**5. Discussion**

Rob has completed his brief study of the current state of the art in humanoid robotics. Along the way he has found very interesting developments for both hardware and software. In almost all fields he found technology that oftentimes exceeds the abilities found in humans. However, there are several questions that come to his mind: why is it so difficult to create human behavior? Or is it intelligence? Or maybe cognition? From his analysis it seems that the most important parts are there, but still something is missing in the overall picture.

The field of humanoid robotics was formally born when a group of engineers decided to replicate human locomotion. This work is more than 40 years old and we are still unable to replicate the simplest walking gait found in humans. In section 3 Rob found several state of the art platforms that are showing signs of improvement for locomotion. He is confident that in the near future a more robust and stable human-like walking gait will be available for biped platforms. However, he does not feel so positive about other forms of motion and the transitions between them. Rob picks the embodied approach, and more specifically the dynamical systems approach, as the best option for handling instabilities and transitions between stable states such as walking, running, crawling, jumping, etc.

In Rob's opinion, grasping and manipulation do seem to be close to be maturing as well. In hardware terms, several platforms are progressing thanks to the integration of state of the art technology in skin-like materials. The addition of this component to the traditional "naked" robotic hand has improved substantially the results of grasping and manipulation. Rob is convinced that the same strategy should be applied in the lower limbs of his humanoid platform. A large part of controlling balance and motion can be transferred to the interactions between materials and environment as it has been showed by morphological computation in section 4.2.4.

There are however several challenges that worry Rob. He is still not sure about the best way to go regarding his cognitive architecture. He is not worried about the quantity or quality of the information collected through state of the art sensors; his study showed that sensors are not the problem. The problem is how to merge all that information and make some sense out of it. The missing piece seems to be finding the right way of creating and then recovering associations. Finally, a proper way of interacting with humans is needed, e.g. language.

The biggest challenge for the area of humanoid robotics right now is the design and implementation of a large project with the collaboration of an equally large number of researchers. If we continue doing research in pieces, then the development of cognitive abilities in humanoid robots will be very slow and the use of humanoids in the future very limited. The above mentioned mega-project should have as common goal the construction of a humanoid robot with state of the art sensors and actuators. If anything can be learned from the embodiment approach 4.2, it is that a complete and sophisticated body like this is needed mainly because of the biggest challenge for the future of humanoid robotics, i.e. the development of cognitive abilities through dynamic interactions with unconstrained environments.

### **6. References**

16 Will-be-set-by-IN-TECH

To summarize, it seems likely that embodied approaches are the future, both from a theoretical perspective (given insights in the cognitive sciences about the functioning of the human mind) and practically speaking (given the numerous examples of the associated benefits in robotic applications) and thus, this is the approach that Rob would prefer when designing his robot. However, he thinks about the successful applications of symbolic approaches and leaves open the door to possible interactions between both approaches. It could be possible to use dynamic tools to face unexpected circumstances and once that information looks stable let a symbolic

There are significant challenges still to overcome for embodied approaches as well. Most of the existing work (while demonstrating that an embodied approach is indeed viable) currently focuses on proof-of-concept solutions to specific problems. These limitations go hand-in-hand

Rob has completed his brief study of the current state of the art in humanoid robotics. Along the way he has found very interesting developments for both hardware and software. In almost all fields he found technology that oftentimes exceeds the abilities found in humans. However, there are several questions that come to his mind: why is it so difficult to create human behavior? Or is it intelligence? Or maybe cognition? From his analysis it seems that the most important parts are there, but still something is missing in the overall picture. The field of humanoid robotics was formally born when a group of engineers decided to replicate human locomotion. This work is more than 40 years old and we are still unable to replicate the simplest walking gait found in humans. In section 3 Rob found several state of the art platforms that are showing signs of improvement for locomotion. He is confident that in the near future a more robust and stable human-like walking gait will be available for biped platforms. However, he does not feel so positive about other forms of motion and the transitions between them. Rob picks the embodied approach, and more specifically the dynamical systems approach, as the best option for handling instabilities and transitions

In Rob's opinion, grasping and manipulation do seem to be close to be maturing as well. In hardware terms, several platforms are progressing thanks to the integration of state of the art technology in skin-like materials. The addition of this component to the traditional "naked" robotic hand has improved substantially the results of grasping and manipulation. Rob is convinced that the same strategy should be applied in the lower limbs of his humanoid platform. A large part of controlling balance and motion can be transferred to the interactions between materials and environment as it has been showed by morphological computation in

There are however several challenges that worry Rob. He is still not sure about the best way to go regarding his cognitive architecture. He is not worried about the quantity or quality of the information collected through state of the art sensors; his study showed that sensors are not the problem. The problem is how to merge all that information and make some sense out of it. The missing piece seems to be finding the right way of creating and then recovering associations. Finally, a proper way of interacting with humans is needed, e.g. language. The biggest challenge for the area of humanoid robotics right now is the design and implementation of a large project with the collaboration of an equally large number of researchers. If we continue doing research in pieces, then the development of cognitive

algorithm work with it and give some feedback to the body.

with the development of physical platforms to test new models.

between stable states such as walking, running, crawling, jumping, etc.

**4.3 Interim summary 2**

**5. Discussion**

section 4.2.4.


URL: *http://dx.doi.org/10.1109/5254.867913*

Anderson, M. L. (2003). Embodied cognition: a field guide., *Artificial Intelligence* 149: 91–130. Anybots (2008). Dexter.

URL: *http://www.anybots.com/*

Bao, Z., McCulloch, I., (Society), S., Staff, S. S., Company, A. C., Staff, A. C. C., Incorporated, C., Staff, C. I., (Firm), S. S. A. & Staff, S. S. A. F. (2009). *Organic Field-Effect Transistors VIII: 3-5 August 2009, San Diego, California, United States*, Proceedings of SPIE–the International Society for Optical Engineering, S P I E-International Society for Optical Engineering.

URL: *http://books.google.com/books?id=IjGvSgAACAAJ*


for Humanoid Robots 19

Rob's Robot: Current and Future Challenges for Humanoid Robots 297

Hickok, G. (2008). Eight problems for the mirror neuron theory of action understanding in monkeys and humans, *Journal of Cognitive Neuroscience* 21(7): 1229–1243. Hirose, M., Haikawa, Y., Takenaka, T. & Hirai, K. (2001). Development of humanoid robot

Hobbelen, D., de Boer, T. & Wisse, M. (2008). System overview of bipedal robots flame and

Iwata, H., Kobashi, S., Aono, T. & Sugano, S. (2005). Design of anthropomorphic 4-dof tactile

URL: *http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1545261* Johnson, J. S., Spencer, J. P. & Schner, G. (2008). Moving to higher ground: The dynamic

URL: *http://www.sciencedirect.com/science/article/pii/S0732118X07000505* Kaneko, K., Harada, K., Kanehiro, F., Miyamori, G. & Akachi, K. (2008). Humanoid

Keyrouz, F. (2008). Efficient binaural sound localization for humanoid robots and telepresence

Ko, H. C., Stoykovich, M. P., Song, J., Malyarchuk, V., Choi, W. M., Yu, C.-J., III, J. B. G., Xiao,

Lipomi, D., Tee, B., Vosgueritchian, M. & Bao, Z. (2011). Stretchable organic solar cells., *Adv*

Liu, H., Meusel, P., Seitz, N., Willberg, B., Hirzinger, G., Jin, M., Liu, Y., Wei, R. & Xie, Z. (2007).

Mahmoudi, E. (2009). Electronic nose technology and its applications, *Sensors & Transducers*

McGeer, T. (1990). Passive dynamic walking, *The International Journal of Robotics Research*

Niiyama, R. & Kuniyoshi, Y. (2010). Design principle based on maximum output force profile for a musculoskeletal robot, *Industrial Robot: An International Journal* 37(3). Oztop, E., Kawato, M. & Arbib, M. A. (2006). Mirror neurons and imitation: A

computationally guided review, *Neural Networks* 19: 254–271.

URL: *http://www.sciencedirect.com/science/article/pii/S0094114X0600098X* Lowe, R., Duran, B. & Ziemke, T. (2010). A dynamic field theoretic model of iowa gambling

URL: *http://www.sensorsportal.com/HTML/DIGEST/august\_09/P\_470.pdf* Mahon, B. Z. & Caramazza, A. (2008). A critical look at the embodied cognition hypothesis

based on compressible silicon optoelectronics, *Nature* 454: 748–753.

tulip: Tailor-made for limit cycle walking, *Intelligent Robots and Systems, 2008. IROS*

interaction manipulator with passive joints, *2005 IEEERSJ International Conference on*

field theory and the dynamics of visual cognition, *New Ideas in Psychology* 26(2): 227

robot hrp-3, *Intelligent Robots and Systems, 2008. IROS 2008. IEEE/RSJ International*

J., Wang, S., Huang, Y. & Rogers, J. A. (2008). A hemispherical electronic eye camera

The modular multisensory dlr-hit-hand, *Mechanism and Machine Theory* 42(5): 612 –

task performance, *Development and Learning (ICDL), 2010 IEEE 9th International*

and a new proposal for grounding conceptual content, *Journal of Physiology Paris*

asimo, *International Conference on Intelligent Robots and Systems*.

*2008. IEEE/RSJ International Conference on*, pp. 2486 –2491. Ishikawa, M. & Oku, H. (2011). Ishikawa oku laboratory, university of tokyo.

URL: *http://www.k2.t.u-tokyo.ac.jp/*

– 251. Dynamics and Psychology.

*Conference on*, pp. 2471 –2478.

applications.

625.

107: 17–25.

102: 59–70.

9(2): 62–82.

*Mater* 23(15): 1771–5.

*Conference on*, pp. 297 –304.

*Intelligent Robots and Systems* pp. 1785–1790.


URL: *http://www.sciencedirect.com/science/article/pii/S0079612308006377*

	- URL: *http://dx.doi.org/10.1371/journal.pone.0013718*

URL: *http://www.festo.com/*


18 Will-be-set-by-IN-TECH

Collette, C., Micaelli, A., Andriot, C. & Lemerle, P. (2007). Dynamic balance control of

Collins, S., Ruina, A., Tedrake, R. & Wisse, M. (2005). Efficient bipedal robots based on

Cui, Q. N., Bachus, L., Knoth, E., O'Neill, W. E. & Paige, G. D. (2008). Eye position and

Davis, S., Tsagarakis, N. & Caldwell, D. (2008). The initial design and manufacturing process

Demiris, Y. & Hayes, G. (2002). *Imitation in animals and artefacts*, MIT Press, Cambridge,

Demiris, Y. & Johnson, M. (2003). Distributed, predictive perception of actions: A

Dineva, E. (2005). *Dynamical Field Theory of Infant Reaching and its Dependence on Behavioral*

Faisal, A., Stout, D., Apel, J. & Bradley, B. (2010). The manipulative complexity of lower

Fischer, M. H. (2008). Finger counting habits modulate spatial-numerical associations, *Cortex*

Fogassi, L., Ferrari, P. F., Gesierich, B., Rozzi, S., Chersi, F. & Rizzolatti, G. (2005). Parietal lobe: from action organization to intention understanding, *Science* 308: 662–667. Franceschini, N., Pichon, J. M. & Blanes, C. (1992). From insect vision to robot vision,

Harnad, S. (1990). The symbol grounding problem, *Physica D: Nonlinear Phenomena*

Haykin, S. & Chen, Z. (2005). The cocktail party problem, *Neural Computation* 17(9): 1875–1902. URL: *http://www.mitpressjournals.org/doi/abs/10.1162/0899766054322964*

Gallagher, S. (2005). *How the body shapes the mind*, Oxford University Press, New York. Gallese, V., Fadiga, L., Fogassi, L. & Rizzolatti, G. (1996). Action recognition in the premotor

*Philosophical Transactions of The Royal Society Of London. Series B: Biological Sciences*

Graduate School for Neuroscience, Ruhr-Universiät-Bochum, Germany. Erlhagen, W., Mukovski, A. & Bicho, E. (2006). A dynamic model for action understanding

URL: *http://www.sciencedirect.com/science/article/pii/S0079612308006377* Dahiya, R., Metta, G., Valle, M. & Sandini, G. (2010). Tactile sensing - from humans to

*Robots, 2007 7th IEEE-RAS International Conference on*, pp. 81 –88.

passive-dynamic walkers, *Science* 307(5712): 1082–1085. URL: *http://www.sciencemag.org/content/307/5712/1082.abstract*

humanoids, *Robotics, IEEE Transactions on* 26(1): 1 –20.

components: A biologically-plausible computational model.

and goal-directed imitation, *Brain Research* 1083: 174–188.

paleolithic stone toolmaking, *PLoS ONE* 5(11): e13718. URL: *http://dx.doi.org/10.1371/journal.pone.0013718*

*Research*, Elsevier, pp. 265 – 270.

*Science* 15(4): 231–243.

URL: *http://www.festo.com/*

cortex, *Brain Research* 119: 593–609.

44: 386–392.

337: 283–294.

42(1-3): 335–346.

Festo (2011).

humanoids for multiple grasps and non coplanar frictional contacts, *Humanoid*

cross-sensory learning both contribute to prism adaptation of auditory space, *in* C. Kennard & R. J. Leigh (eds), *Using Eye Movements as an Experimental Probe of Brain function - A Symposium in Honor of Jean BÃijttner-Ennever*, Vol. 171 of *Progress in Brain*

of a low cost hand for the robot icub, *IEEE International Conference on Humanoid Robots*.

MA, chapter Imitation as a doual-route process featuring predictive and learning

biologically inspired robotics architecture for imitation and learning., *Connection*

*History and Context.*, PhD thesis, Institut für Neuroinformatik & Intrnational

	- URL: *http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1545261*
	- URL: *http://www.sciencedirect.com/science/article/pii/S0732118X07000505*

URL: *http://www.sciencedirect.com/science/article/pii/S0094114X0600098X*


URL: *http://www.sensorsportal.com/HTML/DIGEST/august\_09/P\_470.pdf*


for Humanoid Robots 21

Rob's Robot: Current and Future Challenges for Humanoid Robots 299

Strack, F., Marin, L. & Stepper, S. (1988). Inhibiting and facilitating conditions of the human

Takei, K., Takahashi, T., Ho, J. C., Ko, H., Gillies, A. G., Leu, P. W., Fearing, R. S. & Javey, A.

Tani, J., Ito, M. & Sugita, Y. (2004). Self-organization of distributedly represented multiple

Thill, S. (2011). Considerations for a neuroscience-inspired approach to the design of

Thill, S., Svensson, H. & Ziemke, T. (In Press). Modeling the development of goal-specificity

Thill, S. & Ziemke, T. (2010). Learning new motion primitives in the mirror neuron system: A

Traver, J. & Bernardino, A. (2010). A review of log-polar imaging for visual perception in

Tsakarakis, N., Metta, G., Sandini, G., Vernon, D., Beira, R., Becchi, F., Righetti, L.,

Ueno, T. & Oda, M. (2009). Robotic hand developed for both space missions on the

Umiltà, M. A., Escola, L., Intskirveli, I., Grammont, F., Rochat, M., Caruana, F., Jezzini, A.,

system, *Proceedings of the National Academy of Sciences USA* 105(6): 2209–2213. Vernon, D. (2008). Cognitive vision: The case for embodied perception, *Image Vision Comput.*

Vukobratovic, M. & Borovac, B. (2004). Zero-moment point - thirty five years of its life,

Wermter, S., Elshaw, M. & Farrand, S. (2003). A modular approach to self-organization of robot control based on language instruction, *Connection Science* 15(2-3): 73–94. Wermter, S., Weber, C. & Elshaw, M. (2005). Associative neural models for biomimetic

Wermter, S., Weber, C., Elshaw, M., Panchev, C., Erwin, H. & Pulvermüller, F. (2004). Towards

Wolpert, D. & Kawato, M. (2001). Multiple paired forward and inverse models for motor

*Social Psychology* 54: 768–777.

*Nature Materials* 9(10): 821âA ¸ ˘ S826.

*Neural Networks* 17: 1273–1289.

Springer, Heidelberg, pp. 247–254.

Springer, Heidelberg, pp. 413–423.

*Neuroscience* 21(10): 1151–1175.

26(1): 127–140.

16: 31–46.

in mirror neurons, *Cognitive Computation* .

robotics., *Robotics and Autonomous Systems* pp. 378–398.

IEEE Press, Piscataway, NJ, USA, pp. 1791–1796.

*International Journal of Humanoid Robotics* 1: 157–173.

control, *Neural Networks* 11: 1317–1329.

URL: *http://portal.acm.org/citation.cfm?id=1733023.1733039*

smile: A nonobtrusive test of the facial feedback hypothesis, *Journal of Personality and*

(2010). Nanowire active-matrix circuitry for low-voltage macroscale artificial skin,

behavior schemata in a mirror system: reviews of robot experiments using RNNPB,

artificial intelligent systems, *in* J. Schmidhuber, K. R. Thórisson & M. Looks (eds), *Proceedings of the Fourth Conference on Artificial General Intelligence, LNAI 6830*,

self-organising computational model., *in* S Doncieux et al (ed.), *SAB 2010, LNAI 6226*,

Santos-Victor, J., Ijspeert, A., Carrozza, M. & Caldwell, D. (2007). icub - the design and realization of an open humanoid platform for cognitive and neuroscience research, *Journal of Advanced Robotics, Special Issue on Robotic platforms for Research in*

international space station and commercial applications on the ground, *Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems*, IROS'09,

Gallese, V. & Rizzolatti, G. (2008). When pliers become fingers in the monkey motor

multimodal learning in a mirror-neuron based robot, *Progess in Neural Processing*

multimodal neural robot learning, *Robotics and Autonomous Systems* 47(2-3): 171–175.


URL: *http://www.peratech.com/*

Petman (2011). Boston dynamics.

URL: *http://www.bostondynamics.com/*


URL: *http://dx.doi.org/10.1023/B:AURO.0000016862.38337.f1*


URL: *http://www.shadowrobot.com/*

Shotton, J. & Sharp, T. (2011). Real-time human pose recognition in parts from single depth images, *statosuedu* 2: (to appear).

URL: *http://www.stat.osu.edu/ dmsl/BodyPartRecognition.pdf*

Simmering, V. R., Schutte, A. R. & Spencer, J. P. (2008). Generalizing the dynamic field theory of spatial cognition across real and developmental time scales, *Brain Research* 1202: 68 – 86. Computational Cognitive Neuroscience.

URL: *http://www.sciencedirect.com/science/article/pii/S0006899307013807*

Simmering, V. R. & Spencer, J. P. (2008). Generality with specificity: the dynamic field theory generalizes across tasks and time scales, *Developmental Science* 11(4): 541–555. URL: *http://dx.doi.org/10.1111/j.1467-7687.2008.00700.x*

20 Will-be-set-by-IN-TECH

Park, I.-W., Kim, J.-Y., Lee, J. & Oh, J.-H. (2005). Mechanical design of humanoid robot

Pezzulo, G., Barsalou, L. W., Cangelosi, A., Fischer, M. H., McRae, K. & Spivey, M. J.

Pfeifer, R. & Bongard, J. (2007). *How the body shapes the way we think*, MIT Press, Cambridge. Pfeifer, R. & Iida, F. (2005). Morphological computation: conecting brain, body and

Pfeifer, R., Iida, F. & Gómez, G. (2006). Morphological computing for adaptiver behavior and

Pons, J., Rocon, E., Ceres, R., Reynaerts, D., Saro, B., Levin, S. & Van Moorleghem,

Righetti, L. & Ijspeert, A. J. (2006). Design methodologies for central pattern generators:

Rizzolatti, G. & Sinigaglia, C. (2010). The functional role of the parieto-frontal mirror circuit: interpretations and misinterpretations, *Nature Reviews Neuroscience* 11(4): 264–274. Ruesch, J., Lopes, M., Bernardino, A., Hornstein, J., Santos-Victor, J. & Pfeifer, R. (2008).

Schöner, G. (2008). *Toward a New Grand Theory of Development? Connectionism and*

Shadow Robot Company (2003). Design of a dextrous hand for advanced CLAWAR

Shotton, J. & Sharp, T. (2011). Real-time human pose recognition in parts from single depth

Simmering, V. R., Schutte, A. R. & Spencer, J. P. (2008). Generalizing the dynamic field theory

URL: *http://www.sciencedirect.com/science/article/pii/S0006899307013807* Simmering, V. R. & Spencer, J. P. (2008). Generality with specificity: the dynamic field theory generalizes across tasks and time scales, *Developmental Science* 11(4): 541–555.

URL: *http://www.stat.osu.edu/ dmsl/BodyPartRecognition.pdf*

URL: *http://dx.doi.org/10.1111/j.1467-7687.2008.00700.x*

– 86. Computational Cognitive Neuroscience.

(2011). The mechanics of embodiment: a dialog on embodiment and computational

W. (2004). The manus-hand dextrous robotics upper limb prosthesis: Mechanical and manipulation aspects, *Autonomous Robots* 16: 143–163.

an application to crawling humanoids, *Proceedings of Robotics: Science and Systems*,

Multimodal saliency-based bottom-up attention a framework for the humanoid robot icub, *Robotics and Automation, 2008. ICRA 2008. IEEE International Conference on*,

*Dynamic Systems Theory Re-Considered.*, Oxford University Press, New York, chapter Development as Change of System Dynamics: Stability, Instability, and Emergence.,

applications, *Climbing and Walking Robots and the Supporting Technologies for Mobile*

of spatial cognition across real and developmental time scales, *Brain Research* 1202: 68

platform khr-3 (kaist humanoid robot 3: Hubo), pp. 321 –326.

Peratech (2011).

URL: *http://www.peratech.com/*

URL: *http://www.bostondynamics.com/*

modeling, *Frontiers in Psychology* 2(5).

10.1023/B:AURO.0000016862.38337.f1.

environment, *Japanese Scientific Monthly* 58(2): 48–54.

cognition, *International Congress Series* 1291: 22–29.

URL: *http://dx.doi.org/10.1023/B:AURO.0000016862.38337.f1*

Petman (2011). Boston dynamics.

pp. 191–198.

pp. 962 –967.

p. In press.

*Machines*, pp. 691–698.

URL: *http://www.shadowrobot.com/*

images, *statosuedu* 2: (to appear).


22 Will-be-set-by-IN-TECH

300 The Future of Humanoid Robots – Research and Applications

Yamashita, Y. & Tani, J. (2008). Emergence of functional hierarchy in a multiple timescale

Yokoi, H., Arieta, A. H., Katoh, R., Yu, W., Watanabe, I. & Maruishi, M. (2004). Mutual

*Mental Development, IEEE Transactions on* 3(1): 74 –91.

4(11): 1–18.

neural network model: a humanoid robot experiment, *PLoS Computational Biology*

adaption in a prosthetics application, *in* F. Iida, R. Pfeifer, L. Steels & Y. Kuniyoshi (eds), *Embodied Artificial Intelligence, LNAI 3139*, Springer, Heidelberg, pp. 146–159. Zibner, S., Faubel, C., Iossifidis, I. & Schoner, G. (2011). Dynamic neural fields as building

blocks of a cortex-inspired architecture for robotic scene representation, *Autonomous*
