Progress on “Pico” Air Vehicles

Wood, Robert J.; Finio, Benjamin M.; Karpelson, Michael; Kevin, Y.; Pérez-Arancibia, Néstor O.; Sreetharan, Pratheev S.; Tanaka, Hiroto; Whitney, John P.

doi:10.1007/978-3-319-29363-9_1

Cited by 45 publications

(59 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Estos delicados robots biológicos son apenas del tamaño de un pulgar y mucho más finos, pudiendo confundirse perfectamente con un insecto cuando alzan el vuelo. (Kerpelson et al, 2009, Wood, 2012. Aquajelly es un robot suave submarino inspirados en una medusa capaz de realizar interacción multimodal y recargarse bajo el agua.…”

Section: Inspiración Biológica De Los Robots Suaveunclassified

Robótica suave: diseño y construcción

Márquez

Lau

Montejano

et al. 2019

ICBI

View full text Add to dashboard Cite

En los últimos años, las investigaciones del área de la mecatrónica están encaminadas al desarrollo de robots que ayuden al ser humano en sus actividades cotidianas. Actualmente los trabajos e investigaciones están orientados a los de robots blandos, suaves o softrobots, ya que permiten fácilmente interactuar y adaptarse a cualquier superficie. Los robots blandos tienen una estructura suave, deformables, flexibles, además son seguros comparados con los robots rígidos, sin embargo, son más difíciles de analizar la cinemático y la dinámico. En este artículo describe el estado del arte, clasificación y aplicaciones del robot suave, además se muestra a detalle el diseño y fabricación de un prototipo robot suave llamado pneunet, el diseño de estos es realizado mediante el paquete de software SolidWorks y el molde creando en una impresora 3D. El robot suave está diseñado de material suave y deformable, para que pueda tener sujeción y pueda moverse libremente por todo su espacio de trabajo sin dañar al usuario. El pneunet es construido para conocer el funcionamiento y las características morfológicas de los robots suaves.

show abstract

Section: Inspiración Biológica De Los Robots Suaveunclassified

Robótica suave: diseño y construcción

Márquez

Lau

Montejano

et al. 2019

ICBI

View full text Add to dashboard Cite

show abstract

“…To enable such ambitious scenarios many challenging problems must be addressed and solved. Nano-scale commercial off-the-shelf (COTS) quadrotors still lack a meaningful level of autonomy, contrary to their larger counterparts [9], [11], [12], since their tiny power envelopes and limited payload do not allow to host onboard adequate computing power Table I for four classes of vehicles), Wood et al [13] estimate that only up to 5% is available for onboard computation, and payloads of maximum ∼25% of the total mass can be allotted to the electronics. The traditional approach to autonomous navigation of a UAV is the so-called localization-mapping-planning cycle, which consists of estimating the robot motion using either off-board (e.g., GPS) or onboard sensors (e.g., visual-inertial sensors), building a local 3D map of the environment, and planning a safe trajectory through it [12].…”

Section: Introductionmentioning

confidence: 99%

An Open Source and Open Hardware Deep Learning-Powered Visual Navigation Engine for Autonomous Nano-UAVs

Palossi

Conti

Benini

2019

2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS)

View full text Add to dashboard Cite

Nano-size unmanned aerial vehicles (UAVs), with few centimeters of diameter and sub-10 Watts of total power budget, have so far been considered incapable of running sophisticated visual-based autonomous navigation software without external aid from base-stations, ad-hoc local positioning infrastructure, and powerful external computation servers. In this work, we present what is, to the best of our knowledge, the first 27 g nano-UAV system able to run aboard an end-to-end, closedloop visual pipeline for autonomous navigation based on a stateof-the-art deep-learning algorithm, built upon the open-source CrazyFlie 2.0 nano-quadrotor. Our visual navigation engine is enabled by the combination of an ultra-low power computing device (the GAP8 system-on-chip) with a novel methodology for the deployment of deep convolutional neural networks (CNNs). We enable onboard real-time execution of a state-of-the-art deep CNN at up to 18 Hz. Field experiments demonstrate that the system's high responsiveness prevents collisions with unexpected dynamic obstacles up to a flight speed of 1.5 m/s. In addition, we also demonstrate the capability of our visual navigation engine of fully autonomous indoor navigation on a 113 m previously unseen path. To share our key findings with the embedded and robotics communities and foster further developments in autonomous nano-UAVs, we publicly release all our code, datasets, and trained networks.

show abstract

“…[5]. As an arXiv:1805.01831v4 [cs.RO] 14 May 2019 [14] ∼ 2 : ≤ 0.001 ∼ 0.1 ULP example, in this IoT scenario, a relevant application for intelligent nano-size UAVs can be the online detection of wireless activity, from edge nodes deployed in the environment, via onboard radio packet sniffing [6]. Commercial off-the-shelf (COTS) quadrotors have already started to enter the nano-scale, featuring only few centimeters in diameter and a few tens of grams in weight [7].…”

mentioning

confidence: 99%

“…In Wood et al [14], the authors indicate that, for smallsize UAVs, the maximum power budget that can be spent for onboard computation is 5% of the total, the rest being used by the propellers (86%) and the low-level control parts (9%). The problem of bringing state-of-the-art navigation capabilities on the challenging classes of nano-and pico-size UAVs is therefore strictly dependent on the development of energy-efficient and computationally capable hardware, highly optimized software and new classes of algorithms combined into a next-generation navigation engine.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A 64-mW DNN-Based Visual Navigation Engine for Autonomous Nano-Drones

Palossi

Loquercio

Conti

et al. 2019

IEEE Internet Things J.

154

117

View full text Add to dashboard Cite

Fully-autonomous miniaturized robots (e.g., drones), with artificial intelligence (AI) based visual navigation capabilities, are extremely challenging drivers of Internet-of-Things edge intelligence capabilities. Visual navigation based on AI approaches, such as deep neural networks (DNNs) are becoming pervasive for standard-size drones, but are considered out of reach for nano-drones with a size of a few cm 2 . In this work, we present the first (to the best of our knowledge) demonstration of a navigation engine for autonomous nano-drones capable of closed-loop end-to-end DNN-based visual navigation. To achieve this goal we developed a complete methodology for parallel execution of complex DNNs directly on board resourceconstrained milliwatt-scale nodes. Our system is based on GAP8, a novel parallel ultra-low-power computing platform, and a 27 g commercial, open-source CrazyFlie 2.0 nano-quadrotor. As part of our general methodology, we discuss the software mapping techniques that enable the state-of-the-art deep convolutional neural network presented in [1] to be fully executed aboard within a strict 6 fps real-time constraint with no compromise in terms of flight results, while all processing is done with only 64 mW on average. Our navigation engine is flexible and can be used to span a wide performance range: at its peak performance corner, it achieves 18 fps while still consuming on average just 3.5% of the power envelope of the deployed nano-aircraft. To share our key findings with the embedded and robotics communities and foster further developments in autonomous nano-UAVs, we publicly release all our code, datasets, and trained networks.

show abstract

Progress on “Pico” Air Vehicles

Cited by 45 publications

References 36 publications

Robótica suave: diseño y construcción

Robótica suave: diseño y construcción

An Open Source and Open Hardware Deep Learning-Powered Visual Navigation Engine for Autonomous Nano-UAVs

A 64-mW DNN-Based Visual Navigation Engine for Autonomous Nano-Drones

Contact Info

Product

Resources

About