Towards Optical Flow-based Robotic Homing
Towards Optical Flow-based Robotic Homing
This paper presents a novel biologically-inspired approach for tackling the problem of robot homing. In our method the only information employed is optical flow. Optical flow, which is not a property of landmarks like colour, shape, and size but a property of the camera motion, is used for localising an autonomous robot in a priori unknown environment. Our method exploits the optical flow ‘fingerprint’ of landmarks caused by the motion of the robot in the environment. For this purpose, we have developed a training algorithm that estimates the probability of observing the same landmark from varying distances and velocities. Our method promises to be computationally efficient and inexpensive. The simulation results we present show the validity of our methods.
Diamantas, Sotirios
569b0bb8-9d90-447c-8a23-16d38f29444f
Oikonomidis, Anastasios
876dbe2e-cc0e-4620-a72b-2b44ccf32a07
Crowder, Richard
ddeb646d-cc9e-487b-bd84-e1726d3ac023
Diamantas, Sotirios
569b0bb8-9d90-447c-8a23-16d38f29444f
Oikonomidis, Anastasios
876dbe2e-cc0e-4620-a72b-2b44ccf32a07
Crowder, Richard
ddeb646d-cc9e-487b-bd84-e1726d3ac023
Diamantas, Sotirios, Oikonomidis, Anastasios and Crowder, Richard
(2010)
Towards Optical Flow-based Robotic Homing.
International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Barcelona, Spain.
(Submitted)
Record type:
Conference or Workshop Item
(Other)
Abstract
This paper presents a novel biologically-inspired approach for tackling the problem of robot homing. In our method the only information employed is optical flow. Optical flow, which is not a property of landmarks like colour, shape, and size but a property of the camera motion, is used for localising an autonomous robot in a priori unknown environment. Our method exploits the optical flow ‘fingerprint’ of landmarks caused by the motion of the robot in the environment. For this purpose, we have developed a training algorithm that estimates the probability of observing the same landmark from varying distances and velocities. Our method promises to be computationally efficient and inexpensive. The simulation results we present show the validity of our methods.
Text
IEEEWCCI2010_IJCNN2010_finalPaper.pdf
- Other
More information
Submitted date: 18 July 2010
Additional Information:
Event Dates: July, 2010
Venue - Dates:
International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Barcelona, Spain, 2010-07-01
Organisations:
Agents, Interactions & Complexity
Identifiers
Local EPrints ID: 268755
URI: http://eprints.soton.ac.uk/id/eprint/268755
PURE UUID: 19048d2d-f8e4-4c12-be93-8c315cbbeffc
Catalogue record
Date deposited: 18 Mar 2010 15:31
Last modified: 14 Mar 2024 09:14
Export record
Contributors
Author:
Sotirios Diamantas
Author:
Anastasios Oikonomidis
Author:
Richard Crowder
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics