An intelligible implementation of FastSLAM2.0 on a low-power embedded architecture

Jiménez Serrata, Albert A.; Yang, Shufan; Li, Renfa

dc.contributor.author	Jiménez Serrata, Albert A.
dc.contributor.author	Yang, Shufan
dc.contributor.author	Li, Renfa
dc.date.accessioned	2017-03-07T12:14:33Z
dc.date.available	2017-03-07T12:14:33Z
dc.date.issued	2017-03-02
dc.identifier.citation	An intelligible implementation of FastSLAM2.0 on a low-power embedded architecture 2017, 2017 (1) EURASIP Journal on Embedded Systems
dc.identifier.issn	1687-3955
dc.identifier.doi	10.1186/s13639-017-0075-9
dc.identifier.uri	http://hdl.handle.net/2436/620402
dc.description.abstract	The simultaneous localisation and mapping (SLAM) algorithm has drawn increasing interests in autonomous robotic systems. However, SLAM has not been widely explored in embedded system design spaces yet due to the limitation of processing recourses in embedded systems. Especially when landmarks are not identifiable, the amount of computer processing will dramatically increase due to unknown data association. In this work, we propose an intelligible SLAM solution for an embedded processing platform to reduce computer processing time using a low-variance resampling technique. Our prototype includes a low-cost pixy camera, a Robot kit with L298N motor board and Raspberry Pi V2.0. Our prototype is able to recognise artificial landmarks in a real environment with an average 75% of identified landmarks in corner detection and corridor detection with only average 1.14 W.
dc.language.iso	en
dc.publisher	Springer
dc.relation.url	http://jes.eurasipjournals.springeropen.com/articles/10.1186/s13639-017-0075-9
dc.subject	Simultaneous localisation and mapping
dc.subject	Robotics
dc.subject	Embedded systems
dc.subject	Pixy camera
dc.title	An intelligible implementation of FastSLAM2.0 on a low-power embedded architecture
dc.type	Journal article
dc.identifier.journal	EURASIP Journal on Embedded Systems
dc.date.accepted	2017-02-09
rioxxterms.funder	University of Wolverhampton
rioxxterms.identifier.project	61672217
rioxxterms.version	VoR
rioxxterms.licenseref.uri	http://creativecommons.org/licenses/by/4.0/
rioxxterms.licenseref.startdate	2017-03-07
dc.source.volume	2017
dc.source.issue	1
dc.source.beginpage	27
refterms.dateFCD	2018-10-19T09:23:24Z
refterms.versionFCD	VoR
refterms.dateFOA	2017-03-07T00:00:00Z
html.description.abstract	The simultaneous localisation and mapping (SLAM) algorithm has drawn increasing interests in autonomous robotic systems. However, SLAM has not been widely explored in embedded system design spaces yet due to the limitation of processing recourses in embedded systems. Especially when landmarks are not identifiable, the amount of computer processing will dramatically increase due to unknown data association. In this work, we propose an intelligible SLAM solution for an embedded processing platform to reduce computer processing time using a low-variance resampling technique. Our prototype includes a low-cost pixy camera, a Robot kit with L298N motor board and Raspberry Pi V2.0. Our prototype is able to recognise artificial landmarks in a real environment with an average 75% of identified landmarks in corner detection and corridor detection with only average 1.14 W.