The proposed framework for Multi-Agent Target Tracking supports i) tracking of objects and ii) se... more The proposed framework for Multi-Agent Target Tracking supports i) tracking of objects and ii) search and rescue based on the fusion of very heterogeneous data. The system is based on a novel approach to fusing sensory observations, intelligence and context data (i.e. the data about the environmental conditions relevant for the tracked target). In contrast to the traditional approaches to target tracking (e.g. maritime or aviation domains), the emphasis is on tracking with low quality data sampled at low frequencies from different sensors dispersed throughout a larger area that may be only partially covered. In this demo we illustrate a live, real-time target tracking application that uses a Multi-Agent System approach to find and connect relevant information sources.
The proposed framework for Multi-Agent Target Tracking supports i) tracking of objects and ii) se... more The proposed framework for Multi-Agent Target Tracking supports i) tracking of objects and ii) search and rescue based on the fusion of very heterogeneous data. The system is based on a novel approach to fusing sensory observations, intelligence and context data (i.e. the data about the environmental conditions relevant for the tracked target). In contrast to the traditional approaches to target tracking (e.g. maritime or aviation domains), the emphasis is on tracking with low quality data sampled at low frequencies from different sensors dispersed throughout a larger area that may be only partially covered. In this demo we illustrate a live, real-time target tracking application that uses a Multi-Agent System approach to find and connect relevant information sources.
International Conference on Information Fusion, Jul 6, 2015
This paper introduces a novel approach to robust tracking that combines Particle Filters (PFs) an... more This paper introduces a novel approach to robust tracking that combines Particle Filters (PFs) and estimation of physical constraints using Bayesian Networks (BNs). Heterogeneous Context Data (CD) describing the environment in which tracked objects move, is fused with the help of BNs. The resulting uncertain constraints are incorporated into the filtering process through a modification of the importance weights. Causal probabilistic models representing relations between the tracked objects and their environment are used to derive an updating rule that allows theoretically sound incorporation of uncertain constraints into PF. The approach allows incorporation of new types of CD without requiring any adaptation of the PF algorithm itself. The experimental results confirm that the presented method significantly improves the tracking accuracy in a relevant class of problems characterized by partial sensor coverage and low updating frequencies.
Attractor-directed particle filtering with potential fields
International Conference on Information Fusion, Jul 5, 2016
In this paper we describe a particle filter algorithm that allows incorporation of prior knowledg... more In this paper we describe a particle filter algorithm that allows incorporation of prior knowledge about future states. Incorporation of such knowledge can significantly reduce the uncertainty in the estimation of future state predictions. Estimation of the state is based on a transition model where the current state is not only conditioned on the previous state but also on an attractive potential field, exercising an attractive force on the particles, causing them to travel a certain path towards an attractor point. With the help of dynamic Bayesian networks we can show that the attractor-directed particle filter algorithm is correct if the number of particles used for the estimation approaches infinity. Through an experiment we show how prior knowledge of future states can successfully be used to improve the estimation performance of the attractor-directed particle filter algorithm.
A distributed multi-agent system is used to support collaborative situation assessment and decisi... more A distributed multi-agent system is used to support collaborative situation assessment and decision making for effective management of chemical hazards crisis in industrial areas. The system of agents supports creation of complex information flows between large numbers of stakeholders. The disseminated information and the system states are logged, which supports the analysis of the collaborative crisis management processes as well as the performance of the multi-agent systems framework. An ontology is designed to model the logged process. The fragments of logs that are meaningful to the users are converted to topic maps using the designed ontology. These topic maps are then merged to provide a federated picture of the data. A graphical query mechanism for querying the topic maps has been developed. This query mechanism creates graphical representations of relevant excerpts of the merged topic map, allowing conducting a thorough analysis of the logs.
Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering
Presence monitoring or intrusion detection in a location/area are examples of decision-support ap... more Presence monitoring or intrusion detection in a location/area are examples of decision-support applications. Decision-support applications are applications where monitoring is used to collect (heterogeneous) data and create situational awareness, which further requires decisions and/or actions. As such, decision-support software consists of different interconnected components with very diverse roles, whose communication and synchronization are essential for the application functionality and performance. Despite this complexity, software design for decision-support is often driven by short-term functional requirements and only supported by designers' previous experience. In the current non-systematic approach, mistakes can be easily made, and can be very difficult to repair. In this work, we describe our systematic method for efficient and effective decision-support software design, based on application design-space exploration (DSE). To this end, we describe how to build a design space and present structured methods to traverse the design space towards software solutions that meet user requirements for both functionality and performance. CCS CONCEPTS • Software and its engineering → Software design engineering; Software design techniques; Requirements analysis; Design patterns; • Information systems → Decision support systems; Data analytics.
International audienceUncertainty management is a key aspect of any information fusion (IF) syste... more International audienceUncertainty management is a key aspect of any information fusion (IF) system. Evaluation of how uncertainty is dealt with within a given IF system is distinct from, although closely related to, evaluation of the overall performance of the system. This paper presents the Uncertainty Representation and Reasoning Evaluation Framework (URREF), which is developed by the ISIF Evaluation of Techniques for Uncertainty Representation Working Group (ETURWG) for evaluating the uncertainty management aspects of IF systems. The paper describes the scope of the framework, its core element-the URREF ontology, the elementary fusion process it considers, and how these are related to the subjects being evaluated using the framework. Although material about the URREF has been previously published elsewhere, this work is the first to provide a comprehensive overview of the framework, establishing its scope, core elements, elementary fusion process considered, and relationship betw...
Cloud-Based Intelligence Aquisition and Processing for Crisis Management
Contemporary crisis management has to deal with complex socio-technical environments involving ma... more Contemporary crisis management has to deal with complex socio-technical environments involving many interdependent elements. Many dependencies in such settings result in complex cascading processes that can have adverse effects on the population, environment, and economy. Adequate situation awareness and the capability to predict the development of a crisis situation under different circumstances is a critical element of effective, and timely, crisis management and response. However, this requires rich domain knowledge as complex interdependencies between different socio-technical elements must be understood. Furthermore, substantial domain knowledge is required for (1) determination of what data is relevant in a given situation, (2) the collection of that data, and (3) its analysis; i.e. all the information should be delivered to an expert that can understand that information. Note that domain knowledge is required to “drive” the information requests. Moreover, often multiple exper...
Distributed Perception Networks for Crisis Management; 2006BU1-TRSP
Situation assessment in crisis management applications can be supported by automated information ... more Situation assessment in crisis management applications can be supported by automated information fusion systems, such as Distributed Perception Networks. DPNs are self-organizing fusion systems that can infer hidden events through interpretation of huge amounts of heterogeneous and noisy observations. DPNs are a logical layer on top of existing communication, sensing, processing and data storage infrastructure. They can reliably and efficiently process information of various quality obtained from humans and sensors through the existing communication systems, such as mobile phone networks or internet. In addition, modularity of DPNs supports efficient design and maintenance of very complex fusion systems. In this paper, a fully functional prototype of a DPN system is presented that fuses information from gas sensors and human observations. The task of the system is to compute probability values for the hypothesis that a particular gas is present in the environment. It is discussed how such a system could be used for crisis management.
Towards Characterizing Distributed Complex Situation Assessment as Workflows in Loosely Coupled Systems
IDC, 2012
This paper introduces challenges in contemporary situation assessment using collaborative inferen... more This paper introduces challenges in contemporary situation assessment using collaborative inference and discusses solutions that are based on workflows between distributed processing nodes. The paper exposes the necessary conditions that workflows have to satisfy in order to support accurate situation assessment and provides a systematic approach to verification of the workflows. In particular, we emphasize the link between the complexity of the domain and the complexity of the workflows in terms of data and control coupling. With the help of graphical representations, we characterize the complexity of the domains and identify critical relations that have to be captured by collaborating processes in a workflow supporting correct situation assessment.
Towards robust state estimation with bayesian networks: A new perspective on belief propagation
IAS, 2006
We investigate properties of Bayesian networks (BNs) in the context of state estimation. We intro... more We investigate properties of Bayesian networks (BNs) in the context of state estimation. We introduce a coarse perspective on the inference processes and use this perspective to identify conditions under which state estimation with BNs can be very robust, even if the quality of the model is very low. By making plausible assumptions we can formulate asymptotic properties of the estimation performance with respect to the network topology. In addition, we introduce techniques that support detection of potentially inaccurate inference results.
2017 20th International Conference on Information Fusion (Fusion), 2017
The question addressed in this paper is “what” is to be evaluated by the Uncertainty Representati... more The question addressed in this paper is “what” is to be evaluated by the Uncertainty Representation and Reasoning Evaluation Framework (URREF) ontology. We thus identify the elements composing uncertainty representation and reasoning approaches, which constitute various subjects being assessed. We distinguish between primary evaluation subjects (Uncertainty Representation and Reasoning components of the fusion algorithm), and secondary evaluation subjects (source of information, piece of information, fusion method and mathematical model). This paper proposes a list of source quality criteria to be added to the ontology and establishes formal links between the secondary and primary evaluation subjects. The key contribution of the paper is the update of the definitions of sub-criteria of the Expressiveness criterion together with suggestions for complementary concepts to be included in the ontology (type of scale, type of uncertainty expression). Conclusions are drawn to extend the work in using the expressiveness criterion for information fusion analysis.
Context-Based Vessel Trajectory Forecasting: A Probabilistic Approach Combining Dynamic Bayesian Networks with an Auxiliary Position Determination Process
2020 IEEE 23rd International Conference on Information Fusion (FUSION), 2020
This paper introduces a probabilistic approach for forecasting vessel trajectories. It combines a... more This paper introduces a probabilistic approach for forecasting vessel trajectories. It combines a Dynamic Bayesian Network (DBN) and an auxiliary position determination process to iteratively sample future vessel positions in a scalable and computationally efficient manner. The DBN is a discrete probabilistic model of typical vessel behaviors. It is used for ancestral sampling to predict the speed and orientation of a vessel which, in turn, are used by the auxiliary process to predict the vessel's position in a discretized representation of the space. The DBN is event based and uses latent variables that efficiently encode the context influencing the dynamics of different types of vessels. The parameters of the DBN are learned in an unsupervised fashion by using the Expectation Maximization (EM) algorithm. The experiments with real world data confirm the accuracy and effectiveness of the proposed approach.
Uploads
Papers by Gregor Pavlin