Current Projects

| NDT | RUR | DiPreFE | RIEMANN | Self-Assembly | NCK | past

MAPLE - Multi-robotic path planning and execution

Partners: Charles University (Faculty of Mathematics and Physics)
Duration: 2023-2025

Multi-agent pathfinding (MAPF) is an abstract model for planning the collision-free movement of a group of agents in a shared environment. When applying MAPF techniques to actual robots, for example, in autonomous warehouses, the planning techniques need to fulfill several criteria that the current academic MAPF research does not adequately address. They need to scale to many robots, provide flexibility during plan execution to accommodate minor deviations from the plans, detect possible future issues (collisions) caused by inaccuracies in plan execution or environment changes, and respond adequately to these dynamic changes. We first compare the scalability and solution quality of AI and robotics approaches to solving the MAPF problem. We propose novel planning techniques appropriate for real robots, focusing on the robustness and flexibility of plans. We suggest how to diagnose future failures (collisions) during execution and resolve these failures before they happen.

The project aims to develop path (re-)planning techniques for a group of mobile robots primarily in the autonomous warehouse setting, focusing on robust, flexible, and safe plan execution even after internal and external disturbances.

This project has received funding from the Czech Science Foundation (GACR) under grant agreement no. 23-05104S (STARFOS TACR)

NDT – Autonomous robotic system for ultrasonic and eddy current inspection of metal and composite parts of complex shapes

Partners: LA composite s.r.o., ATG s.r.o.
Duration: 2021-2024

The project goal is research and development of technologies of an autonomous robotic system for inspection of composite materials, spot welds, and rivet joints on parts of complex shapes using ultrasonic and eddy current methods. Autonomy will be provided by a developed navigation method, which combines image and ultrasound/eddy current data.

The partners expect to utilize the project outputs to support their production, services and sales. LAC will employ the developed equipment for output inspection of composite parts in its production and as a customer service. ATG will use the technologies as a new sales item for customers requiring autonomous and advanced technologies for output control. CVUT will acquire new knowledge and technologies for future research, development, and teaching.

Learn more about this project.

This project is co-financed from the state budget by the Technology Agency of the Czech Republic within the TREND Programme under grant agreement No FW03010600. (STARFOS TACR)

RUR - Research and development of a robotic system for automated masonry from clay blocks

Partners: KM Robotics s.r.o. , Wienerberger s.r.o.
Duration: 2021-2023

The main goal of the project is research and development of a functional sample of a robotic system for automated masonry. The aim is to speed up and increase the efficiency of masonry process in comparison to the traditional method of manual masonry. This part of research dealing with robotic system is managed by Wellnea s.r.o (the main participant) and Czech Technical University in Prague (other participant). The partial goal of the project is research and development of a functional sample of masonry material (clay blocks including binder) specially designed for the needs of robotic system - materials marked "RR" (Robot Ready).

This project is co-financed from the state budget by the Technology Agency of the Czech Republic and Ministry of industry and trade within the Trend Programme under grant agreement No FW03010304. (STARFOS TACR)

DiPreFE - Implementation of diagnostics and predictive maintenance for efficient control of photovoltaic power plants by autonomous means

Partners: Decci servis s.r.o., Enprotech a.s., "TMV SS" s.r.o.
Duration: 2020-2024

The goal of this project is to design, develop, and verify a prototype system for predictive maintenance of a photovoltaic powerplant capable of periodic thermographic and visual inspection of PV modules making use of UAVs during the operation time of PP. The system is able to predict module failure and evaluate the influence of this failure on the power production of PP. The system for predictive maintenance allows the proposal of optimal actions to maximalize power production and economic effectiveness. Partial goals are:

  • Design, development, and verification of specialized methods for accurate navigation and location of unmanned aerial vehicles
  • Methods for the collection of thermographic and visual image data, their fusion, and subsequent evaluation to detect potential defects of PV modules with the possible addition of a detailed picture of the expected defective module
  • Estimation of the impact of the module defect on the performance, when the module will be dismantled and measured in laboratory conditions
  • Creation and maintenance of a catalog of module defects with a specific signature in the visual and thermal area and the measured impact on their performance
  • Statistical temporal models of progression of individual types of defects.

Project results (in Czech)

  • Autonomous aerial vehicle for the inspection of photovoltaic power plants - TK03020144-V1
  • System for processing measured data, prediction and evaluation of failures and predictive maintenance of PV plants - TK03020144-V2
This project is co-financed from the state budget by the Technology Agency of the Czech Republic within the THÉTA Programme under grant agreement No TK03020144. (STARFOS TACR)

RIEMANN - ROS-based Education of Advanced Motion Planning and Control

Partners: Bremer Institut für Produktion und Logistik GmbH (BIBA), University of Tartu, Comau S.p.A.
Duration: 2022-2023

This project reduces technological barriers to the use of mobile manipulator robots or fleets in industrial environments. This project will train a large pool of university students and professionals in advanced concepts of autonomous robotics, especially in the use of existing open-source libraries on mobile platforms.

Advanced yet didactic training materials enable professionals to understand the inner workings of robotic systems implemented in ROS and other open-source frameworks. The courses are designed for professionals of all groups and skill levels. Building on the basic courses on ROS and robotic systems, the audience learns at a pace that suits their needs. Regular assessments of skill levels allow for the shortest possible training to achieve maximum impact. Learners can choose to include additional theoretical background to supplement their practical skills with a scientific layer. This design will save many hours currently spent on unnecessary training due to inappropriate course content.

This project is co-financed by the European Union within the EIT Manufacturing umbrella under the activities number 22235 and 23517.

Non-periodic pattern-forming metamaterials: Modular design and fabrication

Duration: 2019-2023

This 5-year long project aims to get as close as possible to its goal of finding a functional macroscopic-scale system capable of assembling complex parts made from simple passive tiles. It can be imagined as if someone strews many small tiles (e.g. LEGO) into some kind of mechanical or magneto-mechanical shaker and minutes (or hours) later gets a fully assembled robotic arm ready to be used. These assembling systems are being quite widely researched and used in biomedicine and nanotechnologies, but there are some limitations present in the macroscale world only. During the first years of the project, we developed stochastic simulators (aTAM, kTAM, and 2HAM) and constructed a robotic system for agitation of self-assembly elements. After the successful assembly of a chessboard pattern, we hit a limitation related to the overall assembly size and used driving force, so the project is now heading towards different electromagnetic tile excitations which would avoid these assembly size limitations.

This project has received funding from the Czech Science Foundation (GACR) under grant agreement no. 19-26143X (STARFOS TACR)

National Competence Center – Cybernetics and Artificial Intelligence

Partners: 4 universities, 3 institutes of Czech Academy of Sciences, and 22 companies
Duration: 2018-2022

The NCK KUI project aims to create a national platform for cybernetics and artificial intelligence which interlinks research and application-oriented centers of robotics and cybernetics for Industry 4.0, Smart Cities, intelligent transport systems and cybersecurity. The connection of innovation leaders will raise effectivity of applied research in key areas, such as advanced technology for globally competitive industry, ICT and transportation for the 21st century. NCK KUI is closely related to the application sector and enables cross-domain collaboration, innovation development and technology transfer. The project consists of 21 research streams and IMR is active in four of them:

  • Artificial Intelligence and Machine Learning
    • Research, development and application of AI and (D)ML methods to smart robotic sensing and manipulation specializing in handling objects of various shapes and sizes that can be hardly described in an analytical way.
  • Robotics and flexible manufacturing
    • Development of a device enabling automatic assembly of thread joints onto a moving target using an interconnected visual-force servoing.
  • Artificial intelligence, autonomous and cooperative transport systems
    • Utilization of artificial intelligence methods in the areas of unmanned vehicles, autonomous logistics systems and automated warehouses with focus on multi-robot navigation and path planning.
  • Robotic operations in a hazardous environment and intelligent maintenance
    • Development of mobile robotic devices capable of operations in inaccessible, harsh, dangerous or contaminated areas with a focus on navigation using learned scene features and visual learned teach-and-repeat robot navigation in environments exhibiting high variability and complex shape and structure.
This project is supported by the Technology Agency of the Czech Republic within the programme National Centres of Competence 1: Support programme for applied research, experimental development and innovation. (STARFOS TACR)

See also our industry applications and recently finished projects.

Page last modified on March 28, 2024, at 08:42 AM EST
Powered by PmWiki