Arne Schuldt

Multiagent Coordination Enabling Autonomous Logistics

This dissertation develops coordination mechanisms for the implementation of autonomous control in logistics with multiagent technology. Therewith, it tackles the challenges of supply network management caused by the complexity, the dynamics, and the distribution of logistics processes. The paradigm of autonomous logistics reduces the computational complexity and copes with the dynamics locally by delegating process control to the participating objects (such as shipping containers). The dissertation specifies and implements the cooperative problem-solving process for autonomous logistics. The presented solution has been used in a realistic simulation of real-world container logistics processes. The validation shows that autonomous control is feasible and that it outperforms the previous centralised dispatching approach by significantly increasing the resource utilisation efficiency.

Designing a Simulation Middleware for FIPA Multiagent Systems

Multiagent systems ease the implementation of software systems to control complex processes. Instead of monolithic programs, decision-making is delegated to software agents as local entities. Like in software development in general, testing and evaluation play an important role also for multiagent systems. Particularly, because run-time interactions between agents and their effects cannot always be predicted at design time. Multiagent-based simulation is an adequate means to evaluate agents regarding their applicability in real-world operation. However, general agent development frameworks do not consider simulation-specific issues. Because they provide no means for synchronisation, an additional simulation middleware is required. Temporal criteria that are relevant for middleware design are defined in this paper. Furthermore, the actual implementation and example applications in logistics are presented.

Distributed Clustering of Autonomous Shipping Containers by Concept, Location, and Time

Recent developments in logistics show an increasing trend towards autonomous control. Intelligent software agents, that represent logistic objects like shipping containers, plan and schedule their way through a logistic network. This paper addresses the aspect of cooperation. A special focus lies on the second step of the model for cooperation, namely team formation. The question is by which criteria shipping containers, or logistic objects and agents in general, can form clusters. Starting from the particular demands of the logistics domain this paper argues in favour of conceptual, spatial, and temporal properties. A framework that takes concept, location, and time into account is introduced and demonstrated by an example application.

Towards the visualisation of shape features: the scope histogram

Classifying objects in computer vision, we are faced with a great many features one can use. This paper argues that diagrammatic representations help to comprehend properties of features. This is important for the purpose of deciding which features should be used for a given classification task. We introduce such a diagrammatic representation for a shape feature and show how it enables one to decide whether this feature helps to distinguish some categories given. Additionally, it shows that the proposed feature keeps up with other features falling into the same complexity class.

The Interaction Effort in Autonomous Logistics Processes: Potential and Limitations for Cooperation

Autonomous control in logistics decreases the computational effort for process control by problem decomposition. To this end, decision-making is delegated to the participating logistics entities. The more process control is decentralised the more interaction effort arises for coordinating the participants for efficient resource utilisation. This increase in interaction effort might even outweigh the decrease in computational effort gained by decomposition. Therefore, it is necessary to reduce the interaction effort by adequate organisational structures. Team formation as a prerequisite for establishing these structures, however, also requires interaction effort. Hence, this chapter analytically narrows the optimal degree at which autonomous control is applied by the interaction effort arising for individual and team action as well as team formation.

A compact shape representation for linear geographical objects: the scope histogram

In the GIS domain we are often faced with a great amount of shape-related data. Therefore, it is a challenging task to find concise description approaches which support the efficient retrieval of specific objects. In order to address this demand we apply a method that has recently been introduced in the context of shape-based image retrieval of two-dimensional silhouettes, namely the scope histogram. Scope histograms pertain to the group of qualitative shape descriptions as they characterise a shape by the general configuration of its parts. In particular, scope histograms allow the comparison of two shapes with constant time complexity. Despite of its low complexity, the approach achieves promising retrieval results. However, up to now the definition of scope histograms is limited to closed polygons.In this paper we investigate the application of scope histograms to the GIS domain. Since the contour of silhouettes is always closed, a restriction to closed polygons is no limitation in that domain. By contrast, it frequently is when dealing with GIS data. In this domain, we are rather often faced with open polygons; think for example of courses of rivers, borders, and coastlines. Therefore, we modify the original definition of scope histograms in order to be able to handle arbitrary polygons. Although our new definition leads to a more compact description than the original one, retrieval results are even improved by this modification.

Decentralisation and Interaction Efficiency in Cooperating Autonomous Logistics Processes

The efficiency of conventional centralised control in logistics is limited due to the complexity, the dynamics, and the distribution of logistics processes. The paradigm of autonomous logistics aims at overcoming these limitations by delegating decision-making to local logistics entities such as packages or containers. Represented by software agents, these entities must cooperate with each other to succeed in their logistics objectives. This paper introduces two interaction protocols for team formation of logistics entities. Which of them is adequate depends on the concrete application at hand. This decision is closely related with the limitations of autonomous logistics. One protocol aims at decreasing the communication effort, i.e., increasing the interaction efficiency. The other one aims at increasing the degree of decentralisation. This paper contributes a thorough investigation that supports system developers in choosing the right protocol for their demands.

Towards Autonomous Logistics: Conceptual, Spatial and Temporal Criteria for Container Cooperation

Shipping containers handle most of today’s intercontinental transport of packaged goods.Managing them in terms of planning and scheduling is a challenging task due to the complexity and dynamics of the involved processes. Hence, recent developments show an increasing trend towards autonomous control with software agents acting on behalf of the logistic objects. Despite of the high degree of autonomy it is still necessary to cooperate in order to achieve certain goals. This paper argues in favour of conceptual, spatial, and temporal properties on which shipping containers can form groups in order to jointly achieve certain goals. A distributed clustering method based on concept, location, and time is introduced. Subsequently, a case study demonstrates its applicability to a problem in the shipping container domain.

Extent, Extremum, and Curvature: Qualitative Numeric Features for Efficient Shape Retrieval

In content-based image retrieval we are faced with continuously growing image databases that require efficient and effective search strategies. In this context, shapes play a particularly important role, especially as soon as not only the overall appearance of images is of interest, but if actually their content is to be analysed, or even to be recognised. In this paper we argue in favour of numeric features which characterise shapes by single numeric values. Therewith, they allow compact representations and efficient comparison algorithms. That is, pairs of shapes can be compared with constant time complexity. We introduce three numeric features which are based on a qualitative relational system. The evaluation with an established benchmark data set shows that the new features keep up with other features pertaining to the same complexity class. Furthermore, the new features are well-suited in order to supplement existent methods.

Glyph extraction from historic document images

This paper is about the reproduction of ancient texts with vectorised fonts. While for OCR only recognition rates count, a reproduction process does not necessarily require the recognition of characters. Our system aims at extracting all characters from printed historic documents without the employment of knowledge of language, font, or writing system. It searches for the best prototypes and creates a document-specific font from these glyphs. To reach this goal, many common OCR preprocessing steps are no longer adequate. We describe the necessary changes of our system that deals particularly with documents typeset in Fraktur. On the one hand, algorithms are described that extract glyphs accurately for the purpose of precise reproduction. On the other hand, classification results of extracted Fraktur glyphs are presented for different shape descriptors.