IROS 2015 Paper Abstract


Paper WeDT3.5

Ho, Hann Woei (Delft University of Technology, Universiti Sains Malaysia), De Wagter, Christophe (Delft University of Technology), Remes, Bart (Delft University of Technology), de Croon, Guido (TU Delft / ESA)

Optical Flow for Self-Supervised Learning of Obstacle Appearance

Scheduled for presentation during the Regular session "Visual Navigation 1" (WeDT3), Wednesday, September 30, 2015, 15:00−15:15, Saal E

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sept 28 - Oct 03, 2015, Congress Center Hamburg, Hamburg, Germany

This information is tentative and subject to change. Compiled on March 3, 2021

Keywords Visual Navigation, Unmanned Aerial Systems, Visual Learning


We introduce a novel setup of self-supervised learning (SSL), in which optical flow provides the supervised outputs. Optical flow requires significant movement for obstacle detection. The main advantage of the introduced method is that after learning, a robot can detect obstacles without moving - reducing the risk of collisions in narrow spaces. We investigate this novel setup of SSL in the context of a Micro Air Vehicle (MAV) that needs to select a suitable landing place. Initially, when the MAV flies over a potential landing area, the optical flow processing estimates a `surface roughness' measure, capturing whether there are obstacles sticking out of the landing surface. This measure allows the MAV to select a safe landing place and then land with other optical flow measures such as the divergence. During flight, SSL takes place. For each image a texton distribution is extracted (capturing the visual appearance of the landing surface in sight), and mapped to the current roughness value by a linear regression function. We first demonstrate this principle to work with offline tests involving images captured on board an MAV, and then demonstrate the principle in flight. The experiments show that the MAV can land safely on the basis of optical flow. After learning it can also successfully select safe landing spots in hover. It is even shown that the appearance learning allows the pixel-wise segmentation of obstacles.



Technical Content © IEEE Robotics & Automation Society

This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2021 PaperCept, Inc.
Page generated 2021-03-03  09:10:52 PST  Terms of use