Micro air vehicle autonomous obstacle avoidance from stereo-vision

Roland Brockers; Yoshiaki Kuwata; Stephan Weiss; Lawrence Matthies

doi:10.1117/12.2055288

3 June 2014 Micro air vehicle autonomous obstacle avoidance from stereo-vision

Roland Brockers, Yoshiaki Kuwata, Stephan Weiss, Lawrence Matthies

Proceedings Volume 9084, Unmanned Systems Technology XVI; 90840O (2014) https://doi.org/10.1117/12.2055288
Event: SPIE Defense + Security, 2014, Baltimore, MD, United States

Abstract

We introduce a new approach for on-board autonomous obstacle avoidance for micro air vehicles flying outdoors in close proximity to structure. Our approach uses inverse-range, polar-perspective stereo-disparity maps for obstacle detection and representation, and deploys a closed-loop RRT planner that considers flight dynamics for trajectory generation. While motion planning is executed in 3D space, we reduce collision checking to a fast z-buffer-like operation in disparity space, which allows for significant speed-up compared to full 3d methods. Evaluations in simulation illustrate the robustness of our approach, whereas real world flights under tree canopy demonstrate the potential of the approach.

Citation Download Citation

Roland Brockers, Yoshiaki Kuwata, Stephan Weiss, and Lawrence Matthies "Micro air vehicle autonomous obstacle avoidance from stereo-vision", Proc. SPIE 9084, Unmanned Systems Technology XVI, 90840O (3 June 2014); https://doi.org/10.1117/12.2055288

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