IEEE Task Force on Evolutionary Developmental Systems and Robotics

IEEE Computational Intelligence Society (CIS) Technical Committee on Cognitive and Developmental Systems (CDS)


Aim and Scope

The objective of this task force is to strengthen the links between evolutionary approaches in artificial intelligence and the developmental and cognitive systems community. There are many potential convergences and common discussion topics, including, but not limited to:

- A large part of the evolutionary intelligence community work on “Generative and Developmental Encoding” to evolve large, life-like neural networks (“artificial brains”); as the name suggest it, these encoding exploit developmental rules to make large neural networks that exhibit some features of biological nervous systems like modularity, hierarchy, repetition, symmetry, etc.

- A new trend in evolutionary intelligence is to study alternative selective pressures and, in particular, selective pressures that encourage exploration (novelty search, behavioral diversity, etc.); these techniques share many objectives and ideas with the exploration algorithms studied in the developmental robotics community (e.g. babbling).

- Evolution can be an effective metaphore to explain and therefore imitate the plasticity of the brain (see neural darwinism and neural replicators).

- Evolution and life-time learning are two complementary processes that interact at different scales and a key research avenue is to understand what should be designed by evolution and what should be left for life-time learning.


Task Force Chair:

Jim Torresen, University of Oslo, Norway


Task Force Vice-Chairs:

Gusz Eiben, Vrije Universiteit Amsterdam, Netherlands

Stéphane Doncieux, Sorbonne Université, France


Task Force Members:

Andrea Soltoggio, Loughborough University, UK

Anthony Clark, Missouri State University, US

Emma Hart, Edinburgh Napier University, UK

Eric Medvet, University of Trieste, Italy

Jared M. Moore, Grand Valley State University, US

Jean-Baptiste Mouret, INRIA, France

Jeff Clune, University of Wyoming/Uber AI Labs, US

Kyrre Glette, University of Oslo, Norway

Nicolas Bredeche, Sorbonne Université, France

Sanaz Mostaghim, Otto von Guericke University Magdeburg, Germany

Sebastian Risi, IT University of Copenhagen, Denmark

Stefano Nichele, Oslo Metropolitan University, Norway


Future Activities

§  Stephane Doncieux is involved in a IROS 2021 workshop entitled "New Horizons for Robot Learning and common obstacles of result transfer to industry"

§  Jeff Clune will give the keynote Improving Robot and Deep Reinforcement Learning via Quality Diversity, Open-Ended, and AI-Generating Algorithms at CORL 2021 (November 8 – 11)

§  Kyrre Glette (together with Frank Veenstra) is planning to host a special session on Evolutionary Robotics in EvoApplications 2022


Past Activities


§  Stephane Doncieux with Antoine Cully and Jean-Baptiste Mouret will present a tutorial on QD algorithms at GECCO 2021. 10–14 July, 2021. There will also be another relevant workshop at the same conference: EvoRLEvolutionary Reinforcement Learning Workshop organised by colleagues.

§  Stefano Nichele (together with Giovanni Iacca and Eric Medvet) will organise a Special Session on Bio-inspired Approaches for Modular Robotics at ALIFE 2021, 19-23 July, 2021

§  Jeff Clune gave a keynote at the ICLR 2021 Neural Architecture Search Workshop, 7 May 2021

§  Jim Torresen gave the tutorial "Ethical Considerations in Robotics and Automation" at ICRA 2021

§  Gusz Eiben (together with Andy Tyrrell and Emma Hart) is a guest editors for a Special Issue on Towards autonomous evolution, (re)production and learning in robotic eco-systems, IEEE Transactions on Cognitive and Developmental Systems

§  Kyrre Glette (together with David Howard and Nick Cheney) is editing a Research Topic “Evolving Robotic Morphologiesin Frontiers in Robotics and AI

§  EU projects in which evolutionary methods are used: SoftManBot and VeriDREAM (Stephane Doncieux reported)


Published papers

§  Doncieux, S., Paolo, G., Laflaquière, A., & Coninx, A. (2020, June). Novelty search makes evolvability inevitable. In Proceedings of the 2020 Genetic and Evolutionary Computation Conference (pp. 85-93).

§  Jegorova, Marija, Stéphane Doncieux, and Timothy M. Hospedales. "Behavioral Repertoire via Generative Adversarial Policy Networks." IEEE Transactions on Cognitive and Developmental Systems (2020).

§  Kim, S., Coninx, A., & Doncieux, S. (2021). From exploration to control: learning object manipulation skills through novelty search and local adaptation. Robotics and Autonomous Systems, 136, 103710.

§  Le Goff, L. K., Hart, E., Coninx, A., & Doncieux, S. (2020, July). On pros and cons of evolving topologies with novelty search. In Artificial Life Conference Proceedings (pp. 423-431). One Rogers Street, Cambridge, MA 02142-1209 USA journals-info@ mit. edu: MIT Press.

§  J. Nordmoen, F. Veenstra, K. O. Ellefsen, and K. Glette, “MAP-Elites enables powerful stepping stones and diversity for modular robotics,” Frontiers in Robotics and AI, vol. 8, p. 56, 2021.

§  T. F. Nygaard, C. P. Martin, J. Torresen, K. Glette, and D. Howard, “Real-world embodied AI through a morphologically adaptive quadruped robot,” Nature Machine Intelligence, vol. 3, no. 5, pp. 410–419, 2021.

§   T. F. Nygaard, C. P. Martin, D. Howard, J. Torresen, and K. Glette, “Environmental adaptation of robot morphology and control through real-world evolution,” Evolutionary Computation, 2021.  

§  Paolo, G., Laflaquiere, A., Coninx, A., & Doncieux, S. (2020, May). Unsupervised learning and exploration of reachable outcome space. In 2020 IEEE International Conference on Robotics and Automation (ICRA) (pp. 2379-2385). IEEE.

§  Paolo, G., Coninx, A., Doncieux, S., & Laflaquière, A. (2021). Sparse Reward Exploration via Novelty Search and Emitters. arXiv preprint arXiv:2102.03140. (accepted at GECCO 2021)

§  Salehi, Achkan, Alexandre Coninx, and Stephane Doncieux. "BR-NS: an Archive-less Approach to Novelty Search." arXiv preprint arXiv:2104.03936 (2021). (accepted at GECCO 2021)



§  Stéphane Doncieux (together with Antoine Cully and Jean-Baptiste Mouret) gave a tutorial at GECCO 2020 on Quality-Diversity Optimization

§  Gusz Eiben (together with Emma Hart and David Howard) organised a the workshop "ADRR — Automated Design of Robots for the Real-world" at GECCO 2020

§  Special issue of Congitive Neurosynamics (Springer) as follow up of the workshop we organized at IEEE ICDL-EPIROB in Oslo. Link

§  Special Issue (SI) on Development and Learning and on Epigenetic Robotics in IEEE Transactions on Cognitive and Developmental Systems. SI with extended versions of the best papers presented in the 2019 ICDL-EpiRob conference.

§  Stefano Nichele is co-chairing IEEE ALIFE at IEEE SSCI 2020. Both “evolutionary developmental systems” and robotics are within the scope. Link: Location Canberra Australia, 1-4 December 2020.


Published papers

§  Pontes-Filho, Sidney, Pedro Lind, Anis Yazidi, Jianhua Zhang, Hugo Hammer, Gustavo BM Mello, Ioanna Sandvig, Gunnar Tufte, and Stefano Nichele. "EvoDynamic: A Framework for the Evolution of Generally Represented Dynamical Systems and Its Application to Criticality." In International Conference on the Applications of Evolutionary Computation (Part of EvoStar), pp. 133-148. Springer, Cham, 2020.

§  K. Heiney, O. H. Ramstad, I. Sandvig, A. Sandvig and S. Nichele, "Assessment and manipulation of the computational capacity of in vitro neuronal networks through criticality in neuronal avalanches," 2019 IEEE Symposium Series on Computational Intelligence (SSCI), Xiamen, China, 2019, pp. 247-254, doi: 10.1109/SSCI44817.2019.9002693.

§  Eseoghene Ben-Iwhiwhu, Pawel Ladosz, Jeffery Dick, Wen-Hua Chen, Praveen Pilly, Andrea Soltoggio, "Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems", accepted as a full paper at GECCO 2020.

§  Paul Ecoffet, Nicolas Bredeche, Jean-Baptiste André. Nothing better to do? Environment quality and the evolution of cooperation by partner choice. Preprint on Biorxiv:

§  Nicolas Fontbonne, Olivier Dauchot and Nicolas Bredeche. Distributed On-line Learning in Swarm Robotics with Limited Communication Bandwidth. Accepted at the Congress on Evolutionary Computation (CEC), 2020. (PDF not yet online)

§  A. Duburcq, N. Bredeche, Y. Chevaleyre. Online Trajectory Planning Through Combined Trajectory Optimization and Function Approximation: Application to the Exoskeleton Atalante. Accepted at the International Conference on Robotics and Automation (ICRA), 2020. (PDF not yet online)

§  A. Bernard, N. Bredeche, J-B. Andre. Indirect genetic effects allow to escape the inefficient equilibrium in a coordination game. Evolution Letters, to appear in 2020. An earlier draft is available as PDF on BioArxiv: 



Published papers


Published papers