DEMIURGE

Automatic Design of Robot Swarms

The research project "DEMIURGE: automatic design of robot swarms" was funded by the European Research Council via an ERC Consolidator Grant between 2016 and 2022.

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. Previously, the collective behavior of robot swarms had been designed via some labor-intensive process.

The project advanced the state of the art in swarm robotics by developing a novel approach to designing and realizing collective behaviors for robot swarms. In this approach, a mission to be performed is specified using a high-level specification language. The design problem is then automatically formulated as an optimization problem that is itself always automatically solved in a computation-intensive way based on simulations.

All in all, this process automatically generates the control software of the individual robots that determines the desired collective behavior, that is, the one that enables the swarm to successfully perform the mission at hand. The approach can be used to concurrently design, together with the control software, also the hardware of the individual robots.

In the project, we studied several control software structures, optimization algorithms, ways to specify requirements, validation protocols, on-line adaptation mechanisms and techniques for generating solution strategies at run time.

Highlights


More videos in our YouTube Channel

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] 
  • A. Ligot, A. Cotorruelo, E. Garone, M. Birattari, "Towards an empirical practice in off-line fully-automatic design of robot swarms", IEEE Transactions on Evolutionary Computation, vol. 26, no. 6, pp. 1236–1245, 2022. [pdf]  [www]  [bibtex] 
  • M. Birattari, A. Ligot, G. Francesca, "AutoMoDe: a modular approach to the automatic off-Line design and fine-tuning of control software for robot swarms", Automated Design of Machine Learning and Search Algorithms, pp. 73–90, 2021. [pdf]  [www]  [bibtex] 
  • D. Bozhinoski, M. Birattari, "Towards an integrated automatic design process for robot swarms", Open Research Europe, vol. 1, 112, 2022. [pdf]  [www]  [bibtex] 
  • 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] 
  • 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] 
  • L. Garattoni, "Cognitive abilities in swarm robotics. Developing a swarm that can collectively sequence tasks.", Doctoral dissertation, Université libre de Bruxelles, 2021. [pdf]  [bibtex] 
  • G. Francesca, "A modular approach to the automatic design of control software for robot swarms: from a novel perspective on the reality gap to AutoMoDe", Doctoral dissertation, Université libre de Bruxelles, 2017. [pdf]  [bibtex] 
  1. I. Gharbi, J. Kuckling, D. Garzón Ramos, M. Birattari, "Show me what you want: inverse reinforcement learning to automatically design robot swarms by demonstration", 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023. [pdf]  [www]  [bibtex]  (Accepted
  2. A. Ligot, M. Birattari, "On using simulation to predict the performance of robot swarms", Scientific Data, vol. 9, 788, 2022. [pdf]  [www]  [bibtex] 
  3. G. Legarda Herranz, P. Rochala, P. Georgiopoulou, A. Ligot, M. Salman, M. Birattari, "BRIC: an interactive smart object for swarm robotics research", Tech. Report, TR/IRIDIA/2022-015, 2022. [pdf]  [bibtex] 
  4. D. Garzón Ramos, M. Salman, K. Ubeda Arriaza, K. Hasselmann, M. Birattari, "MoCA: a modular RGB color arena for swarm robotics experiments", Tech. Report, TR/IRIDIA/2022-014, 2022. [pdf]  [bibtex] 
  5. M. Kegeleirs, D. Garzón Ramos, M. Birattari, "DeimOS: a ROS-ready operating system for the e-puck", Tech. Report, TR/IRIDIA/2022-013, 2022. [pdf]  [bibtex] 
  6. M. Kegeleirs, R. Todesco, D. Garzón Ramos, G. Legarda Herranz, M. Birattari, "Mercator: hardware and software architecture for experiments in swarm SLAM", Tech. Report, TR/IRIDIA/2022-012, 2022. [pdf]  [bibtex] 
  7. G. Legarda Herranz, E. Garone, M. Birattari, "A hybrid-system formalism to verify properties of robot swarms", Book of Abstracts 41st Benelux Meeting on Systems and Control, 46, 2022. [pdf]  [www]  [bibtex] 
  8. A. Sion, A. Reina, M. Birattari, E. Tuci, "Impact of the update time on the aggregation of robotic swarms through informed robots", From Animals to Animats 16: 16th International Conference on Simulation of Adaptive Behavior, SAB 2022, vol. 13499, pp. 381–390, 2022. [pdf]  [www]  [bibtex] 
  9. A. Sion, A. Reina, M. Birattari, E. Tuci, "Controlling robot swarm aggregation through a minority of informed robots", Swarm Intelligence – ANTS, vol. 13941, pp. 91–103, 2022. [pdf]  [www]  [bibtex] 
  10. G. Legarda Herranz, S. Hauert, S. Jones, "Decentralised negotiation for multi-object collective transport with robot swarms", 2022 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), pp. 186–191, 2022. [pdf]  [www]  [bibtex] 
  11. J. Mendiburu Fernando, D. Garzón Ramos, R. Morais Marcos, M. Lima Antonio, M. Birattari, "AutoMoDe-Mate: automatic off-line design of spatially-organizing behaviors for robot swarms", Swarm and Evolutionary Computation, vol. 74, 101118, 2022. [pdf]  [www]  [bibtex] 
  12. D. Bozhinoski, M. Birattari, "Towards an integrated automatic design process for robot swarms", Open Research Europe, vol. 1, 112, 2022. [pdf]  [www]  [bibtex] 
  13. A. Ligot, A. Cotorruelo, E. Garone, M. Birattari, "Towards an empirical practice in off-line fully-automatic design of robot swarms", IEEE Transactions on Evolutionary Computation, vol. 26, no. 6, pp. 1236–1245, 2022. [pdf]  [www]  [bibtex] 
  14. J. Kuckling, V. van Pelt, M. Birattari, "AutoMoDe-Cedrata: automatic design of behavior trees for controlling a swarm of robots with communication capabilities", SN Computer Science, vol. 3, 136, 2022. [pdf]  [www]  [bibtex] 
  15. D. Garzón Ramos, "Comparación empírica de métodos de diseño de enjambres de robots: un estudio en simulación sobre enjambres que coordinan a otros enjambres", Master's thesis, Universidad Nacional de Colombia, 2022. [pdf]  [bibtex] 
  16. I. Gharbi, "Intuitive mission specification for robot swarm by learning from demonstration", Master's thesis, Université libre de Bruxelles, 2022. [pdf]  [bibtex] 
  17. R. Todesco, "RVR: A new robot platform for swarm robotics. The building blocks of new horizons", Master's thesis, Université libre de Bruxelles, 2022. [pdf]  [bibtex] 
  18. A. Hasan, "Building an integrated framework for the automatic modular design of robot swarms", Master's thesis, Université libre de Bruxelles, 2022. [pdf]  [bibtex] 
  19. F. Trouillez, "Robot recognition using a 360-degree vision module for swarm robots: A new view on swarm robotics", Master's thesis, Université libre de Bruxelles, 2022. [pdf]  [bibtex] 
  20. G. Legarda Herranz, D. Garzón Ramos, J. Kuckling, M. Kegeleirs, M. Birattari, "Tycho: a robust, ROS-based tracking system for robot swarms", Tech. Report, TR/IRIDIA/2022-009, 2022. [pdf]  [bibtex] 
  21. D. Garzón Ramos, J. Bolaños, J. Diaz, G. Pachajoa, M. Birattari, "Introduciendo la robótica de enjambres a entusiastas de la robótica: experiencias y resultados de una colaboración académica", I Congreso Internacional de la Sociedad de Doctores e Investigadores de Colombia (SOPHIC 2021): la ciencia al servicio de la sociedad, pp. 46–48, 2021. [pdf]  [www]  [bibtex] 
  22. M. Birattari, A. Ligot, G. Francesca, "AutoMoDe: a modular approach to the automatic off-Line design and fine-tuning of control software for robot swarms", Automated Design of Machine Learning and Search Algorithms, pp. 73–90, 2021. [pdf]  [www]  [bibtex] 
  23. 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] 
  24. 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] 
  25. 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] 
  26. L. Garattoni, "Cognitive abilities in swarm robotics. Developing a swarm that can collectively sequence tasks.", Doctoral dissertation, Université libre de Bruxelles, 2021. [pdf]  [bibtex] 
  27. 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] 
  28. M. Kegeleirs, G. Grisetti, M. Birattari, "Swarm SLAM: challenges and perspectives", Frontiers in Robotics and AI, vol. 8, 23, 2021. [pdf]  [www]  [bibtex] 
  29. I.-B. Vlad, "Importance sampling with intermediate rewards to estimate the performance of a robot swarm", Master's thesis, Vrije Universiteit Brussel, 2021. [pdf]  [bibtex] 
  30. P. Rochala, "Automatic design of collective behaviors for robots that operate in dynamic environments", Master's thesis, Université libre de Bruxelles, 2021. [pdf]  [bibtex] 
  31. A. Cotorruelo, A. Ligot, E. Garone, M. Birattari, "Minimizing the variance in the estimation of the performance of a method for the fully-automatic design of robot swarms: a mathematical proof", Tech. Report, TR/IRIDIA/2021-007, 2021. [pdf]  [bibtex] 
  32. J. Kuckling, K. Hasselmann, V. van Pelt, C. Kiere, M. Birattari, "AutoMoDe Editor: a visualization tool for AutoMoDe", Tech. Report, TR/IRIDIA/2021-009, 2021. [pdf]  [bibtex] 
  33. 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] 
  34. 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] 
  35. F. Pagnozzi, T. Stutzle, "Evaluating the impact of grammar complexity in automatic algorithm design", International Transactions in Operational Research, 2020. [pdf]  [www]  [bibtex] 
  36. 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] 
  37. 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] 
  38. 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] 
  39. 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] 
  40. 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] 
  41. 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] 
  42. 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] 
  43. V. van Pelt, "Automatic modular design of control software in robot swarms: Towards exploitation of behaviour trees features", Master's thesis, Université libre de Bruxelles, 2020. [pdf]  [bibtex] 
  44. M. Birattari, "Notes on the estimation of the expected performance of automatic methods for the design of control software for robot swarms", Tech. Report, TR/IRIDIA/2020-10, 2020. [pdf]  [bibtex] 
  45. 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] 
  46. 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] 
  47. 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] 
  48. 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] 
  49. 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] 
  50. 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] 
  51. 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] 
  52. 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] 
  53. 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] 
  54. M. Allwright, W. Zhu, M. Dorigo, "An open-source multi-robot construction system", HardwareX, vol. 5, e00050, 2019. [pdf]  [www]  [bibtex] 
  55. K. Ubeda Arriaza, "Design of robot swarms by optimization: An instance of AutoMoDe based on simulated annealing", Master's thesis, Université libre de Bruxelles, 2019. [pdf]  [bibtex] 
  56. J. Ruddick, "Comparison of state-of-the-art evolutionary methods for the design of robot swarms", Master's thesis, Université libre de Bruxelles, 2019. [pdf]  [bibtex] 
  57. G. Spaey, "The influence of random walks on automatic design of robot swarms: An experiment with AutoMoDe", Master's thesis, Université libre de Bruxelles, 2019. [pdf]  [bibtex] 
  58. A. AlFaham, "A family of methods based on NEAT for the automatic design of behaviors of single robots and robot swarms", Master's thesis, Vrije Universiteit Brussel, 2019. [pdf]  [bibtex] 
  59. 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] 
  60. 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] 
  61. 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] 
  62. 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] 
  63. 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] 
  64. L. Garattoni, M. Birattari, "Autonomous task sequencing in a robot swarm", Science Robotics, vol. 3, no. 20, eaat0430, 2018. [pdf]  [www]  [bibtex] 
  65. 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] 
  66. M. Kegeleirs, "Developing ROS-based software for the e-puck: An experiment in exploration and mapping", Master's thesis, Université libre de Bruxelles, 2018. [pdf]  [bibtex] 
  67. J. Kuckling, A. Ligot, D. Bozhinoski, M. Birattari, "Search space for AutoMoDe-Chocolate and AutoMoDe-Maple", Tech. Report, TR/IRIDIA/2018-012, 2018. [pdf]  [bibtex] 
  68. K. Hasselmann, A. Ligot, G. Francesca, D. Garzón Ramos, M. Salman, J. Kuckling, J. Mendiburu Fernando, M. Birattari, "Reference models for AutoMoDe", Tech. Report, TR/IRIDIA/2018-002, 2018. [pdf]  [bibtex] 
  69. A. Roli, A. Ligot, M. Birattari, "Complexity measures in automatic design of robot swarms: an exploratory study", WIVACE 2017: Artificial Life and Evolutionary Computation, vol. 830, pp. 243–246, 2018. [pdf]  [www]  [bibtex] 
  70. A. Ligot, K. Hasselmann, B. Delhaisse, L. Garattoni, G. Francesca, M. Birattari, "AutoMoDe, NEAT, and EvoStick: implementations for the e-puck robot in ARGoS3", Tech. Report, TR/IRIDIA/2017-002, 2017. [pdf]  [bibtex] 
  71. G. Francesca, "A modular approach to the automatic design of control software for robot swarms: from a novel perspective on the reality gap to AutoMoDe", Doctoral dissertation, Université libre de Bruxelles, 2017. [pdf]  [bibtex] 

Resources



Relevant software, hardware, and teaching material produced in the DEMIURGE project.

AutoMoDe

Automatic modular design methods.
   

Neuroevolution

Neuroevolutionary design methods.
   

e-puck

Software library to operate the e-puck robot.
   

Tycho

ROS tracking system for swarm robotics.
   

Phormica

Artificial pheromone module for the e-puck.
   

Mercator

Robot platform for swarm SLAM.
   

MoCA

Modular RGB arena for swarms of e-pucks.
   

BRIC

Interactice smart object for the e-puck.
   

Automatic design

Automatic design of robot swarms, by M. Birattari.

Multimedia

Information capsules and video demonstrations.

Bibliography

Curated bibliography used in the publications.

Robot simulation

Simulation of robots with ROS and ARGoS.

In the media


People


Contact


For information on the DEMIURGE project, please find us in: