Special Issue on Robot Vision - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles The International Journal of Robotics Research Year : 2015

Special Issue on Robot Vision

Abstract

The International Journal of Robotics Research (IJRR) has a long history of publishing the state-of-the-art in the field of robotic vision. This is the fourth special issue devoted to the topic. Previous special issues were published in. In a closely related field was the special issue on Visual Servoing published in IJRR, 2003 (Volume 22, Nos 10–11). These issues nicely summarize the highlights and progress of the past 12 years of research devoted to the use of visual perception for robotics. Looking back across these issues we see perennial topics such as calibration; feature detection, description and matching; multi-view geometry; and filtering and prediction. Of course for robotic vision we have also seen many papers with a strong control focus and also a focus on high-speed operation. Perennial challenges over that period, perhaps still open problems, include robustness and vision-guided manipulation. Happily, many techniques have matured over this period and become an integral part of many robotic vision systems, for example visual odometry, visual Simultaneous Localization and Mapping (SLAM), visual place recognition and the fusion of vision with other sensors, most notably inertial sensors. This period has truly seen amazing technological change, not just the constant progress due to Moore's law but major innovations such as field-programmable gate arrays (FPGAs) and graphics processing units (GPUs), mobile computing architectures, low-cost high-performance inertial sensors and RGB-D sensors. Many of these have been driven by demand for consumer products such as smartphones and games, but have also provided a rich bounty for roboticists. The ready availability of capable low-cost off-the-shelf robotic platforms for domains such as underwater autonomous unmanned vehicles (AUVs), flying unmanned aerial vehicles (UAVs) and humanoid robots, all of which could usefully use vision sensors, is also helping to advance the field. Finally, the staple of all robotic vision systems, the camera, is evolving in very interesting directions. We now have cameras that are small, cheap and lightweight, that have progressive scan and global shutters, high dynamic range, high frame rate and wide fields of view obtained by catadioptrics or by multiple cameras with stitched imagery.
Fichier principal
Vignette du fichier
editorial-SI-ijrr.pdf (107.06 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01142837 , version 1 (16-04-2015)

Identifiers

Cite

Jana Košecká, Eric Marchand, Peter Corke. Special Issue on Robot Vision. The International Journal of Robotics Research, 2015, pp.399-401. ⟨10.1177/0278364915574960⟩. ⟨hal-01142837⟩
332 View
558 Download

Altmetric

Share

Gmail Facebook X LinkedIn More