DEMIURGE

Automatic Design of Robot Swarms

The research project "DEMIURGE: automatic design of robot swarms" is funded by the European Research Council via an ERC Consolidator Grant

Principal investigator: Mauro Birattari

The DEMIURGE project


The scope of the DEMIURGE project is the automatic design of robot swarms. Swarm robotics is an appealing approach to the coordination of large groups of robots. Up to now, robot swarms have been designed via some labor intensive process.

Our goal is to advance the state of the art in swarm robotics by developing the DEMIURGE: an intelligent system that is able to design and realize robot swarms in a totally integrated and automatic way.

The DEMIURGE is a novel concept. Starting from requirements expressed in an appropriate specification language, the DEMIURGE will design all aspects of a robot swarm: hardware and control software. The DEMIURGE will not create the design of a robot swarm from scratch: it will operate on a number of preexisting software and hardware modules — it will obtain candidate designs by properly assembling these modules and fine-tuning their parameters.

Publications


  • M. Birattari, A. Ligot, D. Bozhinoski, M. Brambilla, G. Francesca, L. Garattoni, D. Garzón Ramos, K. Hasselmann, M. Kegeleirs, J. Kuckling, F. Pagnozzi, A. Roli, M. Salman, T. Stutzle, "Automatic off-line design of robot swarms: a manifesto", Frontiers in Robotics and AI, vol. 6, 59, 2019. [pdf]  [www]  [bibtex] 
  • L. Garattoni, M. Birattari, "Autonomous task sequencing in a robot swarm", Science Robotics, vol. 3, no. 20, eaat0430, 2018. [pdf]  [www]  [bibtex] 
  • M. Birattari, A. Ligot, K. Hasselmann, "Disentangling automatic and semi-automatic approaches to the optimization-based design of control software for robot swarms", Nature Machine Intelligence, vol. 2, no. 9, pp. 494–499, 2020. [pdf]  [www]  [bibtex] 
  • M. Salman, A. Ligot, M. Birattari, "Concurrent design of control software and configuration of hardware for robot swarms under economic constraints", PeerJ Computer Science, vol. 5, e221, 2019. [pdf]  [www]  [bibtex] 
  • K. Hasselmann, A. Ligot, J. Ruddick, M. Birattari, "Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms", Nature Communications, vol. 12, 4345, 2021. [pdf]  [www]  [bibtex] 
  1. K. Hasselmann, A. Ligot, J. Ruddick, M. Birattari, "Empirical assessment and comparison of neuro-evolutionary methods for the automatic off-line design of robot swarms", Nature Communications, vol. 12, 4345, 2021. [pdf]  [www]  [bibtex] 
  2. F. Pagnozzi, M. Birattari, "Off-policy evaluation of the performance of a robot swarm: Importance sampling to assess potential modifications to the finite-state machine that controls the robots", Frontiers in Robotics and AI, vol. 8, 55, 2021. [pdf]  [www]  [bibtex] 
  3. J. Kuckling, V. van Pelt, M. Birattari, "Automatic modular design of behavior trees for robot swarms with communication capabilities", Applications of Evolutionary Computation: 24th International Conference, EvoApplications 2021, vol. 12694, pp. 130–145, 2021. [pdf]  [www]  [bibtex] 
  4. L. Garattoni, "Cognitive abilities in swarm robotics. Developing a swarm that can collectively sequence tasks.", PhD thesis, Université Libre de Bruxelles, 2021. [pdf]  [bibtex] 
  5. D. Garzón Ramos, D. Bozhinoski, G. Francesca, L. Garattoni, K. Hasselmann, M. Kegeleirs, J. Kuckling, A. Ligot, J. Mendiburu Fernando, F. Pagnozzi, M. Salman, T. Stutzle, M. Birattari, "The automatic off-line design of robot swarms:recent advances and perspectives", R2T2: Robotics Research for Tomorrow's Technology, 2021. [pdf]  [www]  [bibtex] 
  6. M. Kegeleirs, G. Grisetti, M. Birattari, "Swarm SLAM: challenges and perspectives", Frontiers in Robotics and AI, vol. 8, 23, 2021. [pdf]  [www]  [bibtex] 
  7. G. Spaey, M. Kegeleirs, D. Garzón Ramos, M. Birattari, "Evaluation of alternative exploration schemes in the automatic modular design of robot swarms", Artificial Intelligence and Machine Learning: BNAIC 2019, BENELEARN 2019, vol. 1196, pp. 18–33, 2020. [pdf]  [www]  [bibtex] 
  8. J. Kuckling, K. Ubeda Arriaza, M. Birattari, "AutoMoDe-IcePop: automatic modular design of control software for robot swarms using simulated annealing", Artificial Intelligence and Machine Learning: BNAIC 2019, BENELEARN 2019, vol. 1196, pp. 3–17, 2020. [pdf]  [www]  [bibtex] 
  9. F. Pagnozzi, T. Stutzle, "Evaluating the impact of grammar complexity in automatic algorithm design", International Transactions in Operational Research, 2020. [pdf]  [www]  [bibtex] 
  10. M. Salman, D. Garzón Ramos, K. Hasselmann, M. Birattari, "Phormica: photochromic pheromone release and detection system for stigmergic coordination in robot swarms", Frontiers in Robotics and AI, vol. 7, 195, 2020. [pdf]  [www]  [bibtex] 
  11. J. Kuckling, T. Stutzle, M. Birattari, "Iterative improvement in the automatic modular design of robot swarms", PeerJ Computer Science, vol. 6, e322, 2020. [pdf]  [www]  [bibtex] 
  12. A. Ligot, J. Kuckling, D. Bozhinoski, M. Birattari, "Automatic modular design of robot swarms using behavior trees as a control architecture", PeerJ Computer Science, vol. 6, e314, 2020. [pdf]  [www]  [bibtex] 
  13. A. Ligot, K. Hasselmann, M. Birattari, "AutoMoDe-Arlequin: neural networks as behavioral modules for the automatic design of probabilistic finite state machines", Swarm Intelligence -- ANTS, vol. 12421, pp. 109–122, 2020. [pdf]  [www]  [bibtex] 
  14. K. Hasselmann, M. Birattari, "Modular automatic design of collective behaviors for robots endowed with local communication capabilities", PeerJ Computer Science, vol. 6, e291, 2020. [pdf]  [www]  [bibtex] 
  15. M. Birattari, A. Ligot, K. Hasselmann, "Disentangling automatic and semi-automatic approaches to the optimization-based design of control software for robot swarms", Nature Machine Intelligence, vol. 2, no. 9, pp. 494–499, 2020. [pdf]  [www]  [bibtex] 
  16. D. Garzón Ramos, M. Birattari, "Automatic design of collective behaviors for robots that can display and perceive colors", Applied Sciences, vol. 10, no. 13, 4654, 2020. [pdf]  [www]  [bibtex] 
  17. A. Roli, A. Ligot, M. Birattari, "Complexity measures: open questions and novel opportunities in the automatic design and analysis of robot swarms", Frontiers in Robotics and AI, vol. 6, 130, 2019. [pdf]  [www]  [bibtex] 
  18. G. Spaey, M. Kegeleirs, D. Garzón Ramos, M. Birattari, "Comparison of different exploration schemes in the automatic modular design of robot swarms", Proceedings of the Reference AI & ML Conference for Belgium, Netherlands & Luxemburg, BNAIC/BENELEARN 2019, vol. 2491, 2019. [pdf]  [www]  [bibtex] 
  19. J. Kuckling, K. Ubeda Arriaza, M. Birattari, "Simulated annealing as an optimization algorithm in the automatic modular design of robot swarms", Proceedings of the Reference AI & ML Conference for Belgium, Netherlands & Luxemburg, BNAIC/BENELEARN 2019, vol. 2491, 2019. [pdf]  [www]  [bibtex] 
  20. A. Ligot, M. Birattari, "Simulation-only experiments to mimic the effects of the reality gap in the automatic design of robot swarms", Swarm Intelligence, pp. 1–24, 2019. [pdf]  [www]  [bibtex] 
  21. M. Salman, A. Ligot, M. Birattari, "Concurrent design of control software and configuration of hardware for robot swarms under economic constraints", PeerJ Computer Science, vol. 5, e221, 2019. [pdf]  [www]  [bibtex] 
  22. M. Birattari, A. Ligot, D. Bozhinoski, M. Brambilla, G. Francesca, L. Garattoni, D. Garzón Ramos, K. Hasselmann, M. Kegeleirs, J. Kuckling, F. Pagnozzi, A. Roli, M. Salman, T. Stutzle, "Automatic off-line design of robot swarms: a manifesto", Frontiers in Robotics and AI, vol. 6, 59, 2019. [pdf]  [www]  [bibtex] 
  23. M. Kegeleirs, D. Garzón Ramos, M. Birattari, "Random walk exploration for swarm mapping", Towards Autonomous Robotic Systems, TAROS, vol. 11650, pp. 211–222, 2019. [pdf]  [www]  [bibtex] 
  24. D. Bozhinoski, D. Garlan, I. Malavolta, P. Pelliccione, "Managing safety and mission completion via collective run-time adaptation", Journal of Systems Architecture, vol. 95, pp. 19–35, 2019. [pdf]  [www]  [bibtex] 
  25. D. Bozhinoski, D. Di Ruscio, I. Malavolta, P. Pelliccione, I. Crnkovic, "Safety for mobile robotic systems: A systematic mapping study from a software engineering perspective", Journal of Systems and Software, vol. 151, pp. 150–179, 2019. [pdf]  [www]  [bibtex] 
  26. M. Allwright, W. Zhu, M. Dorigo, "An open-source multi-robot construction system", HardwareX, vol. 5, e00050, 2019. [pdf]  [www]  [bibtex] 
  27. A. Ligot, M. Birattari, "On mimicking the effects of the reality gap with simulation-only experiments", Swarm Intelligence -- ANTS, vol. 11172, pp. 109–122, 2018. [pdf]  [www]  [bibtex] 
  28. K. Hasselmann, F. Robert, M. Birattari, "Automatic design of communication-based behaviors for robot swarms", Swarm Intelligence -- ANTS, vol. 11172, pp. 16–29, 2018. [pdf]  [www]  [bibtex] 
  29. M. Allwright, N. Bhalla, C. Pinciroli, M. Dorigo, "Simulating multi-robot construction in ARGoS", Swarm Intelligence -- ANTS, vol. 11172, pp. 188–200, 2018. [pdf]  [www]  [bibtex] 
  30. M. Trabattoni, G. Valentini, M. Dorigo, "Hybrid control of swarms for resource selection", Swarm Intelligence -- ANTS, vol. 11172, pp. 57–70, 2018. [pdf]  [www]  [bibtex] 
  31. J. Kuckling, A. Ligot, D. Bozhinoski, M. Birattari, "Behavior trees as a control architecture in the automatic modular design of robot swarms", Swarm Intelligence -- ANTS, vol. 11172, pp. 30–43, 2018. [pdf]  [www]  [bibtex] 
  32. L. Garattoni, M. Birattari, "Autonomous task sequencing in a robot swarm", Science Robotics, vol. 3, no. 20, eaat0430, 2018. [pdf]  [www]  [bibtex] 
  33. D. Bozhinoski, M. Birattari, "Designing control software for robot swarms: software engineering for the development of automatic design methods", Proceedings of the 1st International Workshop on Robotics Software Engineering, RoSE, pp. 33–35, 2018. [pdf]  [www]  [bibtex] 
  34. A. Roli, A. Ligot, M. Birattari, "Complexity measures in automatic design of robot swarms: an exploratory study", Italian Workshop on Artificial Life and Evolutionary Computation, WIVACE, 2017. [pdf]  [www]  [bibtex] 

Tools


Here is a list of the tools and resources that have been developed under the DEMIURGE project.

AutoMoDe

Automatic modular design methods. Github

NEAT

A version of NEAT for ARGoS3. Github

AutoMoDe-localsearch

An iterative improvement algorithm for AutoMoDe. Github

e-puck

A model of the e-puck robot for ARGoS3. Github

Hardware projects

Hardware developed during the project. website

Lectures and Course materials

Lectures and course material produced by the project here

In the media


People


Contact


For information on the DEMIURGE project, please contact us at:

info@demiurge.be