Evolving Spiking Networks for Turbulence-Tolerant Quadrotor Control

Howard, David; Elfes, Alberto

doi:10.7551/978-0-262-32621-6-ch071

Cited by 15 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Implementations of spiking flight neurocontrollers include [27], where the authors propose a SNN for robust control of a simulated quadrotor in challenging wind conditions. They achieve a better performance in waypoint holding experiments compared with a hand-tuned PID and a multilayer perceptron network.…”

Section: A Micro-airship Designmentioning

confidence: 99%

Evolved neuromorphic radar-based altitude controller for an autonomous open-source blimp

González-Álvarez¹,

Dupeyroux²,

Corradi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Robotic airships offer significant advantages in terms of safety, mobility, and extended flight times. However, their highly restrictive weight constraints pose a major challenge regarding the available computational power to perform the required control tasks. Spiking neural networks (SNNs) are a promising research direction for addressing this problem. By mimicking the biological process for transferring information between neurons using spikes or impulses, they allow for low power consumption and asynchronous event-driven processing. In this paper, we propose an evolved altitude controller based on a SNN for a robotic airship which relies solely on the sensory feedback provided by an airborne radar. Starting from the design of a lightweight, low-cost, open-source airship, we also present a SNN-based controller architecture, an evolutionary framework for training the network in a simulated environment, and a control scheme for ameliorating the gap with reality. The system's performance is evaluated through real-world experiments, demonstrating the advantages of our approach by comparing it with an artificial neural network and a linear controller. The results show an accurate tracking of the altitude command with an efficient control effort.

show abstract

Section: A Micro-airship Designmentioning

confidence: 99%

Evolved neuromorphic radar-based altitude controller for an autonomous open-source blimp

González-Álvarez¹,

Dupeyroux²,

Corradi³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…They were able to evolve good SNN controllers in a small number of generations in a wall-following scenario. Howard and Elfes ( 2014 ) presented a quadrotor neurocontroller that performed a hovering task in challenging wind conditions. With a feed-forward network taking the differences between current position and target position as input and pitch, roll and thrust as output, weights and topology were evolved to minimize the spatial error.…”

Section: Learning and Robotics Applicationsmentioning

confidence: 99%

A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks

et al. 2018

View full text Add to dashboard Cite

Biological intelligence processes information using impulses or spikes, which makes those living creatures able to perceive and act in the real world exceptionally well and outperform state-of-the-art robots in almost every aspect of life. To make up the deficit, emerging hardware technologies and software knowledge in the fields of neuroscience, electronics, and computer science have made it possible to design biologically realistic robots controlled by spiking neural networks (SNNs), inspired by the mechanism of brains. However, a comprehensive review on controlling robots based on SNNs is still missing. In this paper, we survey the developments of the past decade in the field of spiking neural networks for control tasks, with particular focus on the fast emerging robotics-related applications. We first highlight the primary impetuses of SNN-based robotics tasks in terms of speed, energy efficiency, and computation capabilities. We then classify those SNN-based robotic applications according to different learning rules and explicate those learning rules with their corresponding robotic applications. We also briefly present some existing platforms that offer an interaction between SNNs and robotics simulations for exploration and exploitation. Finally, we conclude our survey with a forecast of future challenges and some associated potential research topics in terms of controlling robots based on SNNs.

show abstract

“…Due to the potentially destructive nature of stochastically optimising controllers for ying robots, simulation is popular [4,6,19,27,28]. Simulation also allows evaluation to occur faster than realtime, however the faster the simulation is, the more abstracted the underlying model of reality tends to be.…”

Section: Er With Flying Robotsmentioning

confidence: 99%

“…Simulation (e.g. [19]) is a popular choice as it is parallelisable, and, depending on model complexity, may run many times faster than real-time. Simulation su ers from the 'reality gap' [22], whereby the necessarily-abstracted physical laws present in the simulation inaccurately represent real-world conditions, resulting in performance degredation when the former is transferred to the la er.…”

Section: Introductionmentioning

confidence: 99%

On Self-Adaptive Mutation Restarts for Evolutionary Robotics with Real Rotorcraft

Howard

2017

Preprint

View full text Add to dashboard Cite

Self-adaptive parameters are increasingly used in the eld of Evolutionary Robotics, as they allow key evolutionary rates to vary autonomously in a context-sensitive manner throughout the optimisation process. A signi cant limitation to self-adaptive mutation is that rates can be set unfavourably, which hinders convergence. Rate restarts are typically employed to remedy this, but thus far have only been applied in Evolutionary Robotics for mutation-only algorithms. is paper focuses on the level at which evolutionary rate restarts are applied in population-based algorithms with >1 evolutionary operator. A er testing on a real hexacopter hovering task, we conclude that individual-level restarting results in higher tness solutions without tness stagnation, and population restarts provide a more stable rate evolution. Without restarts, experiments can become stuck in suboptimal controller/rate combinations which can be di cult to escape from.

show abstract

Evolving Spiking Networks for Turbulence-Tolerant Quadrotor Control

Cited by 15 publications

References 21 publications

Evolved neuromorphic radar-based altitude controller for an autonomous open-source blimp

Evolved neuromorphic radar-based altitude controller for an autonomous open-source blimp

A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks

On Self-Adaptive Mutation Restarts for Evolutionary Robotics with Real Rotorcraft

Contact Info

Product

Resources

About