Print Email Facebook Twitter Fully neuromorphic vision and control for autonomous drone flight Title Fully neuromorphic vision and control for autonomous drone flight Author Paredes-Vallés, Federico (TU Delft Control & Simulation) Hagenaars, J.J. (TU Delft Control & Simulation) Dupeyroux, J.J.G. (TU Delft Control & Simulation) Stroobants, S. (TU Delft Control & Simulation) Xu, Y. (TU Delft Control & Simulation) de Croon, G.C.H.E. (TU Delft Control & Simulation) Date 2024 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. To reference this document use: http://resolver.tudelft.nl/uuid:6cbe83a3-1f86-48b0-b478-88e71f807546 DOI https://doi.org/10.1126/scirobotics.adi0591 Embargo date 2024-11-15 ISSN 2470-9476 Source Science Robotics, 9 (90) Bibliographical 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. Part of collection Institutional Repository Document type journal article Rights © 2024 Federico Paredes-Vallés, J.J. Hagenaars, J.J.G. Dupeyroux, S. Stroobants, Y. Xu, G.C.H.E. de Croon Files file embargo until 2024-11-15