Evolutionary Robotics for Micro Air Vehicles

Small robots with limited computational and sensory capabilities are becoming more commonplace. Designing effective behavior for small robotic platforms to complete complex tasks is a major challenge. A promising methodology to address this problem is found in Evolutionary Robotics (ER), in which a robot’s controller, and possibly its body, is optimized using Evolutionary Learning (EL) techniques. This approach satisfies given computational constraints, while often resulting in unexpected solutions that exploit sensory-motor coordination to achieve complex tasks.

After more than 20 years of research on ER there are still many open questions. Most issues surround the question of how ER is implemented on a real robotic platform resulting in effective robust behavior. Additionally, most implementation of ER to date have been to robots completing relatively simple tasks in a constrained environment.

Can Evolutionary Robotics be used to enable small, computationally limited flying robotic platforms to complete goal-driven tasks in complex environments?

2016

  • [DOI] K. Scheper and G. {de Croon}, “Abstraction as a mechanism to cross the reality gap in evolutionary robotics,” in From animals to animats 14, 2016, p. 280–292.
    [Bibtex]
    @inproceedings{228b1c6d26fc487aa0e3bfbdddebd54b,
    author = {Kirk Scheper and {de Croon}, Guido},
    booktitle = {From Animals to Animats 14},
    day = {10},
    doi = {10.1007/978-3-319-43488-9_25},
    editor = {Elio Tuci and Alexandros Giagkos and Myra Wilson and John Hallam},
    isbn = {978-3-319-43487-2},
    keywords = {Evolutionary Robotics, Reality Gap, Abstraction, Homogeneous Swarm Control},
    language = {English},
    month = {August},
    pages = {280--292},
    publisher = {Springer Science+Business Media},
    series = {Lecture Notes in Computer Science},
    title = {Abstraction as a Mechanism to Cross the Reality Gap in Evolutionary Robotics},
    url = {https://research.tudelft.nl/en/publications/abstraction-as-a-mechanism-to-cross-the-reality-gap-in-evolutiona},
    volume = {9825},
    year = {2016}
    }
  • [DOI] K. Scheper, S. Tijmons, C. {de Visser}, and G. {de Croon}, “Behavior trees for evolutionary robotics,” Artificial life, vol. 22, iss. 1, p. 23–48, 2016.
    [Bibtex]
    @article{8a89b8035e7640cd8c22b9b9c10e46dc,
    author = {Kirk Scheper and Sjoerd Tijmons and {de Visser}, Coen and {de Croon}, Guido},
    day = {17},
    doi = {10.1162/ARTL_a_00192},
    issn = {1064-5462},
    journal = {Artificial Life},
    keywords = {Behaviour Tree, Evolutionary Robotics, Reality Gap, MAVs},
    language = {English},
    month = {February},
    number = {1},
    pages = {23--48},
    publisher = {MIT Press Journals},
    title = {Behavior Trees for Evolutionary Robotics},
    url = {https://research.tudelft.nl/en/publications/behavior-trees-for-evolutionary-robotics},
    volume = {22},
    year = {2016}
    }

2017

  • [DOI] K. Scheper, G. {de Croon}, and B. J. {Pijnacker Hordijk}, “Vertical landing for micro air vehicles using event-based optical flow,” Journal of field robotics, vol. 35, iss. 1, p. 69–90, 2017.
    [Bibtex]
    @article{a00fe842992c47199eb7c04cf26e211a,
    author = {Kirk Scheper and {de Croon}, Guido and {Pijnacker Hordijk}, B.J.},
    day = {15},
    doi = {10.1002/rob.21764},
    issn = {1556-4967},
    journal = {Journal of Field Robotics},
    keywords = {Aerial robotics, Bio-inspired methods, Optical flow, Perception, Sensors},
    language = {English},
    month = {December},
    number = {1},
    pages = {69--90},
    publisher = {Wiley},
    title = {Vertical Landing for Micro Air Vehicles using Event-Based Optical Flow},
    url = {https://research.tudelft.nl/en/publications/vertical-landing-for-micro-air-vehicles-using-event-based-optical},
    volume = {35},
    year = {2017}
    }
  • [DOI] K. Scheper and G. {de Croon}, “Abstraction, sensory-motor coordination, and the reality gap in evolutionary robotics,” Artificial life, vol. 23, iss. 2, p. 124–141, 2017.
    [Bibtex]
    @article{1d42dbaa10b44d63bd05b3cc966659e5,
    author = {Kirk Scheper and {de Croon}, Guido},
    day = {1},
    doi = {10.1162/ARTL_a_00227},
    issn = {1064-5462},
    journal = {Artificial Life},
    keywords = {Sensory-Motor Control, Evolutionary Robotics, Reality Gap, Micro Air Vehicle},
    language = {English},
    month = {June},
    number = {2},
    pages = {124--141},
    publisher = {MIT Press Journals},
    title = {Abstraction, Sensory-Motor Coordination, and the Reality Gap in Evolutionary Robotics},
    url = {https://research.tudelft.nl/en/publications/abstraction-sensory-motor-coordination-and-the-reality-gap-in-evo},
    volume = {23},
    year = {2017}
    }

2018

  • [DOI] K. Scheper, M. Karasek, C. {de Wagter}, B. Remes, and G. {de Croon}, “First autonomous multi-room exploration with an insect-inspired flapping wing vehicle,” in International conference on robotics and automation, United States, 2018, p. 5546 – 5552.
    [Bibtex]
    @inproceedings{cc073f0277f348a993652fbf4f64dacf,
    address = {United States},
    author = {Kirk Scheper and Matej Karasek and {de Wagter}, Christophe and Bart Remes and {de Croon}, Guido},
    booktitle = {International Conference on Robotics and Automation},
    doi = {10.1109/ICRA.2018.8460702},
    language = {English},
    note = {ICRA 2018: 2018 IEEE International Conference on Robotics and Automation ; Conference date: 21-05-2018 Through 25-05-2018},
    pages = {5546 -- 5552},
    publisher = {IEEE },
    title = {First autonomous multi-room exploration with an insect-inspired flapping wing vehicle},
    url = {https://research.tudelft.nl/en/publications/first-autonomous-multi-room-exploration-with-an-insect-inspired-f},
    year = {2018}
    }
  • [DOI] M. Coppola, {. N. }. McGuire, {. Y. W. }. Scheper, and {. C. H. E. }. {de Croon}, “On-board communication-based relative localization for collision avoidance in micro air vehicle teams,” Autonomous robots, vol. 42, iss. 8, p. 1787–1805, 2018.
    [Bibtex]
    @article{0ee50b7413ad4992a0e3219ab9403636,
    author = {Mario Coppola and McGuire, {Kimberly N.} and Scheper, {Kirk Y.W.} and {de Croon}, {Guido C.H.E.}},
    doi = {10.1007/s10514-018-9760-3},
    issn = {0929-5593},
    journal = {Autonomous Robots},
    keywords = {Autonomous flight, Collision avoidance, Indoor exploration, Micro Air Vehicles, Relative localization},
    language = {English},
    number = {8},
    pages = {1787–1805},
    publisher = {Springer Science+Business Media},
    title = {On-board communication-based relative localization for collision avoidance in Micro Air Vehicle teams},
    url = {https://research.tudelft.nl/en/publications/on-board-communication-based-relative-localization-for-collision-},
    volume = {42},
    year = {2018}
    }

2019

  • [DOI] K. Scheper, “Abstraction as a tool to bridge the reality gap in evolutionary robotics,” PhD Thesis, 2019.
    [Bibtex]
    @phdthesis{389f453ef7ff4feaa35332755cf9a9e1,
    author = {Kirk Scheper},
    day = {10},
    doi = {10.4233/uuid:389f453e-f7ff-4fea-a353-32755cf9a9e1},
    keywords = {Evolutionary Robotics, Reality Gap, Abstraction, Robust behavior, MAV},
    language = {English},
    month = {September},
    school = {Delft University of Technology},
    title = {Abstraction as a Tool to Bridge the Reality Gap in Evolutionary Robotics},
    url = {https://research.tudelft.nl/en/publications/abstraction-as-a-tool-to-bridge-the-reality-gap-in-evolutionary-r},
    year = {2019}
    }
  • [DOI] F. {Paredes Valles}, K. Scheper, and G. {de Croon}, “Unsupervised learning of a hierarchical spiking neural network for optical flow estimation: from events to global motion perception,” Ieee transactions on pattern analysis and machine intelligence, vol. 42 (2020), iss. 8, p. 2051–2064, 2019.
    [Bibtex]
    @article{160fcfa507614338ba72f8cf914add6a,
    author = {{Paredes Valles}, Fede and Kirk Scheper and {de Croon}, Guido},
    doi = {10.1109/TPAMI.2019.2903179},
    issn = {0162-8828},
    journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    keywords = {Event-based vision, Feature extraction, Motion detection, Neural nets, Neuromorphic computing, Unsupervised learning},
    language = {English},
    month = {March},
    number = {8},
    pages = {2051--2064},
    publisher = {IEEE },
    title = {Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception},
    url = {https://research.tudelft.nl/en/publications/unsupervised-learning-of-a-hierarchical-spiking-neural-network-fo},
    volume = {42 (2020)},
    year = {2019}
    }
  • D. Olejnik, M. Karasek, B. Duisterhof, K. Scheper, T. {van Dijk}, and G. {de Croon}, “A tailless flapping wing mav performing monocular visual servoing tasks,” in International micro air vehicle competition and conference, 2019, p. 60–66.
    [Bibtex]
    @inproceedings{9e60942988e14049bdf37a95c7464e5f,
    author = {Diana Olejnik and Matej Karasek and Bart Duisterhof and Kirk Scheper and {van Dijk}, Tom and {de Croon}, Guido},
    booktitle = {International Micro Air Vehicle Competition and Conference},
    editor = {P. Campoy},
    language = {English},
    note = {International Micro Air Vehicle Competition and Conference 2019, IMAV 2019 ; Conference date: 30-09-2019 Through 04-10-2019},
    pages = {60--66},
    title = {A Tailless Flapping Wing MAV Performing Monocular Visual Servoing Tasks},
    url = {https://research.tudelft.nl/en/publications/a-tailless-flapping-wing-mav-performing-monocular-visual-servoing-2},
    url2 = {http://www.imavs.org/2019/},
    year = {2019}
    }

2020

  • [DOI] {. Y. W. }. Scheper and G. {de Croon}, “Evolution of robust high speed optical-flow-based landing for autonomous mavs,” Robotics and autonomous systems, vol. 124, 2020.
    [Bibtex]
    @article{9a283c0ce100493190e8b39ed1bad552,
    author = {Scheper, {Kirk Y.W.} and {de Croon}, Guido},
    doi = {10.1016/j.robot.2019.103380},
    issn = {0921-8890},
    journal = {Robotics and Autonomous Systems},
    keywords = {Evolutionary robotics, Bio-inspired landing, Reality gap, High speed flight},
    language = {English},
    month = {February},
    publisher = {Elsevier},
    title = {Evolution of robust high speed optical-flow-based landing for autonomous MAVs},
    url = {https://research.tudelft.nl/en/publications/evolution-of-robust-high-speed-optical-flow-based-landing-for-aut},
    volume = {124},
    year = {2020}
    }
  • [DOI] {. A. }. Olejnik, {. P. }. Duisterhof, M. Karásek, {. Y. W. }. Scheper, T. {Van Dijk}, and {. C. H. E. }. {De Croon}, “A tailless flapping wing mav performing monocular visual servoing tasks,” Unmanned systems, vol. 8, iss. 4, p. 287–294, 2020.
    [Bibtex]
    @article{8c20c8bdc06f4e7b81bcbc4b52319049,
    author = {Olejnik, {Diana A.} and Duisterhof, {Bardienus P.} and Matej Kar{\'a}sek and Scheper, {Kirk Y.W.} and {Van Dijk}, Tom and {De Croon}, {Guido C.H.E.}},
    doi = {10.1142/S2301385020500235},
    issn = {2301-3850},
    journal = {Unmanned Systems},
    keywords = {flapping wings, MAV, visual servoing},
    language = {English},
    number = {4},
    pages = {287--294},
    publisher = {World Scientific Publishing},
    title = {A Tailless Flapping Wing MAV Performing Monocular Visual Servoing Tasks},
    url = {https://research.tudelft.nl/en/publications/a-tailless-flapping-wing-mav-performing-monocular-visual-servoing},
    volume = {8},
    year = {2020}
    }

 

Leave a Reply