Refine
Labor/Institute
Keywords
- Artificial Intelligence (17)
- ITS (Intelligent Transportation Systems) (17)
- Fahrerassistenzsystem (15)
- Künstliche Intelligenz (8)
- Prozesssteuerung (6)
- Autonomes Fahrzeug (5)
- Bayesian Networks (4)
- OOBN (4)
- Hirntumor (3)
- Papierindustrie (3)
Year of publication
Document Type
- Conference Proceeding (19)
- Article (13)
- Part of a Book (3)
Reviewed
- ja (1)
The new generation of autonomous vehicles (AVs) are being designed to act autonomously and collect travel data based on various smart devices and sensors. The goal is to enable AVs to operate under their own power. Naturalistic driving studies (NDSs) collect data continuously from real traffic activities, in order not to miss any safety-critical event. In NDSs of AVs, however, the data they collect is influenced by various sources that degrade their forecasting accuracy. A convolutional neural network (CNN) is proposed to process a large amount of traffic data in different formats. A CNN can detect anomalies in traffic data that negatively affect traffic efficiency and identify the source of data anomalies, which can help reduce traffic congestion and vehicular queuing.
We propose a system design for preventive traffic safety in general intersection situations involving all present traffic participants (vehicles and vulnerable road users) in the context of their environment and traffic rules. It exploits the developed overall probabilistic framework for modeling and analysis of intersection situations under uncertainties in the scene, in measured data or in communicated information. It proposes OOBN modeling for the cognitive assessment of potential and real danger in intersection situations and presents schematically an algorithm for multistage cognitive situation assessment. A concept for the interaction between situation assessment and the proposed Proactive coaching Safety Assistance System (PaSAS) is outlined. The assessment of danger in a situation development serves as a filter for the output and intensity of HMI-signals for directing driver's attention to essentials.
In diesem Artikel wird ein Ansatz zur Erkennung von Spurwechselmanövern mit Hilfe von objekt-orientierten Bayes Netzen beschrieben. Dieser Ansatz ist eine Erweiterung von Grundlagenarbeiten zur Einscherererkennung. Zunächst werden die zur Erkennung von Spurwechselvorgängen erforderlichen Fahrsituationsmerkmale vorgestellt. Darauf aufbauend wird das entwickelte objekt-orientierte Bayes Netz zur Modellierung der Spurwechsel erläutert. Dabei wird ein Spurwechsel als eine Beziehung zwischen zwei Fahrzeugen betrachtet. Dabei kann ein Fahrzeug in der Spur bleiben, die Spur nach links oder nach rechts wechseln. Durch die Kombination der Möglichkeiten der beiden Fahrzeuge entstehen 9 Klassen. Aus den relativen Positionen der Fahrzeuge ergeben sich aus den 9 Situationsklassen 27 mögliche Spurwechselmanöver. Dabei ist das Einschervorgang ein Sonderfall der modellierten Fahrmanöver.
We present an application, where extensions of existing methods for decision-theoretic troubleshooting are used for industrial process operation and asset management. The extension includes expected average cost of asset management actions, prediction of signals' level-trend development, risk assessment for disturbance analysis and predictive maintenance on demand.
The increasing complexity of large-scale industrial processes and the struggle for cost reduction and higher profitability means automated systems for processes diagnosis in plant operation and maintenance are required. We have developed a methodology to address this issue and have designed a prototype system on which this methodology has been applied. The methodology integrates decision-theoretic troubleshooting with risk assessment for industrial process control. It is applied to a pulp digesting and screening process. The process is modeled using generic object-oriented Bayesian networks (OOBNs). The system performs reasoning under uncertainty and presents to users corrective actions, with explanations of the root causes. The system records users’ actions with associated cases and the BN models are prepared to perform sequential learning to increase its performance in diagnostics and advice.
Die entwickelte Methodik für die Fehlerursachenanalyse (RCA) stellt ein Instrument zur Entscheidungsunterstützung dar, das den Prozesszustand auf der Grundlage qualitativer und quantitativer Informationen bewertet. Das vorgestellte RCA-System nutzt die verfügbaren Daten, um die wahrscheinlichsten Grundursachen zu ermitteln und schlägt eine Handlungssequenz vor. Die Lernfähigkeit des Systems ermöglicht seine sequentielle Online-Anpassung, um Änderungen im Prozessbetrieb zu berücksichtigen.
Applications of object-oriented Bayesian networks for causal analysis of process disturbances
(2003)
We discuss a hybrid approach for causal analysis of disturbances in industrial process operation. It represents a combination of OOBN with first level diagnostic packages and physical models serving as agents in the system design and providing evidence for automated reasoning on abnormality in process operation. The aim is causal analysis of non-measurable disturbances as a decision advice complement to the distributed control system (DCS). The approach includes prediction of signals' level-trend development, risk assessment for disturbance analysis and predictive maintenance on demand. The methodology has been applied on a screening process with a pressure-flow network in a Pulp Mil.
ADAPTIVE RISK ASSESSMENT IN COMPLEX LARGE SCALE PROCESSES WITH REDUCED COMPUTATIONAL COMPLEXITY
(2004)
We have developed a methodology that targets risk assessment for process operation. It includes both abnormality prediction and evaluation of its development, provided no corrective actions are taken, as well as a possibility to examine the impact of intended actions. It handles the uncertainties in the domain and the big number of influences on the effect variables by utilizing causal probabilistic modeling. The process is modeled by Hidden Markov Models (HMM), and object oriented dynamic Bayesian networks (OOBNs). Various modeling techniques and assumptions have been used to reduce the computational complexity and ensure fast inference. The methodology is applied in a case study.
Cooperative perception makes it possible – in addition to emergency warnings – to provide drivers with early advisory warnings about potentially dangerous driving situations. Based on research results pertaining to imminent crash warnings, it was expected that the effectiveness of such advisory warnings depends on situation-specific anticipations by the driver. During a simulator study, N = 20 drivers went through a wide range of longitudinal traffic and intersection scenarios. The scenarios varied in the possibility to anticipate traffic conflicts (Anticipation: high vs. low) and were completed under different visibility conditions (Visibility: obstructed vs. visible), with and without driver assistance based on cooperative perception (i.e., visual-auditory advisory warnings two seconds prior to the last-possible warning moment; assistance: no assistance vs. with assistance). The warning concept was based on empirical pre-studies and previously validated on a public test intersection. During non-assisted driving, critical situations were mainly experienced when the possibility to anticipate traffic conflicts was low. Visual obstructions lead to a further increase in the frequency of critical situations. Furthermore, the results indicate a clear mitigation of critical encounters when providing early advisory warnings which is independent from sight obstructions. This applies particularly to surprising and unexpected scenarios and thus illustrates the potential of cooperative perception to enhance active traffic safety.