Towards Contextual Action Recognition and Target Localization with Active Allocation of Attention

Exploratory gaze movements are fundamental for gathering the most relevant information regarding the partner during social interactions. We have designed and implemented a system for dynamic attention allocation which is able to actively control gaze movements during a visual action recognition task. During the observation of a partner’s reaching movement, the robot is able to contextually estimate the goal position of the partner hand and the location in space of the candidate targets, while moving its gaze around with the purpose of optimizing the gathering of information relevant for the task. Experimental results on a simulated environment show that active gaze control provides a relevant advantage with respect to typical passive observation, both in term of estimation precision and of time required for action recognition.

[1]  D. Shore,et al.  More efficient scanning for familiar faces. , 2008, Journal of vision.

[2]  Yiannis Demiris,et al.  Perceiving the unusual: Temporal properties of hierarchical motor representations for action perception , 2006, Neural Networks.

[3]  Christian Balkenius,et al.  Integrating Epistemic Action (Active Vision) and Pragmatic Action (Reaching): A Neural Architecture for Camera-Arm Robots , 2008, SAB.

[4]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[5]  Yiannis Demiris,et al.  Hierarchical attentive multiple models for execution and recognition of actions , 2006, Robotics Auton. Syst..

[6]  Eric Sommerlade,et al.  Information-theoretic active scene exploration , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  M. Land.  Eye movements and the control of actions in everyday life , 2006, Progress in Retinal and Eye Research.

[8]  Giovanni Pezzulo,et al.  How can bottom-up information shape learning of top-down attention-control skills? , 2010, 2010 IEEE 9th International Conference on Development and Learning.

[9]  Guido C. H. E. de Croon,et al.  Adaptive Gaze Control for Object Detection , 2011, Cognitive Computation.

[10]  R. Johansson,et al.  Eye–Hand Coordination during Learning of a Novel Visuomotor Task , 2005, The Journal of Neuroscience.

[11]  K. Fujii,et al.  Visualization for the analysis of fluid motion , 2005, J. Vis..

[12]  Keith Kastella.  Discrimination gain to optimize detection and classification , 1997, IEEE Trans. Syst. Man Cybern. Part A.

[13]  Jürgen Schmidhuber,et al.  Learning to Generate Artificial Fovea Trajectories for Target Detection , 1991, Int. J. Neural Syst..

[14]  Yiannis Demiris,et al.  Towards an open-source social middleware for humanoid robots , 2011, 2011 11th IEEE-RAS International Conference on Humanoid Robots.

[15]  Dario Floreano,et al.  Enactive Robot Vision , 2008, Adapt. Behav..

[16]  Dieter Fox,et al.  Reinforcement learning for sensing strategies , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[17]  Yiannis Demiris,et al.  Content-based control of goal-directed attention during human action perception , 2006, ROMAN 2006 - The 15th IEEE International Symposium on Robot and Human Interactive Communication.

[18]  R. Weale.  Vision. A Computational Investigation Into the Human Representation and Processing of Visual Information. David Marr , 1983 .

[19]  Ieee Robotics.  2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sendai, Japan, September 28 - October 2, 2004 , 2004, IROS.

[20]  R. Bajcsy.  Active perception , 1988 .

[21]  Yiannis Demiris,et al.  Hierarchies for Embodied Action Perception , 2013, Computational and Robotic Models of the Hierarchical Organization of Behavior.