Vision-based fast navigation of micro aerial vehicles

Giuseppe Loianno; Vijay Kumar

doi:10.1117/12.2224520

25 May 2016 Vision-based fast navigation of micro aerial vehicles

Giuseppe Loianno, Vijay Kumar

Proceedings Volume 9836, Micro- and Nanotechnology Sensors, Systems, and Applications VIII; 98361T (2016) https://doi.org/10.1117/12.2224520
Event: SPIE Defense + Security, 2016, Baltimore, MD, United States

Abstract

We address the key challenges for autonomous fast flight for Micro Aerial Vehicles (MAVs) in 3-D, cluttered environments. For complete autonomy, the system must identify the vehicle's state at high rates, using either absolute or relative asynchronous on-board sensor measurements, use these state estimates for feedback control, and plan trajectories to the destination. State estimation requires information from different sensors to be fused, exploiting information from different, possible asynchronous sensors at different rates. In this work, we present techniques in the area of planning, control and visual-inertial state estimation for fast navigation of MAVs. We demonstrate how to solve on-board, on a small computational unit, the pose estimation, control and planning problems for MAVs, using a minimal sensor suite for autonomous navigation composed of a single camera and IMU. Additionally, we show that a consumer electronic device such as a smartphone can alternatively be employed for both sensing and computation. Experimental results validate the proposed techniques. Any consumer, provided with a smartphone, can autonomously drive a quadrotor platform at high speed, without GPS, and concurrently build 3-D maps, using a suitably designed app.

Citation Download Citation

Giuseppe Loianno and Vijay Kumar "Vision-based fast navigation of micro aerial vehicles", Proc. SPIE 9836, Micro- and Nanotechnology Sensors, Systems, and Applications VIII, 98361T (25 May 2016); https://doi.org/10.1117/12.2224520

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available