Within computer science, autonomous robotics takes the uneasy role of a discipline where the features of both systems (i.e., robots) and their operating environment (i.e., the physical world) conspire to make the application of the experimental scientific method most difficult. This is the reason why much experimental work in robotics is, from the methodological point of view, built on shaky grounds. In particular, scientifically sound benchmarking tools are still largely missing. This chapter starts from Rawseeds, a project focused precisely on benchmarking in robotics, to highlight the reasons for these difficulties and to propose strategies for overcoming some of them. The main result of Rawseeds is a Benchmarking Toolkit: a readily usable instrument to assess and compare algorithms for SLAM, localization, and mapping. Its most innovative aspects include a set of high-quality, validated, multi-sensor datasets, collected both in indoor and in outdoor locations and complemented by ground truth data, and the explicit definition of a set of quantitative performance metrics for the evaluation of algorithms.
Fontana, G., Matteucci, M., Sorrenti, D. (2014). Rawseeds: Building a Benchmarking Toolkit for Autonomous Robotics. In F. Amigoni, V. Schiaffonati (a cura di), Methods and Experimental Techniques in Computer Engineering (pp. 55-68). Springer Verlag [10.1007/978-3-319-00272-9_4].
Rawseeds: Building a Benchmarking Toolkit for Autonomous Robotics
SORRENTI, DOMENICO GIORGIOUltimo
2014
Abstract
Within computer science, autonomous robotics takes the uneasy role of a discipline where the features of both systems (i.e., robots) and their operating environment (i.e., the physical world) conspire to make the application of the experimental scientific method most difficult. This is the reason why much experimental work in robotics is, from the methodological point of view, built on shaky grounds. In particular, scientifically sound benchmarking tools are still largely missing. This chapter starts from Rawseeds, a project focused precisely on benchmarking in robotics, to highlight the reasons for these difficulties and to propose strategies for overcoming some of them. The main result of Rawseeds is a Benchmarking Toolkit: a readily usable instrument to assess and compare algorithms for SLAM, localization, and mapping. Its most innovative aspects include a set of high-quality, validated, multi-sensor datasets, collected both in indoor and in outdoor locations and complemented by ground truth data, and the explicit definition of a set of quantitative performance metrics for the evaluation of algorithms.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
