Dr. Antoine Cully now is the director of the Adaptive and Intelligent Robotics lab, Imperial College London.
He was a Research Associate in the Personal Robotics Lab since January 2016. Before joining the laboratory, he received the M.Sc. degree in Intelligent Systems and Robotics from the University Pierre et Marie Curie (UPMC), Paris, France, in 2012. He received the same year the Engineer degree in Robotics from the Polytech-Paris UPMC engineer school, Paris, France.
After receiving these two degrees, Antoine joined the Institut des Systèmes Intelligents et de Robotique at UPMC where he received the PhD degree in Robotics and Artificial Intelligence. His PhD thesis focuses on learning algorithms that grants robots the ability to adapt to unforeseen situations, like mechanical damages in less than 2 minutes. His work has been internationally recognized with a publication in Nature (featured on the cover of the May 2015 issue), which received the “Outstanding paper 2015 award” from the International Society for Artificial Life. His PhD has also been rewarded by the “Best thesis award” from the French Association for Artificial Intelligence.
His research interests cover many aspects of learning algorithms applied to physical robots. In particular, this includes Evolutionary Robotics, Stochastic Optimization, Artificial Neural Networks, among others. Antoine is currently working for the EU H2020 project "PAL", in which he develops learning methods that allow robots the adapt to the preferences of their users.
In general, he investigates different approaches that grant robots with the ability to discover and adapt their abilities according to their environment, to different situations or to their users.
More information can be found on his personal web page.
Publications
Journals
→ Cully, A. , Clune, J., Tarapore, D. and Mouret, J.-B. (2015). Robots that can adapt like animals. Nature, 521, Pages 503-507
→ Cully, A. and Mouret, J.-B. (2015). Evolving a Behavioral Repertoire for a Walking Robot. . Evolutionary Computation Journal, . Vol. 24, No. 1, Pages 59-88
→ Koos, S., Cully, A. and Mouret, J.-B. (2013). Fast Damage Recovery in Robotics with the T-Resilience Algorithm. International Journal of Robotics Research. Vol 32 No 14 Pages 1700-1723.
Conferences
→ Tarapore D., Clune J., Cully, A. and Mouret, J.-B. (2016). How Do Different Encodings Influence the Performance of the MAP-Elites Algorithm? Proceedings of Genetic and Evolutionary Computation Conference (GECCO). Pages 175-182.
→ Maestre, C., Cully, A. , Gonzales, C. and Doncieux, S (2015). Bootstrapping interactions with objects from raw sensorimotor data: a Novelty Search based approach . IEEE International Conference on Developmental and Learning and on Epigenetic Robotics (ICDL-EPIROB).
→ Jehanno, J.-M., Cully, A. and Mouret, J.-B. (2014). Design of a Wheel-Legged Hexapod Robot for Creative Adaptation. Proceedings of Climbing and walking robot conference (CLAWAR).
→ Cully, A. and Mouret, J.-B. (2013). Behavioral Repertoire Learning in Robotics. Proceedings of Genetic and Evolutionary Computation Conference (GECCO). Pages 175.
Refereed Workshop Papers
→ Zambelli M., Fischer T., Petit M., Chang H.J., Cully A., and Demiris Y. (2016). Towards Anchoring Self-Learned Representations to Those of Other Agents. IROS 2016 Workshop on Bio-Inspired Social Robot Learning in Home Scenarios.
→ Chatzilygeroudis, K., Cully, A. and Mouret, J.-B., Towards semi-episodic learning for robot damage recovery. International Conference on Robotics and Automation (ICRA) 2016 (accepted for oral presentation).
→ Ecarlat, P., Cully, A. , Maestre, C. and Doncieux, S. (2015). Learning a high diversity of object manipulations through an evolutionary-based babbling. International Conference on Intelligent Robots and Systems (IROS) 2015.
→ Koos, S., Cully, A. and Mouret, J.-B. (2014). Abstract of: Fast Damage Recovery in Robotics with the T- Resilience Algorithm. ALIFE 14: The Fourteenth Conference on the Synthesis and Simulation of Living Systems. Pages 156-157.
→Cully, A. and Mouret, J.-B. (2014). Learning to Walk in Every Direction with the TBR-Learning algorithm. . ALIFE 14: The Fourteenth Conference on the Synthesis and Simulation of Living Systems. Pages 146-147.
