[robotics-worldwide] Online datasets for long-term mapping by mobile robots

Tom Duckett tduckett at lincoln.ac.uk
Fri Mar 30 03:20:38 PDT 2012


ONLINE DATASETS FOR LONG-TERM MAPPING BY MOBILE ROBOTS

Persistent mapping in dynamic environments is one of the current outstanding challenges for mobile robotics research to enable long-term automomy. Experimental validation of algorithms for long-term mapping requires data collected over longer periods of time.

Several datasets for long-term mobile robot mapping and localisation in indoor environments are provided under an Open Data Commons Attribution License at the following URL: 

http://robotics.researchdata.lncn.eu/

(short URL: http://lncn.eu/ijvz )

The datasets consist of time-stamped multi-session robot sensor data, including
(1) greyscale omni-directional images, 2D laser scans and odometry data recorded at the University of Lincoln, UK over periods of up to 7 weeks, and (2) 2D laser scans and odometry data recorded at the University of Örebro, Sweden over a 5 week period, as reported in the following papers:

Feras Dayoub, Tom Duckett and Grzegorz Cielniak, Long-Term Experiments with an Adaptive Spherical View Representation for Navigation in Changing Environments, Robotics and Autonomous Systems, Vol. 59, No. 5, pp. 285-295, May 2011.

Peter Biber and Tom Duckett, Experimental Analysis of Sample-Based Maps for Long-Term SLAM, International Journal of Robotics Research, Vol. 28, No. 1, pp. 20-33, 2009.


--
Dr. Tom Duckett
Reader in Computer Science
University of Lincoln
Brayford Pool
Lincoln
LN6 7TS
Phone: +44 1522 837113
Fax: +44 1522 886974

The University of Lincoln - a top performer in student satisfaction, enjoying an unrivalled ascent through the University league tables, set in a dynamic, research rich and vibrant campus in the heart of a great historic student-friendly city.

The information in this e-mail and any attachments may be confidential. If you have received this email in error please notify the sender immediately and remove it from your system. Do not disclose the contents to another person or take copies.
 
Email is not secure and may contain viruses. The University of Lincoln makes every effort to ensure email is sent without viruses, but cannot guarantee this and recommends recipients take appropriate precautions.
 
The University may monitor email traffic data and content in accordance with its policies and English law. Further information can be found at: http://www.lincoln.ac.uk/legal.


More information about the robotics-worldwide mailing list