Logo Universität Bremen


Universität Bremen - Faculty 3 - Computer Science


Home «Service «List of members Detail

Photo: Bosse, Stefan
Priv.-Doz. Dr. rer. nat  Stefan  Bosse  (Vertretungsprofessor)
Research group/institution:
Link to external site  Robotic  (ROBO)

Room:DFKI/RH5 2.25
Phone [business]: +49 (421) 218 - 0
Fax number: +49 (421) 218 - 64150
Phone number (external):+49 (421) 17845-4103
E-Mail :email

Link to external site Official Homepage
Link to external site Personal Homepage
Link to external site Publications



Research experience and project leadership in the fields:

  • Distributed AI
  • Multi-agent Systems and their technological deployment
  • Self-organizing and self-adaptive Systems
  • Agent Platforms
  • Machine Learning
  • Distributed and Parallel Systems
  • Simulation of and with Multi-agent Systems
  • Development and design of Sensorial adn Self-adaptive Materials; Material Science
  • Sensor Networks with embedded systems
  • Design of parallel and distributed embedded systems
  • Digital circuit design with high-level synthesis approaches
  • Sensor signal processing
  • Virtual Machines
  • Compiler Design


Lectures in bachelor and master courses teaching basic and higher-level knowledge of computer science, circuit design, and distributed and parallel systems, multi-agent systems and distributed AI.

  • University of Bremen: Parallel and distributed embedded systems, Design of embedded systems, Multi-agent Systems
  • University of Koblenz: Introduction to Functional Programming, Distributed and parallel Programming, Multi-agent Systems

Conferences and Journals

  • Organization of international conferences, i.e., SysInt 2014 Conference held in Bremen, ECSA-2, Basel (November 2015)
  • Guest Editor in several international journals, i.e., IEEE Sensors, Elsevier Mechattronics

Design of Programming Langauges

  • ConPro: Concurrent Programming, Parallel programming language for digital hardware designs and SoC using high-level synthesis
  • SEM: SeSAm Simulation Language, Textual representation of behaviorual models for multi-agent systems and the SeSAm simulator
  • AAPL: Activity-based Agent Programming Language, generic programming language for modelling of mobile state-based multi-agent systems, which are deplyoed in heterogeneous networks
  • AFL: Agent FORTH, a stack-based FORTH programming language with agent behaviour related to the ATG model, migration, and tuple space interaction
  • AgentJS: Agent JavaScript, based on AAPL, programming language for the JAM agent platform
  • VPL: Virtual Database Programming Language, Interface programming language for the virtual graph database VDB that is deployed in the Synthesis Toolkit SynDK used for the construction of complex compiler and synthesis frameworks.
  • JavaScript Semantic Type System (JST/JS+)


Stefan Bosse studied physics at the University of Bremen. He received a Doctoral Degree (Dr. rer. nat.) in physics in the year 2002 at the University of Bremen, and the post-doctoral degree (Habilitation) and the Venia Legendi in Computer Science in the year 2016 at the University of Bremen.

Since 2018 he is a visiting professor at the University of Koblenz, Faculty of Computer Science.

In the year 2004 he joined the Department of Mathematics & Computer Science and the working group robotics. He works as a senior researcher and lecturer. Since 2002 his scientific work focuses on parallel and distributed systems, data processing in large-scale sensor networks with multi-agent systems, material-integrated sensing systems, digital circuit design, compiler construction, and general artificial intelligence.

He teaches several courses at the University of Bremen in fundamental computer science and in selected advanced topics covering the design of digital logic data processing systems on RTL, massive parallel and multi-agent system design, high-level synthesis, and material-integrated sensing systems with a high interdisciplinary background.

Since 2008 he conducts projects in the ISIS Sensorial Materials Scientific Centre pushing interdisciplinary research filling the gap between technology and computer sciences, and recently joining the ISIS council.

He acts as a reviewer and a guest editor for several international journals, i.e., ACM TODAES (rev.), IEEE Sensors (G.Ed.), ELSEVIER Mechatronics (G.Ed.), and is a member of international conference programme and organizing committees, i.e., SYSINT.

Pers. Additional information


The 3rd International Workshop on Data-driven Self-regulating Systems (DSS 2017)
In conjunction with 11th IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO)
(Proceedings appear in IEEE Digital Library)
September 18-22, 2017 in University of Arizona, Tucson, AZ, CFP link: http://dss2017.inn.ac/
Workshop Organizers: Evangelos Pournaras, ETH Zurich, Switzerland
Akshay Uttama Nambi S.N., Microsoft Research Lab, India
Stefan Bosse, University of Bremen, Germany
Habilitation Fachvortrag
Titel: Vom Internet der Dinge hin zu sensorischen Clouds - Verteilte Datenverarbeitung in heterogenen Netzen mit mobile Agenten
Title: From the Internet-of-Things to Sensor Clouds - Unified Distributed Computing in Heterogeneous Environments with Mobile Agents
Abstract: The growing complexity of computer networks and their heterogeneous composition with devices ranging from servers with high computational power and high-resource requirements down to low-resource mobile and embedded devices with low computational power demands unified and scalable new data processing paradigms and methodologies. The Internet-of-Things (IoT) is one major example and use-case rising in the past decade, strongly correlated with Cloud Computing and Big Data concepts, and extending the Internet Cloud domain with distributed autonomous sensor networks consisting of miniaturized low-power smart sensors. These smart sensors, for example, embedded in technical structures, are pushed by new trends emerging in engineering and micro-system applications. Smart and distributed sensing systems are one of the technological cornerstones of the Internet-of-Things, wearable electronic devices, future transportation, environmental monitoring and smart cities. Mobile Multi-Agent systems represent a well known parallel and distributed computing paradigm, and can be closely related to the communicating mobile process paradigm. Mobile Agents are well suited for reliable distributed and parallel data processing in such heterogeneous networks. This approach enables the development of sensor clouds of the future integrated in daily use computing environments and the Internet. Agents can migrate between different hardware and software platforms by migrating the program code of the agent, embedding the state and the data of an agent, too. Agent mobility crossing different execution platforms, agent interaction by using tuple-space databases, and agent code reconfiguration enable the design of reliable distributed sensor processing networks.
Zeit / Veranstaltungsort: Mi. 03.08. 16:00, Ort: CART Rotunde - 0.67
3rd International Electronic Conference on Sensors and Applications, 15-30 November, 2016, Basel
Section S2: Smart Systems and Structures, Section Chair: Stefan Bosse
Call For Papers! [Sciforum ECSA-3 CFP]


Recent Publications


S. Bosse, Incremental Distributed Learning with JavaScript Agents for Earthquake and Disaster Monitoring, International Journal of Distributed Systems and Technologies (IJDST), (2017), accepted, under publication
Abstract: Ubiquitous computing and The Internet-of-Things (IoT) emerge rapidly in today’s life and evolve to Self-organizing systems (SoS). A unified and scalable information processing and communication methodology is required. In this work mobile agents are used to merge the IoT with Mobile and Cloud environments seamlessly. A portable and scalable Agent Processing Platform (APP) provides an enabling technology that is central for the deployment of Multi-agent Systems (MAS) in strongly heterogeneous networks including the Internet. A large-scale use-case deploying Multi-agent systems in a distributed heterogeneous seismic sensor and geodetic network is used to demonstrate the suitability of the MAS and platform approach. The MAS is used for earthquake monitoring based on a new incremental distributed learning algorithm applied to regions of sensor data from stations of a seismic network with global ensemble voting. This network environment can be extended by ubiquitous sensing devices like smart phones. Different (mobile) agents perform sensor sensing, aggregation, local learning and prediction, global voting and decision making, and the application. The incremental distributed learning algorithm outperforms a prior developed non-incremental algorithm (Distributed Interval Decision Tree learner) and can be efficiently used in low-resource platform networks.

D. Lehmhus, S. Bosse, M. Busse, Autonomous Property Change in Adaptive Composites: A Simulation-based study on Multi-Agent-Systems Approaches, DGM Verbundwerkstoffe Congress, 21. Symposium, 5. - 7. July 2017, Bremen, Germany
Abstract: Load-bearing structures are typically designed towards relevant load cases assuming static shape and fixed sets of materials properties decided upon during design and materials selection. Structures that could change local properties in service in response to load change could raise additional weight saving potentials , thus supporting lightweight design and sustainability. Materials with such capabilities must necessarily be composite in the sense of a heterogeneous build-up, exhibiting e. g. an architecture consisting of numerous active cells with sensing, signal and data processing and actuation/stimulation capability. One concern regarding active smart cellular structures is correlated control of cells’ responses, and the underlying informational organization providing robustness and real-time capabilities. We suggest a two-stage approach which combines machine learning with mobile and reactive Multi-agent Systems (MAS). In it, the MAS’ task is to analyse loading situations based on sensor data and negotiate matching spatial redistributions of material properties like elastic modulus to achieve higher-level optimization aims like a minimum of the total strain energy within the structure, or a reduction of peak stress levels. The associated machine learning approach would be employed to recognise loading situations already encountered in the past for which optimized solutions exist and in such cases bypass the MAS system to directly enforce the respective property distribution. In the present study, a proof of concept of the approach is presented which combines finite element method (FEM) and MAS simulation, with the former primarily taking the place of the physical structure. In addition, FEM simulations are used for off-line training of the MAS prior to its deployment in the real or simulated structure. The classification models learned this way represent a starting point which is constantly being updated at run-time during the service life of the structure using incremental learning techniques.


Stefan Bosse, Armin Lechleiter, A hybrid approach for Structural Monitoring with self-organizing multi-agent systems and inverse numerical methods in material-embedded sensor networks, Mechatronics, (2016), DOI:10.1016/j.mechatronics.2015.08.005.
Abstract: One of the major challenges in Structural Monitoring of mechanical structures is the derivation of meaningful information from sensor data. This work investigates a hybrid data processing approach for material-integrated Structural Health and Load Monitoring systems by using self-organizing mobile multi-agent systems (MAS), and inverse numerical methods providing the spatial resolved load information from a set of sensors embedded in the technical structure with low-resource agent processing platforms scalable to microchip level, enabling material-integrated real-time sensor systems. The MAS is deployed in a heterogeneous environment and offers event-based sensor preprocessing, distribution, and pre- computation. Inverse numerical approaches usually require a large amount of computational power and storage resources, not suitable for resource constrained sensor node implementations. Instead, the computation is partitioned into spatial off-line (outside the network) and on-line parts, with on-line sensor processing performed by the agent system. A unified multi-domain simulation framework is used to profile and validate the proposed approach.

Stefan Bosse, Industrial Agents and Distributed Agent-based Learning, 3rd International Electronic Conference on Sensors and Applications . 15-30 Nov. 2016, MDPI, 2016, DOI:10.3390/ecsa-3-S2004.
Abstract: Today sensor data processing and information mining become more and more complex concerning the amount of sensor data to be processed, the data dimension, the data quality, and the relationship between derived information and input data. This is the case especially in large-scale sensing and measuring processes embedded in Cloud environments. Measuring uncertainties, calibration errors, and unreliability of sensors have a significant impact on the derivation quality of suitable information. In the technical and industrial context the raising complexity and distribution of data processing is a special issue. Commonly, information is derived from raw input data by using some kind of mathematical model and functions, but often being incomplete or unknown. If reasoning of statements is primarily desired, Machine Learning can be an alternative. Traditionally, sensor data is acquired and delivered to and processed by a central processing unit. In this paper, the deployment of distributed Machine Learning using mobile Agents forming self-organizing and self-adaptive systems (self-X) is discussed and posing the benefit for the enhancement of the sensor and data processing in technical and industrial systems. This also addresses the quality of the computed statements, e.g., an accurate prediction of run-time parameters like mechanical loads or health conditions, the efficiency, and the reliability in the presence of partial system failures.

Dirk Lehmhus, Stefan Bosse, Self-adaptive Smart Materials: A new Agent-based Approach, 3rd International Electronic Conference on Sensors and Applications . 15-30 Nov. 2016, MDPI, 2016, DOI:10.3390/ecsa-3-S2005.
Abstract: Load-bearing engineering structures typically have a static shape fixed during design based on expected usage and associated load cases. But neither can all possible loading situations be foreseen, nor could this large set of conditions be reflected in a practical design methodology— and even if either was possible, the result could only be the best compromise and thus deviate significantly from the optimum solution for any specific load case. In contrast, a structure that could change its local properties in service based on the identified loading situation could potentially raise additional weight saving potentials and thus support lightweight design, and in consequence, sustainability. Materials of this kind would necessarily exhibit a cellular architecture consisting of active cells with sensing and actuation capabilities. Suitable control mechanisms both in terms of algorithms and hardware units would form an integral part of these. A major issue in this context is correlated control of actuators and informational organization meeting real-time and and robustness requirements. In this respect, the present study discusses a two-stage approach combining mobile & reactive Multi-agent Systems (MAS) and Machine Learning. While MAS will negotiate property redistribution, machine learning shall recognise known load cases and suggest matching property fields directly.

Stefan Bosse, Distributed Machine Learning with Self-organizing Mobile Agents for Earthquake Monitoring, IEEE 1st International Workshops on Foundations and Applications of Self Systems (FASW), SASO Conference, DSS Workshop, 12 September 2016, Augsburg, Germany, 2016, 2016, DOI:10.1109/FAS-W.2016.38.
Abstract: Ubiquitous computing and The Internet-of-Things (IoT) raises rapidly in today's life and is becoming part of self-organizing systems (SoS). A unified and scalable information processing and communication methodology using mobile agents is presented to merge the IoT with Mobile and Cloud environments seamless. A portable and scalable Agent Processing Platform (APP) is an enabling technology that is central for the deployment of Multi-agent Systems (MAS) in strong heterogeneous networks including the Internet. A large-scale distributed heterogeneous seismic sensor and geodetic network used for earthquake analysis is one example, which can be extended by ubiquitous sensing devices like smart phones. To simplify the development and deployment of MAS in the Internet domain agents are directly implemented in JavaScript (JS). The proposed JS Agent Machine (JAM) is an enabling technology. It is capable to execute AgentJS agents in a sandbox environment with full run-time protection, low-resource requirements, and Machine Learning as a service. A simulation of a seismic network and real earthquake data demonstrates the deployment of the JAM platform. Different (mobile) agents perform sensor sensing, aggregation, local learning and prediction, global voting, and the application.

Stefan Bosse, Mobile Multi-Agent Systems for the Internet-of-Things and Clouds using the JavaScript Agent Machine Platform and Machine Learning as a Service, The IEEE 4th International Conference on Future Internet of Things and Cloud , 22-24 August 2016, Vienna, Austria, 2016, 2016, DOI:10.1109/FiCloud.2016.43.
Abstract: The Internet-of-Things (IoT) gets real in today's life and is becoming part of pervasive and ubiquitous computing networks offering distributed and transparent services. A unified and common data processing and communication methodology is required to merge the IoT, sensor networks, and Cloud-based environments seamless, which can be fulfilled by the mobile agent-based computing paradigm, discussed in this work. Currently, portability, resource constraints, security, and scalability of Agent Processing Platforms (APP) are essential issues for the deployment of Multi-agent Systems (MAS) in strong heterogeneous networks including the Internet, addressed in this work. To simplify the development and deployment of MAS it would be desirable to implement agents directly in JavaScript, which is a well known and public widespread used programming language, and JS VMs are available on all host platforms including WEB browsers. The novel proposed JS Agent Machine (JAM) is capable to execute AgentJS agents in a sandbox environment with full run-time protection and Machine learning as a service. Agents can migrate between different JAM nodes seamless preserving their data and control state by using a on-the-fly code-to-text transformation in an extended JSON+ format. A Distributed Organization System (DOS) layer provides JAM node connectivity and security in the Internet, completed by a Directory-Name Service offering an organizational graph structure. Agent authorization and platform security is ensured with capability-based access and different agent privilege levels.

Stefan Bosse, Structural Monitoring with Distributed-Regional and Event-based NN-Decision Tree Learning using Mobile Multi-Agent Systems and common JavaScript platforms, Procedia Technology, 3rd International Conference on System-Integrated Intelligence: New Challenges for Product and Production Engineering, June 13th (Mon.) - 15th (Wed.) 2016: Paderborn, Germany, 2016, DOI:10.1016/j.protcy.2016.08.063.
Abstract: Among the Internet-of-Things, one major field of application deploying agent-based sensor and information processing is Structural Load and Structural Health Monitoring (SLM/SHM) of mechanical structures. This work investigates a data processing approach for material-integrated and mobile ubiquitous SHM and SLM systems by using self-organizing mobile multi-agent systems (MAS), executed on a highly portable JavaScript-based Agent Processing Platform (APP), and optimized Machine Learning (ML) methods providing load class recognition from a set of sensors embedded in the technical structure. Machine learning approaches usually require a large amount of computational power and storage resources and ML is commonly performed off-line, not suitable for resource constrained sensor network implementations. Instead, a novel distributed-regional on-line learning is applied, with on-line distributed sensor processing and learning performed by the agent system. The APP provides ML as a service, and the agent itself only collects training and analysis data passed to the APP, finally returning a learned model that is saved by the agent in a compact format (and is available on any other location). A case study shows that the learning algorithm is suitable (stable) for noisy and time varying sensor data. Spatial global learning is reduced and mapped on local region learning with global voting.

Stefan Bosse, Armin Lechleiter, Dirk Lehmhus, Data evaluation in smart sensor networks using inverse methods and artificial intelligence (AI): Towards real-time capability and enhanced flexibility, Proc. of the CIMTEC, - 7th Forum on New Materials, Perugia, Italy, June 5 to 9, 2016, 5th International Conference “Smart and Multifunctional Materials, Structures and Systems, 2016, 2016, DOI:10.4028/www.scientific.net/AST.101.55.
Abstract: Data evaluation is crucial for gaining information from sensor networks. Main challenges include processing speed and adaptivity to system change, both prerequisites for SHM-based weight reduction via relaxed safety factors. Our study looks at soft real time solutions providing feedback within defined but flexible, application-controlled intervals. These can rely on minimizing computation/communication latencies e.g. by parallel computation. Strategies towards this aim can be model-based, including inverse FEM, or model-free, including machine learning, which in practice bases training on a defined system state, too, hence also facing challenges at state changes. We thus introduce hybrid data evaluation combining multi-agent based systems (MAS) with inverse FEM, mainly relying on matrix operations that can be partially distributed: The MAS perform sensor data acquisition, aggregation, pre-computation, and finally application (the LM/SHM itself and higher information processing and visualization layers, i.e., WEB interfaces). System capabilities are evaluated against a virtual test case, demonstrating enhanced stability and reliability. Besides, we analyze system performance under conditions of in-service change and discuss system layouts suited to improve coverage of this issue.


Last change by sbosse am 11.06.2018