Cargando…

Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera

Recent advances have shown for the first time that it is possible to beat a human with an autonomous drone in a drone race. However, this solution relies heavily on external sensors, specifically on the use of a motion capture system. Thus, a truly autonomous solution demands performing computationa...

Descripción completa

Detalles Bibliográficos
Autores principales: Rojas-Perez, Leticia Oyuki, Martinez-Carranza, Jose
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8620925/
https://www.ncbi.nlm.nih.gov/pubmed/34833511
http://dx.doi.org/10.3390/s21227436
_version_ 1784605334508142592
author Rojas-Perez, Leticia Oyuki
Martinez-Carranza, Jose
author_facet Rojas-Perez, Leticia Oyuki
Martinez-Carranza, Jose
author_sort Rojas-Perez, Leticia Oyuki
collection PubMed
description Recent advances have shown for the first time that it is possible to beat a human with an autonomous drone in a drone race. However, this solution relies heavily on external sensors, specifically on the use of a motion capture system. Thus, a truly autonomous solution demands performing computationally intensive tasks such as gate detection, drone localisation, and state estimation. To this end, other solutions rely on specialised hardware such as graphics processing units (GPUs) whose onboard hardware versions are not as powerful as those available for desktop and server computers. An alternative is to combine specialised hardware with smart sensors capable of processing specific tasks on the chip, alleviating the need for the onboard processor to perform these computations. Motivated by this, we present the initial results of adapting a novel smart camera, known as the OpenCV AI Kit or OAK-D, as part of a solution for the ADR running entirely on board. This smart camera performs neural inference on the chip that does not use a GPU. It can also perform depth estimation with a stereo rig and run neural network models using images from a 4K colour camera as the input. Additionally, seeking to limit the payload to 200 g, we present a new 3D-printed design of the camera’s back case, reducing the original weight 40%, thus enabling the drone to carry it in tandem with a host onboard computer, the Intel Stick compute, where we run a controller based on gate detection. The latter is performed with a neural model running on an OAK-D at an operation frequency of 40 Hz, enabling the drone to fly at a speed of 2 m/s. We deem these initial results promising toward the development of a truly autonomous solution that will run intensive computational tasks fully on board.
format Online
Article
Text
id pubmed-8620925
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86209252021-11-27 Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera Rojas-Perez, Leticia Oyuki Martinez-Carranza, Jose Sensors (Basel) Article Recent advances have shown for the first time that it is possible to beat a human with an autonomous drone in a drone race. However, this solution relies heavily on external sensors, specifically on the use of a motion capture system. Thus, a truly autonomous solution demands performing computationally intensive tasks such as gate detection, drone localisation, and state estimation. To this end, other solutions rely on specialised hardware such as graphics processing units (GPUs) whose onboard hardware versions are not as powerful as those available for desktop and server computers. An alternative is to combine specialised hardware with smart sensors capable of processing specific tasks on the chip, alleviating the need for the onboard processor to perform these computations. Motivated by this, we present the initial results of adapting a novel smart camera, known as the OpenCV AI Kit or OAK-D, as part of a solution for the ADR running entirely on board. This smart camera performs neural inference on the chip that does not use a GPU. It can also perform depth estimation with a stereo rig and run neural network models using images from a 4K colour camera as the input. Additionally, seeking to limit the payload to 200 g, we present a new 3D-printed design of the camera’s back case, reducing the original weight 40%, thus enabling the drone to carry it in tandem with a host onboard computer, the Intel Stick compute, where we run a controller based on gate detection. The latter is performed with a neural model running on an OAK-D at an operation frequency of 40 Hz, enabling the drone to fly at a speed of 2 m/s. We deem these initial results promising toward the development of a truly autonomous solution that will run intensive computational tasks fully on board. MDPI 2021-11-09 /pmc/articles/PMC8620925/ /pubmed/34833511 http://dx.doi.org/10.3390/s21227436 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Rojas-Perez, Leticia Oyuki
Martinez-Carranza, Jose
Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera
title Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera
title_full Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera
title_fullStr Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera
title_full_unstemmed Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera
title_short Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera
title_sort towards autonomous drone racing without gpu using an oak-d smart camera
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8620925/
https://www.ncbi.nlm.nih.gov/pubmed/34833511
http://dx.doi.org/10.3390/s21227436
work_keys_str_mv AT rojasperezleticiaoyuki towardsautonomousdroneracingwithoutgpuusinganoakdsmartcamera
AT martinezcarranzajose towardsautonomousdroneracingwithoutgpuusinganoakdsmartcamera