, die ein erster Schritt zu einem besseres Verständnis der mentalen Repräsentation von Plänen sein soll und somit auch bessere Assistenzsysteme ermöglichen soll. Insbesondere werden der Detaillierungsgrad der Pläne, der zu berücksichtigenden Planungshorizont, im Plan enthaltene Alternativen und der Zusammenhang der Elemente eines Plans, diskutiert und Modellierungsmöglichkeiten mit Hilfe der Situations-Operator-Modellbildung vorgeschlagen. Des Weitern werden die möglichen Einflüsse von Unsicherheiten und Arbeitsbelastung erörtert. Abschließend wird eine geplante Versuchskampagne zur Untersuchung der Planung vorgestellt, in der eine neu entwickelte Mikrowelt eingesetzt wird, deren Ansatz über bekannte ältere inhaltlich hinaus geht.

This contribution presents firstly the implementation of an automated cognitive-based supervision concept of a real vehicle. The concept employs a Situation-Operator-Modelling (SOM) approach as a representational level to model and formalize the logic of interaction between driver, vehicle and environment based on sensor and video data. The programmed implementation is realized by a Java-Application which can be connected with the ViewCar, the DLR experimental vehicle equipped with specialized sensors and cameras. As an output, the application dsiplays the interpreted situation and all allowed driver actions, which were tested with replay applications on the desktop and in flowing traffic in the ViewCar itself.