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

Hagenaars, Jesse; Paredes-Vallés, Federico; Bohté, Sander M.; Croon, Guido C. H. E. de

doi:10.1109/lra.2020.3012129

Cited by 18 publications

(42 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We focus on two approaches for training neuromorphic networks for control: evolutionary approaches and imitation learning. Genetic or evolutionary approaches have been commonly used to produce neuromorphic solutions to a variety of control tasks, including robotic control [2,28], drone control [21], video games [37], and engine control [45]. Imitation learning has also been popularly used for control of neuromorphic systems, especially for self-driving robots [17,22].…”

Section: Background and Related Workmentioning

confidence: 99%

Evolutionary vs imitation learning for neuromorphic control at the edge*

Schuman

Patton

Kulkarni

et al. 2022

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

Neuromorphic computing offers the opportunity to implement extremely low power artificial intelligence at the edge. Control applications, such as autonomous vehicles and robotics, are also of great interest for neuromorphic systems at the edge. It is not clear, however, what the best neuromorphic training approaches are for control applications at the edge. In this work, we implement and compare the performance of evolutionary optimization and imitation learning approaches on an autonomous race car control task using an edge neuromorphic implementation. We show that the evolutionary approaches tend to achieve better performing smaller network sizes that are well-suited to edge deployment, but they also take significantly longer to train. We also describe a workflow to allow for future algorithmic comparisons for neuromorphic hardware on control applications at the edge.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Evolutionary vs imitation learning for neuromorphic control at the edge*

Schuman

Patton

Kulkarni

et al. 2022

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

show abstract

“…In the last years event-based vision has attracted increasing research interest in the robotics and computer vision communities [3]. Most of the existing works have focused on the development of event-based methods for well known fundamental problems such as feature detection and tracking [4], optical flow estimation [5], depth estimation [6], robot localisation [7], motion and object segmentation [8], object detection [9], feedback control [10], and visual servoing [11], among others.…”

Section: Related Workmentioning

confidence: 99%

UAV human teleoperation using event-based and frame-based cameras

Tapia

Eguíluz

Dios

et al. 2021

2021 Aerial Robotic Systems Physically Interacting With the Environment (AIRPHARO)

View full text Add to dashboard Cite

Teleoperation is a crucial aspect for human-robot interaction with unmanned aerial vehicles (UAVs) applications. Fast perception processing is required to ensure robustness, precision, and safety. Event cameras are neuromorphic sensors that provide low latency response, high dynamic range and low power consumption. Although classical image-based methods have been extensively used for human-robot interaction tasks, responsiveness is limited by their processing rates. This paper presents a human-robot teleoperation scheme for UAVs that exploits the advantages of both traditional and event cameras. The proposed scheme was tested in teleoperation missions where the pose of a multirotor robot is controlled in real time using human gestures detected from events.

show abstract

“…The scope of works that have implemented SNN controllers for MAVs in real scenarios is much more limited. The first work that integrates a SNN in the closed-loop control of a real-world flying robot is very recent [30]. There, the authors present a SNN for controlling the landing of a quadrotor by exploiting the optical flow divergence from a downward-looking camera and the readings of an inertial measurement unit (IMU).…”

Section: A Micro-airship Designmentioning

confidence: 99%

“…Our work aims to extend the framework proposed in [30], by (1) controlling the altitude instead of landing; (2) considering an open-source micro blimp, which has less control authority and harder to model dynamics than a quadrotor; and (3) exploiting solely the range measurements provided by a radar, reducing the number of required sensors on-board (i.e., no IMU).…”

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

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

Cited by 18 publications

References 34 publications

Evolutionary vs imitation learning for neuromorphic control at the edge*

Evolutionary vs imitation learning for neuromorphic control at the edge*

UAV human teleoperation using event-based and frame-based cameras

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

Contact Info

Product

Resources

About