**6. References**

Albus, J. and Barbera, A. (2005). RCS: A Cognitive Architecture for Intelligent Multi-Agent Systems. *Annual Reviews in Control,* Vol.29, No.1, pp. 87-99, 2005

Implementation of a Framework for Imitation

Germany

BC, 2010

Vol.14, No.7, pp. 72-84, 2007

Vol.5, No.4, pp. 547-586, 2008

*Interaction,* Vol.12, pp. 391-438, 1997

*Artificial Intelligence,* Vol.33, pp. 1-64, 1987

River, N.J., Prentice Hall/Pearson Education.

*Sciences,* Vol.3, No.6, pp. 233-242, 1999

Press. New York, NY, USA

Embedding. *Science,* Vol.290, No.5500, pp. 2323-2326, 2000

*IEEE Control Systems Magazine,* Vol.14, No.1, pp. 57-71, 2002

Learning on a Humanoid Robot Using a Cognitive Architecture 209

Haikonen, P. (2007). Essential Issues of Conscious Machines. *Journal of Consciousness Studies,*

Ijspeert, A., Nakanishi, J. and Schaal, S. (2002). Movement Imitation with Nonlinear Dynamical

Ijspeert, A., Nakanishi, J. and Schaal, S. (2003). Learning Attractor Landscapes for Learning

Kawamura, K. and Browne, W. N. (2009). Cognitive Robotics. In: *Encyclopedia of Complexity* 

Kawamura, K., Gordon, S., Ratanaswasd, P., Erdemir, E. and Hall, J. (2008). Implementation of

Kawamura, K., Peters II, R., Bodenheimer, R., Sarkar, N., Park, J., Spratley, A. and

Konidaris, G., Kuindersma, S., Barto, A. and Grupen, R. (2010). Constructing Skill Trees for

Krichmar, J. and Reeke, G. (2005). The Darwin Brain-Based Automata: Synthetic Neural

Kulic, D., Takano, W. and Nakamura, Y. (2008). Combining Automated on-Line Segmentation

*Conference on Robotics and Automation*, pp.2591-2598, Pasadena, CA, USA, 2008 Laird, J., Newell, A. and Rosenbloom, P. (1987). Soar: An Architecture for General Intelligence.

Roweis, S. and Saul, L. (2000). Nonlinear Dimensionality Reduction by Locally Linear

Russell, S. J. and Norvig, P. (2010). Artificial Intelligence : A Modern Approach. Upper Saddle

Schaal, S. (1999). Is Imitation Learning the Route to Humanoid Robots. *Trends in Cognitive* 

Schaal, S. and Atkeson, C. (2002). Robot Juggling: Implementation of Memory-Based Learning.

Schneider, W. (1999). Working Memory in a Multilevel Hybrid Connectionist Control

Architecture (Cap2). In: *Models of Working Memory: Mechanisms of Active Maintenance and Executive Control*. A.Miyake and P. Shah (Ed.), 340–374, Cambridge University

*Robotics and Automation*, pp.1398-1403, Washington, DC, USA, 2002

Thrun and K. Obermayer (Ed.), 1547-1554, MIT Press. 15

Systems in Humanoid Robots. *Proceedings of the 2002 IEEE International Conference on* 

Motor Primitives. In: *Advances in Neural Information Processing Systems*. S. Becker, S.

*and System Science*. R. A. Meyers (Ed.), 1109-1126, Springer Science. Heidelberg,

Cognitive Control for a Humanoid Robot. *International Journal of Humanoid Robotics,*

Hambuchen, K. (2004). Multiagent-Based Cognitive Robot Architecture and Its Realization. *International Journal of Humanoid Robotics,* Vol.1, No.1, pp. 65-93, 2004 Keiras, D. E. and Meyer, D. E. (1997). An Overview of the Epic Architecture for Cognition and

Performance with Application to Human-Computer Interaction. *Human-Computer* 

Reinforcement Learning Agents from Demonstration Trajectories. *Proceedings of Advances in Neural Information Processing Systems (NIPS 2010)*, pp.1-11, Vancouver,

Models and Real-World Devices. In: *Modelling in the Neurosciences: From Biological Systems to Neuromimetic Robotics*. G. N. Reeke, R. R. Poznanski, K. A. Lindsay, J. R.Rosenberg and O. Sporns (Ed.), 613–638, Taylor and Francis. Boca, Raton, FL, USA

and Incremental Clustering for Whole Body Motions. *Proceedings of IEEE International* 


208 The Future of Humanoid Robots – Research and Applications

Anderson, J. R., Matessa, M. and Lebiere, C. (1997). ACT-R: A Theory of Higher Level

Anderson, M. (2003). Embodied Cognition: A Field Guide. *Artificial Intelligence,* Vol.149, No.1,

Argall, B., Chernova, S, Veloso, M, and Browning, B (2009). A Survey of Robot Learning from Demonstration. *Robotics and Autonomous Systems,* Vol.57, No.5, pp. 469-483, 2009 Atkeson, C., Moore, A. and Schaal, S. (1997). Locally Weighted Learning. *Artificial intelligence* 

Atkeson, C. and Schaal, S. (1997). Robot Learning from Demonstration. *Proceedings of the* 

Bentivegna, D. and Atkeson, C. (2001). Learning from Observation Using Primitives.

Billard, A. (2001). Learning Motor Skills by Imitation: A Biologically Inspired Robotic Model.

Billard, A., Calinon, S., Dillmann, R. and Schaal, S. (2007). Robot Programming by

Brooks, R. (1986). A Robust Layered Control System for a Mobile Robot. *IEEE Journal of* 

Brooks, R. (1991). How to Build Complete Creatures Rather Than Isolated Cognitive

Brooks, R., Breazeal, C., Marjanovi , M., Scassellati, B. and Williamson, M. (1999). The Cog

*Agents*. C. Nehaniv (Ed.), 52-87, Springer-Verlag. Heidelberg, Berlin, Germany Brooks, R. A. (1991). Intelligence without Representation. *Artificial Intelligence,* Vol.47, No.1-3,

Calinon, S. and Billard, A. (2007). Incremental Learning of Gestures by Imitation in a

Calinon, S., Guenter, F. and Billard, A. (2007). On Learning, Representing, and Generalizing a

Dillmann, R., Kaiser, M. and Ude, A. (1995). Acquisition of Elementary Robot Skills from

Dillmann, R., Rogalla, O., Ehrenmann, M., Zollner, R. and Bordegoni, M. (2000). Learning

Gobet, F., Lane, P., Croker, S., Cheng, P., Jones, G., Oliver, I. and Pine, J. (2001). Chunking

*Robotics Research (ISRR-1999),*, pp.229-238, Snowbird, UT, USA, 2000

*Human-robot interaction*, pp.255-262, New York, NY, USA, 2007

*Cybernetics and Systems,* Vol.32, No.1, pp. 155-193, 2001

*Robotics and Automation,* Vol.2, No.1, pp. 14-23, 1986

*Fourteenth International Conference on Machine Learning*, pp.11-73, Morgan Kaufmann,

*Proceedings of the 2011 International Conference on Robotics & Automation*, pp.1988-1993,

Demonstration. In: *Handbook of Robotics*. B. Siciliano and O. Khatib (Ed.), Springer.

Simulators. In: *Architectures for Intelligence*. K. VanLehn (Ed.), 225–239, Erlbaum.

Project: Building a Humanoid Robot. In: *Computation for Metaphors, Analogy, and* 

Humanoid Robot. *Proceedings of the 2007 ACM/IEEE International Conference on* 

Task in a Humanoid Robot. *IEEE Transactions on Systems, Man, and Cybernetics, Part B,*

Human Demonstration. *Proceedings of the 1995 International Symposium on Intelligent* 

Robot Behaviour and Skills Based on Human Demonstration and Advice: The Machine Learning Paradigm. *Proceedings of the Ninth International Symposium of* 

Mechanisms in Human Learning. *Trends in cognitive sciences,* Vol.5, No.6, pp. 236-243,

No.4, pp. 439-462, 1997

*review,* Vol.11, No.1, pp. 11-73, 1997

pp. 91-130, 2003

Seoul, Korea, 2001

New York, NY, USA

Hillsdale, NJ

pp. 139-159, 1991

2001

Vol.37, No.2, pp. 286-298, 2007

*Robotic System*, pp.1-38, Pisa, Italy, 1995

1997

Cognition and Its Relation to Visual Attention. *Human-Computer Interaction,* Vol.12,


**0**

**11**

*USA*

**A Multi-Modal Panoramic Attentional Model for**

*Honda Research Institute USA, 425 National Ave Suite 100,Mountain View CA 94043*

Humanoid robots are becoming increasingly competent in perception of their surroundings and in providing intelligent responses to worldly events. A popular paradigm to realize such responses is the idea of attention itself. There are two important aspects of attention in the context of humanoid robots. First, *perception* describes how to design the sensory system to filter out useful salient features in the sensory field and perform subsequent higher level processing to perform tasks such as face recognition. Second, the *behavioral response* defines how the humanoid should act when it encounters the salient features. A model of attention enables the humanoid to achieve a semblance of liveliness that goes beyond exhibiting a mechanized repertoire of responses. It also facilitates progress in realizing models of higher-level cognitive processes such as having people direct the robot's attention to a

Studies indicate that humans employ attention as a mechanism for preventing sensory overload(Tsotsos et al., 2005),(Komatsu, 1994) – a finding which is relevant to robotics given that information bandwidth is often a concern. The neurobiologically inspired models of Itti (Tsotsos et al., 2005), initially developed for modeling visual attention have been improved(Dhavale et al., 2003) and their scope has been broadened to include even auditory modes of attention(Kayser et al., 2008). Such models have formed the basis of multi-modal

Typical implementations of visual attention mechanisms employ a bottom-up processing of camera images to arrive at the so-called "saliency map", which encodes the unconstrained salience of the scene. Salient regions identified from saliency map are processed by higher-level modules such as object and face recognition. The results of these modules are then used as referential entities for the task at hand(e.g. acknowledging a familiar face, noting the location of a recognized object). Building upon the recent additions to Itti's original model(Tsotsos et al., 2005), some implementations also use top-down control mechanisms to constrain the salience(Cynthia et al., 2001),(Navalpakkam and Itti, 2005),(Moren et al., 2008). In most of the implementations, the cameras are held fixed, simplifying processing and consequent attention mechanism modeling. However, this restricts the visual scope of attention, particularly in situations when the robot has to interact with multiple people who may be spread beyond its limited field-of-view. Moreover, they may choose to advertise their

Attempts to overcome this situation lead naturally to the idea of widening the visual scope and therefore, to the idea of a *panoramic* attention. In most of the implementations which

attention mechanisms in (humanoid) robots(Maragos, 2008),(Rapantzikos, 2007).

presence through a non-visual modality such as speech utterances.

**1. Introduction**

specific target stimulus(Cynthia et al., 2001).

**Robots and Applications**

Ravi Sarvadevabhatla and Victor Ng-Thow-Hing

