Evolved Neuromorphic Control for High Speed Divergence-based Landings of MAVs

Evolved Neuromorphic Control for High Speed Divergence-based Landings of MAVs

Hagenaars, Jesse (TU Delft Aerospace Engineering)

de Croon, G.C.H.E. (mentor)
Paredes-Vallés, F. (mentor)

Delft University of Technology

Aerospace Engineering

2020-02-13

Flying insects are capable of autonomous vision-based navigation in cluttered environments, reliably avoiding objects through fast and agile manoeuvres. Meanwhile, insect-scale micro air vehicles still lag far behind their biological counterparts, displaying inferior performance at a fraction of the energy efficiency. In light of this, it is in our interest to try and mimic flying insects in terms of their vision-based navigation capabilities, and consequently apply gained knowledge to a manoeuvre of relevance. This thesis does so through evolving spiking neural networks for controlling divergence-based landings of micro air vehicles, while minimising the network's spike rate. We demonstrate vision-based neuromorphic control for a real-world, continuous problem, as well as the feasibility of extending this controller to one that is end-to-end-learnt, and can work with an event-based camera. Furthermore, we provide insight into the resources required for successfully solving the problem of divergence-based landing, showing that high-resolution control can be learnt with only a single spiking neuron. Finally, we look at evolving only a subset of the spiking neural network's available hyperparameters, suggesting that the best results are obtained when all parameters are affected by the learning process.

spiking neural networks
optical flow
micro air vehicles
neuroevolution

http://resolver.tudelft.nl/uuid:48040e88-f507-4676-a5da-2b701a07f387

2021-02-13

Student theses

master thesis

© 2020 Jesse Hagenaars