Learning emergent behaviours for a hierarchical Bayesian framework for active robotic perception
- 192 Downloads
In this research work, we contribute with a behaviour learning process for a hierarchical Bayesian framework for multimodal active perception, devised to be emergent, scalable and adaptive. This framework is composed by models built upon a common spatial configuration for encoding perception and action that is naturally fitting for the integration of readings from multiple sensors, using a Bayesian approach devised in previous work. The proposed learning process is shown to reproduce goal-dependent human-like active perception behaviours by learning model parameters (referred to as “attentional sets”) for different free-viewing and active search tasks. Learning was performed by presenting several 3D audiovisual virtual scenarios using a head-mounted display, while logging the spatial distribution of fixations of the subject (in 2D, on left and right images, and in 3D space), data which are consequently used as the training set for the framework. As a consequence, the hierarchical Bayesian framework adequately implements high-level behaviour resulting from low-level interaction of simpler building blocks by using the attentional sets learned for each task, and is able to change these attentional sets “on the fly,” allowing the implementation of goal-dependent behaviours (i.e., top-down influences).
KeywordsMultisensory active perception Hierarchical Bayes models Bioinspired robotics Human–robot interaction Emergence Scalability Adaptive behaviour
The authors would particularly like to thank, at the Institute of Biomedical Research in Light and Image of the University of Coimbra (IBILI/UC), Prof. Miguel Castelo-Branco, João Castelhano, Carlos Amaral and Marco Simões for their help with the psychophysical experiments.
Conflict of interest
This supplement was not sponsored by outside commercial interests. It was funded entirely by ECONA, Via dei Marsi, 78, 00185 Roma, Italy.
- Bajcsy R (1985) Active perception vs passive perception. In: Third IEEE workshop on computer vision, Bellair, Michiganm, pp 55–59Google Scholar
- Bessière P, Laugier C, Siegwart R (eds) (2008) Probabilistic reasoning and decision making in sensory-motor systems, volume 46 of Springer tracts in advanced robotics, Springer. ISBN: 978-3-540-79006-8Google Scholar
- Buswell GT (1935) How people look at pictures: a study of the psychology and perception in art. University Chicago Press, ChicagoGoogle Scholar
- Ferreira JF (2011) Bayesian cognitive models for 3D structure and motion multimodal perception. PhD thesis, Faculty of Sciences and Technology of the University of Coimbra (FCTUC)Google Scholar