An emotion-driven attention model for service robot

This paper presents an Emotion-Driven Attention (EDA) model for the service robot based on cognitive structure of human, which integrates the emotion mechanism with cognitive system to manage attention allocation, and enable the robot react to emotional social cues appropriately. For a service robot, the typical tasks including interactive manipulation and object handover. During the interaction with human, the human's facial expression can be recognized by the robot in the real-time, which is considered as a social cue to trigger a corresponding emotion of the robot by Self-Organizing Map (SOM). Then, the robot's emotion plays as a reinforcement signal to regulate the attention parameters, which may result in grasping or avoiding the identified object according to the human intention. We estimate the proposal in both simulated situations and interactive scenarios, the dynamic variations of attention intensity and behaviors based on different emotional states indicate the effectiveness of the proposed model.

[1]  Dimitri Ognibene,et al.  Ecological Active Vision: Four Bioinspired Principles to Integrate Bottom–Up and Adaptive Top–Down Attention Tested With a Simple Camera-Arm Robot , 2015, IEEE Transactions on Autonomous Mental Development.

[2]  Hong Qiao,et al.  Robust object tracking guided by top-down spectral analysis visual attention , 2015, Neurocomputing.

[3]  Zhiliang Wang,et al.  Affective transfer computing model based on attenuation emotion mechanism , 2011, Journal on Multimodal User Interfaces.

[4]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[5]  Tobias Brosch,et al.  The impact of emotion on perception, attention, memory, and decision-making. , 2013, Swiss medical weekly.

[6]  Tobias Egner,et al.  Interactions between Attention and Emotion , 2015 .

[7]  Jeff T. Larsen,et al.  Context dependence of the event-related brain potential associated with reward and punishment. , 2004, Psychophysiology.

[8]  Task relevance regulates the interaction between reward expectation and emotion , 2014, Experimental Brain Research.

[9]  Zijiang J. He,et al.  Perceptual learning to reduce sensory eye dominance beyond the focus of top-down visual attention , 2012, Vision Research.

[10]  Kent A. Kiehl,et al.  The interplay of attention and emotion: top-down attention modulates amygdala activation in psychopathy , 2013, Cognitive, affective & behavioral neuroscience.

[11]  Susanne Frennert,et al.  Review: Seven Matters of Concern of Social Robots and Older People , 2014, International Journal of Social Robotics.

[12]  H. M. Müller,et al.  The non-stop road from concrete to abstract: high concreteness causes the activation of long-range networks , 2013, Front. Hum. Neurosci..

[13]  Gary R. Bradski,et al.  Learning OpenCV 3: Computer Vision in C++ with the OpenCV Library , 2016 .

[14]  Arno Villringer,et al.  Neural Control of Vascular Reactions: Impact of Emotion and Attention , 2014, The Journal of Neuroscience.

[15]  The emotion-induced memory trade-off: More than an effect of overt attention? , 2013, Memory & cognition.

[16]  Andrew Ortony,et al.  The Cognitive Structure of Emotions , 1988 .

[17]  Uipil Chong,et al.  Facial Expression Recognition Using Local Transitional Pattern on Gabor Filtered Facial Images , 2013 .

[18]  A. Mehrabian Basic dimensions for a general psychological theory : implications for personality, social, environmental, and developmental studies , 1980 .

[19]  Yongzhao Zhan,et al.  A neural-AdaBoost based facial expression recognition system , 2014, Expert Syst. Appl..

[20]  Jukka Peltola,et al.  Immediate effects of deep brain stimulation of anterior thalamic nuclei on executive functions and emotion-attention interaction in humans , 2014, Journal of clinical and experimental neuropsychology.

[21]  M. Maggi,et al.  Risky choices and emotion-based learning , 2015 .

[22]  R. Viviani Emotion regulation, attention to emotion, and the ventral attentional network , 2013, Front. Hum. Neurosci..

[23]  Frank Tong,et al.  Contrasting Bottom-up Saliency and Top-Down Attention in the Early Visual Pathway. , 2015, Journal of vision.

[24]  Michael H. Breitner,et al.  Intelligent trading of seasonal effects: A decision support algorithm based on reinforcement learning , 2014, Decis. Support Syst..

[25]  Andreas Keil,et al.  The dynamic allocation of attention to emotion: Simultaneous and independent evidence from the late positive potential and steady state visual evoked potentials , 2013, Biological Psychology.

[26]  P. Ekman Emotion in the human face , 1982 .