Share Email Print
cover

Proceedings Paper

Vision-based fast navigation of micro aerial vehicles
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 25 May 2016
PDF: 14 pages
Proc. SPIE 9836, Micro- and Nanotechnology Sensors, Systems, and Applications VIII, 98361T (25 May 2016); doi: 10.1117/12.2224520
Show Author Affiliations
Giuseppe Loianno, Univ. of Pennsylvania (United States)
Vijay Kumar, Univ. of Pennsylvania (United States)


Published in SPIE Proceedings Vol. 9836:
Micro- and Nanotechnology Sensors, Systems, and Applications VIII
Thomas George; Achyut K. Dutta; M. Saif Islam, Editor(s)

© SPIE. Terms of Use
Back to Top