REMINDER: As we approach the end of the year, please see below for details of our Special Issue on Active Vision and Perception in Human-Robot Collaboration in Frontiers in Neurorobotics, with a deadline of December 31st 2020. If you are doing work in active vision, in humans or machines, please consider submitting experimental or review papers. Any questions? Just get in touch!
CFP – Special Issue in Neurorobotics - Active Vision and Perception in Human-Robot Collaboration Link: https://www.frontiersin.org/research-topics/13958/active-vision-and-perception-in-human-robot-collaboration --------------------------------------------------------------------------------------------------- Scope: Humans naturally interact and collaborate in unstructured social environments that produce an overwhelming amount of information and may yet hide behaviourally relevant variables. Uncovering the underlying design principles that allow humans to adaptively find and select relevant information, e.g. effectors, affordances, etc, is important for Robotics, but also other fields, such as Computational Neuroscience and Interaction Design. Current solutions cover specific tasks, e.g. autonomous cars, and usually employ over-redundant, expensive, and computationally demanding sensory systems that attempt to cover the wide set of sensing conditions which the systems may have to deal with. Adaptive control of the sensors and of the perception process is a key solution found by nature to cope with such problems, as shown by the foveal anatomy of the eye and its high mobility. Alongside this interest in “active” vision, collaborative robotics has recently progressed to human-robot interaction in real manufacturing. Measuring and modelling task-specific gaze behaviours seems to be essential for smooth human-robot interaction. Indeed, anticipatory control for human-in-the-loop architectures, which can enable robots to proactively collaborate with humans, relies heavily on observing gaze and actions patterns of the human partner. We are interested in manuscripts that present novel computational and robotic models, theories and experimental results as well as reviews relevant to understand how human actively control their perception during social interaction and in which condition they fail, and how these insights may enable natural interaction between humans and artificial systems in non-trivial conditions. Topics: topics of interest include (but are not limited to): * Active perception for intention and action prediction * Activity and action recognition in the wild * Active perception for social interaction * Human-robot collaboration in unstructured environments * Human-robot collaboration in presence of sensory limits * Joint Human-Robot search and exploration * Testing setup for social perception in real or virtual environments * Setup for transferring active perception skills from humans to robots * Machine learning methods for active social perception * Benchmarking and quantitative evaluation with human subject experiments * Gaze-based Factors for Intuitive Human-Robot Collaboration * Active perception modelling for social interaction and collaboration * Head-mounted eye tracking and gaze estimation during social interaction * Estimation and guidance of partner situation awareness and attentional state in human-robot collaboration * Multimodal Social perception * Adaptive social perception * Egocentric vision in social interaction; * Explicit and implicit sensorimotor communication; * Social attention; * Natural human-robot (machine) interaction; * Collaborative exploration; * Joint attention; * Multimodal social attention; * Attentive activity recognition; * Belief and mental state attribution in robots Keywords: Active Vision, Social Perception, Intention Prediction, Egocentric Vision, Natural Human-Robot Interaction --------------------------------------------------------------------------------------------------- Important Dates: Full Paper Submission Deadline: 31/12/2020 Following the general publication policy of the journal, as soon as papers are accepted for publication, they will be published shortly thereafter and available to online independently on the submission deadlines. --------------------------------------------------------------------------------------------------- Topic Editors: Dimitri Ognibene , University of Essex & Milano Bicocca University: dimitri.ognib...@essex.ac.uk<mailto:dimitri.ognib...@essex.ac.uk> Tom Foulsham, University of Essex : fouls...@essex.ac.uk<mailto:fouls...@essex.ac.uk> Giovanni Maria Farinella, University of Catania : gfarine...@dmi.unict.it<mailto:gfarine...@dmi.unict.it> Letizia Marchegiani – Aalborg University: l...@es.aau.dk<mailto:l...@es.aau.dk>
_______________________________________________ uai mailing list uai@engr.orst.edu https://it.engineering.oregonstate.edu/mailman/listinfo/uai
