Current projects

HERCULES

(Horizon 2020)

HERCULES is our take on prestigious Horizon 2020 call. It aims to provide an industrial-level implementation of state-of-the-art real-time scheduling techniques, applying them to cutting-edge hardware platforms based on heterogeneous multi-core architecture. New applications are being proposed integrating more and more functionalities in the objects commonly used for our daily activities, imposing a number of additional requirements to embedded systems designers. Project HERCULES will provide the required infrastructure to obtain an order-of-magnitude improvement in the cost and power consumption of next generation real-time applications. It will develop an integrated framework to allow achieving predictable performance on top of cutting-edge heterogeneous commercial-of-the-shelf multi-core platforms, implementing real-time scheduling techniques and execution models recently proposed. The framework will be applied to e.g. to the innovative industrial use case: a pioneering autonomous driving system for the automotive domain.

FLOPPThe factory of the future 

(FLexible, Optimized and controllable Production Platforms)

Project no. CZ.01.1.02/0.0/0.0/15_019/0004688, co-financed by the European Union. In the factory of the future, manufactures will improve production by applying new design priciples, implementing digital technologies, and integrating processes across the value chain. Flexibility, quality, speed and safety will also be enhanced.

eRobot

(Technology for industrial robots integration into production systems based on Industry 4.0​)

Nowadays, robotic production lines are often developed in software tools such as Tecnomatix Process Simulate. Unfortunately, these tools have insufficient support for the energy optimization of the designed line. Therefore, the primary goal of this project is to create algorithms for the optimization of robotic production lines and integrate them into software tools used in industry. All tools developed in this project will be tested on robotic platforms formed in the laboratory environment and consequently on the real robotic cells in production.​

FOREST

(Flexible Scheduling and Optimization Algorithms for Distributed Real-time Embedded Systems)

The growing complexity of Distributed Real-time Embedded Systems creates new challenges for scientific practices. For example, the automotive domain is undergoing a ground-breaking transformation with its recent commitment to making the vision of autonomous driving a reality. A common aspect for all these functions is that they rely on the periodic communication of vast amounts of sensor data that need both, timely processing and efficient use of the communication network. We will concentrate on modern time-triggered (TT) protocols that are used in many safety-critical domains. TT scheduling is characterized by complete determinism, and is, hence, particularly easy to verify and have certified. However, the traditional TT paradigm offers limited flexibility: once the schedule is computed, it is not possible to modify it, for example in response to events that may have occurred during run-time or if the resource capacity has changed.

CAK 3

(Center for Applied Cybernetics)

Center for Applied Cybernetics is a government-funded flagship project of applied cybernetics forming a collaboration platform between a few excellent czech technical universities and a dozen of hi-tech industry partners. Our goal in this project is to achieve an advancement in areas of manufacturing, energy-aware optimization and human resources optimization. We aim to develop a set of software tools based on modeling of industrial processes and optimization algorithms enabling automatization of decision making. Results of this project will contribute to the next industrial revolution - strategy Industry 4.0.

SALTT

(Scheduling Algorithms for Time-Triggered Systems)

SALTT project, funded by Office of Naval Research, develops a new theory and algorithms for message scheduling in real-time communication networks used in airplanes, cars and other vessels. A key research challenge is to find a way how to synthesize dependable and efficient schedules. With a time-predictable networking, future Engineered Resilient Systems can rely on timely communication, which helps to ensure an efficient, reliable, safe, and guaranteed connectivity.  

Industry cooperation

Consulting in Mathematical Optimization and Scheduling

We provide consulting services for companies and individuals in areas of mathematical optimization and scheduling. We are established research group in these areas with a long scientific publication record. We proceed by a detailed analysis of the problem in order to propose an efficient algorithm. However, since we keep tight cooperation with industry, we know, how to face real-life problems our customers deal with. Our advices will be valuable for your business.

Consulting in Embedded Systems and Real-Time OSs

We offer consulting services for companies and individuals in areas of embedded systems, real-time operating systems (Linux, VxWorks, OSEK) and fieldbuses systems (CAN, Profibus, Interbus S). We will advise you in security and safety aspects of embedded hardware. Moreover, we are experienced in hardware design, prototyping and development. 

Skoda Auto

We cooperate with Skoda Auto on reducing energy consumption of existing and to-be-designed robotic cells. One of our main goal is to save about 20 % of energy till 2018. Even though the target seems to be difficult to reach our preliminary results show that about 25 % of energy can be saved for an existing robotic cell by only changing robots speeds. If a full potential of our optimization algorithms is exploited the saving is expected to be even higher. Besides the energy optimization, we also collaborate on the various assistant systems inside cars, such as road sign detection, etc.

Volkswagen

The objective of this work was to realize open-source Linux-based CAN-to-CAN gateway and to provide a thorough timing analysis and measurement of packet latencies, introduced by such a gateway into a real-time networked system. The code of the CAN driver was accepted in mainline Linux.  This allows other companies and researches interested in this topic to use the driver and independently review our results and methods, as well as to use them as a base for their own experiments. Our methods and results are relevant not only for the special case of CAN-to-CAN routing, but also for the whole Linux networking system in general. The introduced gateway itself is a public available open source component using the existing Linux Kernel networking infrastructure for the Controller Area Network protocol family (PF CAN). The other topic of cooperation was QoS management and performance evaluation of CAN-CAN gateway. Further we worked on Car-to-Car communication system while  extending the Linux kernel for support of "automotive Wi-Fi" (IEEE 802.11p). This technology will be used in future cars for communication between the cars and between cars and highway infrastructure. In addition, we work on network protocol analyzer for this kind of communication.

EATON

One of the results of cooperation with EATON is Rapid prototyping platform for safety controller with time-triggered scheduling. This product allows for rapid prototyping of software for control units based on the Simulink tool. It supports a control unit based on a safety microcontroller (MCU TMS570 by Texas Instruments). With this product, developers create applications as Simulink models (in a graphical way) and our product then converts the model to the source code, compile it and download it to the control unit. The code is generated with the help of Embedded Coder toolbox. The generated code contains device drivers for all devices available on the control unit. The product also contains Simulink blocks for accessing all the peripherals. Supported peripherals are: CAN, FlexRay, digital I/O, analog I/O, power outputs, PWM outputs. We apply new time-triggered scheduling algorithms to meet timing requirements of safety applications

Air Navigation Services of the Czech Republic

We deliver high-quality rosters for Air Navigation Services of the Czech Republic allowing them to schedule shifts in highly constrained environments. Our solution consist of multi-user system (using web access to the server hosted in the company) allows human resources planning consisting of: annual leave planning, shift design, employee preferences record, automated roster generation (considering available staff, specific number and qualification of employees needed to perform various tasks, training certifications, assignment of mentors to new trainees), and swapping of duties. Further it allows for seating plan generation considering breaks and balanced workload of employees.

Profibus Czech Association

We serve as 1 out of 27 Regional Profibus Associations around the world. Profibus Czech Association organizes trainings for customers from industry.

Profibus FDL Master for European Train Control System

Delivered product was commercialized via AZD to Czech Railways.

Completed projects

ADORES

(Adaptive Scheduling and Optimization Algorithms for Distributed Real-time Embedded Systems)

In this project we aim to study structure and properties of specific scheduling problems. In our work, the first step consist of proving computational complexity of the problem in order to determine suitable solution method. Understanding structural properties of our problem is important both for heuristical approaches and exact algorithms. In more specific details, the goal of this project is to obtain a better understanding of scheduling problems in order to facilitate the development of algorithms for the automated synthesis of provably correct systems. We will concentrate on the development of (1) scheduling algorithms for time-triggered networks on local layer while focusing on adaptivity and energy awareness, (2) combinatorial optimization algorithms for global layer while considering heterogeneous resources and allowing for an energy-aware execution of tasks, but still guaranteeing system-wide timing requirements, and (3) reservation framework integrating our algorithms with the ones developed by other authors and evaluating the algorithms in on-line execution.

REMI

(Rescheduling Algorithms for Mixed-criticality Real-time Systems, U. S. Office of Naval Research)

In REMI project we work on the line of research consisting of theoretical framework and algorithms for scheduling problems with mixed-criticality. Many modern applications are of mixed criticality, where safety-critical tasks have to co-exist with less critical ones that are not subject to hard constraints. Recent research in real-time systems has yielded some promising techniques for meeting the two aspects timing properties and efficiency. Mixed-criticality approach assumes multiple processing time values to be specified for each task depending on the levels of assurance. This simple observation, dealing with tasks executed on processors initiates our idea to use the same mixed-criticality approach while dealing with messages transmitted on Time-Triggered networks.

DEMANES

(Design, Monitoring and Operation of Adaptive Networked Embedded Systems)

The goal of DEMANES is to provide component-based methods, framework and tools for development of runtime adaptive systems, making them capable of reacting to changes in themselves, in their environment (battery state, availability and throughput of the network connection, availability of external services, etc.) and in user needs (requirements).

SESAMO

(Security and Safety Modeling)

The SESAMO project addresses the root causes of problems arising with convergence of safety and security in embedded systems at architectural level, where subtle and poorly understood interactions between functional safety and security mechanisms impede system definition, development, certification, and accreditation procedures and standards. Intense market innovation is being held back by this root cause: the absence of a rigorous theoretical and practical understanding of safety and security feature interaction. The proposed solution is to develop a component-oriented design methodology based upon model-driven technology, jointly addressing safety and security aspects and their interrelation for networked embedded systems in multiple domains (e.g., avionics, transportation, industry control). (Taken from sesamo-project.eu)

ARTIST2

The central objective for the ArtistDesign European Network of Excellence on Embedded Systems Design was to build on existing structures and links forged in the FP6 Artist2 NoE, to become a virtual Center of Excellence in Embedded Systems Design. This was mainly achieved through tight integration between the central players of the European research community. These teams had already established a long-term vision for embedded systems in Europe, which advances the emergence of Embedded Systems as a mature discipline. Moreover, we participated in ARTIST as the only partner from Central-Eastern European region out of 35 partners in total.

OCERA

The objective of this project was the improvement of embedded distributed computing systems for applications with real-time constraints. The project outputs developed in our department are open source components such as LinCAN. LinCAN (Linux CAN driver) is used by several hi-tech companies developing embedded systems (OKI USA, Unicontrols CZ, Technologic Systems USA, Ingeneria Almudi ES, BFAD GmbH & Co.KG DE, Applied Biosystems AU, etc.). Other of the results of this project is ORTE - an open source implementation of Real-Time Publish-Subscribe (RTPS) communication protocol. RTPS is an application layer protocol targeted at real-time communication area, which is built on the top of standard UDP stack. Because it uses only the UDP protocol, it retains control of timing and reliability.

FRESCOR

The aim of the FRESCOR project was to develop a framework that integrates advanced flexible scheduling techniques directly into an embedded systems design methodology, covering all the levels involved in the implementation, from the OS primitives (focusing on Linux and its real-time extensions), through the middleware, up to the application level. For embedded systems developers the project provides the engineering solutions to manage timing requirements at a high level of abstraction, thus lowering the design and development costs, and speeding up the time to market. Our group addressed namely design and implementation of real-time communication protocols (based on Ethernet, CAN, WiFi, ZigBee) and scheduling on reconfigurable hardware architectures (Virtex IV, MPC).