Publications

@article{sr_vr,

title = {Visual Route-following for Tiny Autonomous Robots},

author = {Tom van Dijk and Christophe De Wagter and Guido C.H.E. de Croon},

url = {https://www.science.org/doi/abs/10.1126/scirobotics.adk0310},

doi = {10.1126/scirobotics.adk0310},

issn = {2470-9476},

year  = {2024},

date = {2024-07-17},

urldate = {2024-07-17},

journal = {Science Robotics},

volume = {9},

number = {92},

pages = {eadk0310},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{izzo_sr,

title = {Optimality principles in spacecraft neural guidance and control},

author = {Dario Izzo and Emmanuel Blazquez and Robin Ferede and Sebastien Origer and Christophe De Wagter and Guido C. H. E. de Croon},

doi = {10.1126/scirobotics.adi6421},

issn = {2470-9476},

year  = {2024},

date = {2024-06-19},

urldate = {2024-06-19},

journal = {Science Robotics},

volume = {9},

number = {91},

issue = {91},

pages = {eadi6421},

abstract = {This Review discusses the main results obtained in training end-to-end neural architectures for guidance and control of interplanetary transfers, planetary landings, and close-proximity operations, highlighting the successful learning of optimality principles by the underlying neural models. Spacecraft and drones aimed at exploring our solar system are designed to operate in conditions where the smart use of onboard resources is vital to the success or failure of the mission. Sensorimotor actions are thus often derived from high-level, quantifiable, optimality principles assigned to each task, using consolidated tools in optimal control theory. The planned actions are derived on the ground and transferred on board, where controllers have the task of tracking the uploaded guidance profile. Here, we review recent trends based on the use of end-to-end networks, called guidance and control networks (G&CNets), which allow spacecraft to depart from such an architecture and to embrace the onboard computation of optimal actions. In this way, the sensor information is transformed in real time into optimal plans, thus increasing mission autonomy and robustness. We then analyze drone racing as an ideal gym environment to test these architectures on real robotic platforms and thus increase confidence in their use in future space exploration missions. Drone racing not only shares with spacecraft missions both limited onboard computational capabilities and similar control structures induced from the optimality principle sought but also entails different levels of uncertainties and unmodeled effects and a very different dynamical timescale. Onboard optimal guidance and control could be entirely neural based in future space missions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{4f72ee48af594442976869c1133ef133,

title = {ALBERO: Agile Landing on Branches for Environmental Robotics Operations},

author = {Liming Zheng and Salua Hamaza},

url = {https://research.tudelft.nl/en/publications/albero-agile-landing-on-branches-for-environmental-robotics-opera},

doi = {10.1109/LRA.2024.3349914},

issn = {2377-3766},

year  = {2024},

date = {2024-01-01},

journal = {IEEE Robotics and Automation Letters},

volume = {9},

number = {3},

pages = {2845–2852},

publisher = {Institute of Electrical and Electronics Engineers (IEEE)},

note = {Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{<LineBreak>doi:10.1126/scirobotics.adi0591,

title = {Fully neuromorphic vision and control for autonomous drone flight},

author = {F. Paredes-Vallés and J. J. Hagenaars and J. Dupeyroux and S. Stroobants and Y. Xu and G. C. H. E. Croon},

url = {https://www.science.org/doi/abs/10.1126/scirobotics.adi0591},

doi = {10.1126/scirobotics.adi0591},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Science Robotics},

volume = {9},

number = {90},

pages = {eadi0591},

abstract = {Biological sensing and processing is asynchronous and sparse, leading to low-latency and energy-efficient perception and action. In robotics, neuromorphic hardware for event-based vision and spiking neural networks promises to exhibit similar characteristics. However, robotic implementations have been limited to basic tasks with low-dimensional sensory inputs and motor actions because of the restricted network size in current embedded neuromorphic processors and the difficulties of training spiking neural networks. Here, we present a fully neuromorphic vision-to-control pipeline for controlling a flying drone. Specifically, we trained a spiking neural network that accepts raw event-based camera data and outputs low-level control actions for performing autonomous vision-based flight. The vision part of the network, consisting of five layers and 28,800 neurons, maps incoming raw events to ego-motion estimates and was trained with self-supervised learning on real event data. The control part consists of a single decoding layer and was learned with an evolutionary algorithm in a drone simulator. Robotic experiments show a successful sim-to-real transfer of the fully learned neuromorphic pipeline. The drone could accurately control its ego-motion, allowing for hovering, landing, and maneuvering sideways—even while yawing at the same time. The neuromorphic pipeline runs on board on Intel’s Loihi neuromorphic processor with an execution frequency of 200 hertz, consuming 0.94 watt of idle power and a mere additional 7 to 12 milliwatts when running the network. These results illustrate the potential of neuromorphic sensing and processing for enabling insect-sized intelligent robots. A fully neuromorphic vision-to-control pipeline enables fast and energy-efficient ego-motion control of a flying drone. Despite the ability of visual processing enabled by artificial neural networks, the associated hardware and large power consumption limit deployment on small flying drones. Neuromorphic hardware offers a promising alternative, but the accompanying spiking neural networks are difficult to train, and the current hardware only supports a limited number of neurons. Paredes-Vallés et al. now present a neuromorphic pipeline to control drone flight. They trained a five-layer spiking neural network to process the raw inputs from an event camera. The network first estimated ego-motion and subsequently determined low-level control commands. Real-world experiments demonstrated that the drone could control its ego-motion to land, hover, and maneuver sideways, with minimal power consumption. —Melisa Yashinski},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{de8ac946100443458e17cbd79b635dbb,

title = {Optical flow-based control for micro air vehicles: an efficient data-driven incremental nonlinear dynamic inversion approach},

author = {Hann Woei Ho and Ye Zhou and Yiting Feng and Guido C. H. E. Croon},

url = {https://research.tudelft.nl/en/publications/optical-flow-based-control-for-micro-air-vehicles-an-efficient-da},

doi = {10.1007/s10514-024-10174-4},

issn = {0929-5593},

year  = {2024},

date = {2024-01-01},

journal = {Autonomous Robots},

volume = {48},

number = {8},

publisher = {Springer},

note = {Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{6f5b1c4a51c9425fa5f6453b926bf8c4,

title = {Deep Reinforcement Learning With Dynamic Graphs for Adaptive Informative Path Planning},

author = {Apoorva Vashisth and Julius Ruckin and Federico Magistri and Cyrill Stachniss and Marija Popovic},

url = {https://research.tudelft.nl/en/publications/deep-reinforcement-learning-with-dynamic-graphs-for-adaptive-info},

doi = {10.1109/LRA.2024.3421188},

issn = {2377-3766},

year  = {2024},

date = {2024-01-01},

journal = {IEEE Robotics and Automation Letters},

volume = {9},

number = {9},

pages = {7747–7754},

publisher = {IEEE},

note = {Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{0e519d5771bb43beae6e808559be46fa,

title = {Visual route following for tiny autonomous robots},

author = {Tom Dijk and Christophe De Wagter and Guido C. H. E. Croon},

url = {https://research.tudelft.nl/en/publications/visual-route-following-for-tiny-autonomous-robots},

doi = {10.1126/scirobotics.adk0310},

issn = {2470-9476},

year  = {2024},

date = {2024-01-01},

journal = {Science Robotics},

volume = {9},

number = {92},

pages = {eadk0310},

publisher = {American Association for the Advancement of Science},

note = {Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{e6b721abd0284a90a9aedb90bd9a7da0,

title = {Optimality principles in spacecraft neural guidance and control},

author = {Dario Izzo and Emmanuel Blazquez and Robin Ferede and Sebastien Origer and Christophe De Wagter and Guido C. H. E. Croon},

url = {https://research.tudelft.nl/en/publications/optimality-principles-in-spacecraft-neural-guidance-and-control},

doi = {10.1126/scirobotics.adi6421},

issn = {2470-9476},

year  = {2024},

date = {2024-01-01},

journal = {Science Robotics},

volume = {9},

number = {91},

publisher = {American Association for the Advancement of Science},

note = {Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{cc309432ce7b43009e0742f2afc3b9b3,

title = {Editorial: Special Issue on Advancing Micro Air Vehicle Technologies: Selected Papers from IMAV 2022},

author = {G. C. H. E. Croon and C. De Wagter},

url = {https://research.tudelft.nl/en/publications/editorial-special-issue-on-advancing-micro-air-vehicle-technologi},

doi = {10.1142/S2301385024020035},

issn = {2301-3850},

year  = {2024},

date = {2024-01-01},

journal = {Unmanned Systems},

volume = {12},

number = {3},

pages = {563–564},

publisher = {World Scientific Publishing},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{b4c869ece0b34c1c863cad462c79f190,

title = {Improving the Computational Efficiency of ROVIO},

author = {S. A. Bahnam and C. De Wagter and G. C. H. E. De Croon},

url = {https://research.tudelft.nl/en/publications/improving-the-computational-efficiency-of-rovio-2},

doi = {10.1142/S2301385024410012},

issn = {2301-3850},

year  = {2024},

date = {2024-01-01},

journal = {Unmanned Systems},

volume = {12},

number = {3},

pages = {589–598},

publisher = {World Scientific Publishing},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{5ab41ef5d22d4c92b58b0e0673ac9097,

title = {A Morphing Quadrotor-Blimp with Balloon Failure Resilience for Mobile Ecological Sensing},

author = {Suryansh Sharma and Mike Verhoeff and Floor Joosen and RR Venkatesha Prasad and Salua Hamaza},

url = {https://research.tudelft.nl/en/publications/a-morphing-quadrotor-blimp-with-balloon-failure-resilience-for-mo},

doi = {10.1109/LRA.2024.3406061},

issn = {2377-3766},

year  = {2024},

date = {2024-01-01},

journal = {IEEE Robotics and Automation Letters},

volume = {9},

number = {7},

pages = {6408–6415},

publisher = {IEEE},

note = {Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{6cbe83a31f8648b0b47888e71f807546,

title = {Fully neuromorphic vision and control for autonomous drone flight},

author = {F. Paredes-Vallés and J. J. Hagenaars and J. Dupeyroux and S. Stroobants and Y. Xu and G. C. H. E. Croon},

url = {https://research.tudelft.nl/en/publications/fully-neuromorphic-vision-and-control-for-autonomous-drone-flight},

doi = {10.1126/scirobotics.adi0591},

issn = {2470-9476},

year  = {2024},

date = {2024-01-01},

journal = {Science Robotics},

volume = {9},

number = {90},

publisher = {American Association for the Advancement of Science},

note = {Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{16169a19bf6b46818ecc18a9f2bd5e0f,

title = {End-to-end neural network based optimal quadcopter control},

author = {Robin Ferede and Guido Croon and Christophe De Wagter and Dario Izzo},

url = {https://research.tudelft.nl/en/publications/end-to-end-neural-network-based-optimal-quadcopter-control},

doi = {10.1016/j.robot.2023.104588},

issn = {0921-8890},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Robotics and Autonomous Systems},

volume = {172},

publisher = {Elsevier},

note = {Funding Information: This work was supported by the European Space Agency.This research was co-funded under the Discovery programme of, and funded by, the European Space Agency. Funding Information: This work was supported by the European Space Agency . Publisher Copyright: © 2023 The Authors},

keywords = {},

pubstate = {published},

tppubtype = {article}

}