Intrinsically motivated learning of real-world sensorimotor skills with developmental constraints

Intrinsically Motivated Learning in Natural and Artificial Systems

Volumn 9783642323751, Issue , 2013, Pages 303-365

  Oudeyer, Pierre Yves ^a   Baranes, Adrien ^a   Kaplan, Frédéric ^b  

^a INRIA   (France)

^b EPFL   (Switzerland)

Author keywords

[No Author keywords available]

Indexed keywords

DEVELOPMENTAL MECHANISMS; DEVELOPMENTAL ROBOTICS; HIGH DIMENSIONALITY; INTRINSIC MOTIVATION; PROPERTY; REAL-WORLD; SENSORIMOTOR APPARATUS; SENSORIMOTORS; TASK SPACE; TECHNICAL CHALLENGES;

EDUCATION;

EID: 84886642171     PISSN: None     EISSN: None     Source Type: Book    
DOI: 10.1007/978-3-642-32375-1_13     Document Type: Chapter

References (134)

1. Angluin, D.: Queries and concept learning. Mach. Learn. 2, 319-342 (1988)
2. Asada, M., Hosoda, K., Kuniyoshi, Y., Ishiguro, H., Inui, T., Yoshikawa, Y., Ogino, M., Yoshida, C.: Cognitive developmental robotics: A survey. IEEE Trans. Auton. Mental Dev. 1(1), 12-34 (2009)
3. Bakker, B., Schmidhuber, J.: Hierarchical reinforcement learning based on subgoal discovery and subpolicy specialization. In: Proceedings of the 8th Conference on Intelligent Autonomous Systems (IAS-8) (2004)
4. Baldassarre, G., Mirolli, M.: Temporal-difference competence-based intrinsic motivation (TD-CB-IM): A mechanism that uses the td-error as an intrinsic reinforcement for deciding which skill to learn when. In:. In: Baldassarre, G., Mirolli, M. (eds.) Intrinsically Motivated Learning in Natural and Artificial Systems, pp. 255-276. Springer, Berlin (2012)
5. Ball, P.: The Self-made Tapestry-Pattern formation in nature. Oxford University Press, New York (1999)
6. Baranes, A., Oudeyer, P.-Y.: Riac: Robust intrinsically motivated exploration and active learning. IEEE Trans. Auton. Mental Dev. 1(3), 155-169 (2009)
7. Baranes, A., Oudeyer, P.-Y.: Intrinsically motivated goal exploration for active motor learning in robots: A case study. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010) (2010a)
8. Baranes, A., Oudeyer, P.-Y.: Maturationally constrained competence-based intrinsically motivated learning. In: Proceedings of IEEE International Conference on Development and Learning (ICDL 2010) (2010b)
9. Baranes, A., Oudeyer, P.-Y.: The interaction of maturational constraints and intrinsic motivations in active motor development. In: Proceedings of IEEE ICDL-Epirob 2011 (2011)
10. Baranes, A., Oudeyer, P-Y.: Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots, Robotics and Autonomous Systems, http://dx.doi.org/10.1016/j.robot. 2012.05.008, (2012)
11. Barto, A., Singh, S., Chenatez, N.: Intrinsically motivated learning of hierarchical collections of skills. In: Proceedings of the 3rd International Conference Development Learning, San Diego, pp. 112-119 (2004)
12. Barto, A.G.: Intrinsic motivation and reinforcement learning. In: Baldassarre, G., Mirolli, M. (eds.) Intrinsically Motivated Learning in Natural and Artificial Systems, pp. 17-47. Springer, Berlin (2012)
13. Berk, L.: Child Development. Allyn and Bacon, Boston (2008)
14. Berlyne, D.: Conflict, Arousal and Curiosity. McGraw-Hill, New York (1960)
15. Berthier, N.E., Clifton, R., McCall, D., Robin, D.: Proximodistal structure of early reaching in human infants. Exp. Brain Res. 127(3), 259-269 (1999)
16. Billard, A., Calinon, S., Dillmann, R., Schaal, S.: Robot programming by demonstration. In: Handbook of Robotics. Springer, Berlin (2008)
17. Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)
18. Bishop, C.M.: Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, Berlin (1st ed., 2006/corr. 2nd printing edition, 2007)
19. Bjorklund, D.: The role of immaturity in human development. Psychol. Bull. 122(2), 153-169 (1997)
20. Blank, D., Kumar, D., Meeden, L., Marshall, J.: Bringing up robot: Fundamental mechanisms for creating a self-motivated, self-organizing architecture. Cybern. Syst. 36(2), 125-150 (2002)
21. Brafman, R., Tennenholtz, M.: R-max: A general polynomial time algorithm for near-optimal reinforcement learning. In: Proceedings of IJCAI'01 (2001)
22. Bremner, J., Slater, A. (eds.): Theories of Infant Development. Blackwell, Cambridge (2003)
23. Bronson, G.: The postnatal growth of visual capacity. Child. Dev. 45(4), 873-890 (1974)
24. Calinon, S., Guenter, F., Billard, A.: On learning, representing and generalizing a task in a humanoid robot. IEEE Trans. Syst. Man Cybern. B, 37(2), 286-298 (2007)
25. Castro, R., Novak, R.: Minimax bounds for active learning. IEEE Trans. Inform. Theory 54, 151-156 (2008)
26. Cazalets, J., Borde, M., Clarac, F.: Localization and organization of the central pattern generator for hindlimb locomotion in newborn rat. J. Neurosci. 15, 4943-4951 (1995)
27. Cederborg, T., Ming, L., Baranes, A., Oudeyer, P.-Y.: Incremental local online gaussian mixture regression for imitation learning of multiple tasks. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010) (2010)
28. Chaloner, K., Verdinelli, I.: Bayesian experimental design: A review. J. Stat. Sci. 10, 273-304 (1995)
29. Chung, W., Fu, L.-C., Hsu, S.-H.: Motion control. In: Handbook of Robotics, pp. 133-159. Springer, Berlin (2008)
30. Cohn, D., Atlas, L., Ladner, R.: Improving generalization with active learning. Mach. Learn. 15(2), 201-221 (1994)
31. Cohn, D., Ghahramani, Z., Jordan, M.: Active learning with statistical models. J. Artif. Intell. Res. 4, 129-145 (1996)
32. Csikszentmihalyi, M.: Creativity-Flow and the Psychology of Discovery and Invention. Harper Perennial, New York (1996)
33. d'Avella, A., Portone, A., Fernandez, L., Lacquaniti, F.: Control of fast-reaching movement by muscle synergies combinations. J. Neurosci. 26(30), 7791-7810 (2006)
34. d'Avella, A., Saltiel, P., Bizzi, E.: Combinations of muscle synergies in the construction of a natural motor behavior. Nat. Neurosci. 6, 300-308 (2003)
35. Dayan, P.: Exploration from generalisation mediated by multiple controllers. In: Baldassarre, G., Mirolli, M. (eds.) Intrinsically Motivated Learning in Natural and Artificial Systems, pp. 73-91. Springer, Berlin (2012)
36. Dayan, P., Belleine, W.: Reward, motivation and reinforcement learning. Neuron 36, 285-298 (2002)
37. De Charms, R.: Personal Causation: The Internal Affective Determinants of Behavior. Academic, New York (1968)
38. Deci, E., Ryan, M.: Intrinsic Motivation and Self-determination in Human Behavior. Plenum, New York (1985)
39. Dick, T., Oku, Y., Romaniuk, J., Cherniack, N.: Interaction between cpgs for breathing and swallowing in the cat. J. Physiol. 465, 715-730 (1993)
40. Doya, K.: Metalearning and neuromodulation. Neural Netw. 15(4-5), 495-506 (2002)
41. Eyre, J.: Development and Plasticity of the Corticospinal System in Man. Neural Plast.; 10(1-2), 93-106 (2003)
42. Faller, D., Klingmüller, U., Timmer, J.: Simulation methods for optimal experimental design in systems biology. Simulation 79, 717-725 (2003)
43. Fedorov, V.: Theory of Optimal Experiment. Academic, New York (1972)
44. Festinger, L.: A Theory of Cognitive Dissonance. Row & Peterson, Evanston (1957)
45. Fisher, K., Silvern, L.: Stages and individual differences in cognitive development. Annu. Rev. Psychol. 36, 613-648 (1985)
46. Franceschini, N., Pichon, J., Blanes, C.: From insect vision to robot vision. Phil. Trans. R. Soc. Lond. B 337, 283-294 (1992)
47. Ghahramani, Z.: Solving inverse problems using an em approach to density estimation. In: Mozer, M., Smolensky, P., Toureztky, D., Elman, J., Weigend, A. (eds.) Proceedings of the 1993 Connectionist Models Summer School (1993)
48. Gibson, J.: The Ecological Approach to Visual Perception. Lawrence Erlbaum Associates, Hillsdale (1986)
49. Grollman, D.H., Jenkins, O.C.: Incremental learning of subtasks from unsegmented demonstration. In: International Conference on Intelligent Robots and Systems, Taipei (2010)
50. Hart, S., Grupen, R.: Intrinsically motivated hierarchical manipulation. In: Proceedings of the 2008 IEEE Conference on Robots and Automation (ICRA) (2008)
51. Hart, S., Grupen, R.: Intrinsically motivated affordance discovery and modeling. In: Baldassarre, G., Mirolli, M. (eds.) Intrinsically Motivated Learning in Natural and Artificial Systems, pp. 279-300. Springer, Berlin (2012)
52. Huang, X., Weng, J.: Novelty and reinforcement learning in the value system of developmental robots. In: Prince, C., Demiris, Y., Marom, Y., Kozima, H., Balkenius, C. (eds.) Proceedings of the 2nd International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, pp. 47-55. Lund University Cognitive Studies 94, Lund (2002)
53. Hull, C.L.: Principles of Behavior: An Introduction to Behavior Theory. Appleton-Century-Croft, New York (1943)
54. Hunt, J.M.: Intrinsic motivation and its role in psychological development. Nebraska Symp. Motiv. 13, 189-282 (1965)
55. Iida, F., Pfeifer, R.: Cheap and rapid locomotion of a quadruped robot: Self-stabilization of bounding gait. In: Proceedings of the 8th International Conference on Intelligent Autonomous Systems (IAS-8), Amsterdam, Netherlands, Groen, F. et al. (Eds.) (2004)
56. James, W.: The Principles of Psychology. Harvard University Press, Cambridge (1890)
57. Johnson, M.: Functional brain development in humans. Nat. Rev. Neurosci. 2(7), 475-483 (2001)
58. Kagan, J.: Motives and development. J. Pers. Soc. Psychol. 22, 51-66 (1972)
59. Kakade, S., Dayan, P.: Dopamine: Generalization and bonuses. Neural Netw. 15, 549-559 (2002)
60. Kaplan, F., Oudeyer, P.-Y.: The progress-drive hypothesis: An interpretation of early imitation. In: Nehaniv, C., Dautenhahn, K. (eds.) Models and Mechanisms of Imitation and Social Learning: Behavioural, Social and Communication Dimensions, pp. 361-377. Cambridge University Press, Cambridge (2007)
61. Kemp, C., Edsinger, A.: What can i control?: The development of visual categories for a robots body and the world that it influences. In: In 5th IEEE International Conference on Development and Learning (ICDL-06), Special Session on Autonomous Mental Development (2006)
62. Khatib, O.: A unified approach for motion and force control of robot manipulators: The operational space formulation. IEEE J. Robot. Autom. 3(1), 43-53 (1987)
63. Konczak, J., Borutta, M., Dichgans, J.: The development of goal-directed reaching in infants. Learning to produce task-adequate patterns of joint torque. Exp. Brain Res. 106(1), 156-168 (1997)
64. Kumar, S., Narasimhan, K., Patwardhan, S., Prasad, V.: Experiment design, identification and control in large-scale chemical processes. In: The 2010 International Conference on Modelling, Identification and Control (ICMIC), pp. 155-160 (2010)
65. Lee, M., Meng, Q., Chao, F.: Staged competence learning in developmental robotics. Adap. Behav. 15(3), 241-255 (2007)
66. Lee, W.: Neuromotor synergies as a basis for coordinated intentional action. J. Mot. Behav. 16, 135-170 (1984)
67. Lopes, M., Melo, F., Montesano, L.: Active learning for reward estimation in inverse reinforcement learning. In: Proceedings of European Conference on Machine Learning (ECML/PKDD) (2009)
68. Lopes, M., Oudeyer, P.-Y.: Active learning and intrinsically motivated exploration in robots: Advances and challenges (guest editorial): IEEE Trans. Auton. Mental Dev. 2(2), 65-69 (2010)
69. Lungarella, M., Metta, G., Pfeifer, R., Sandini, G.: Developmental robotics: A survey. Connect. Sci. 15(4), 151-190 (2003)
70. Ly, O., Lapeyre, M., Oudeyer, P.-Y.: Bio-inspired vertebral column, compliance and semi-passive dynamics in a lightweight robot. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011) (2011)
71. Ly, O., Oudeyer, P.-Y.: Acroban the humanoid: Playful and compliant physical child-robot interaction. In: ACM Siggraph Emerging Technologies, pp. 1-1 (2010)
72. MacNeilage, P.: The Origin of Speech. Oxford University Press, Oxford (2008)
73. Meltzoff, A., Moore, M.: Imitation of facial and manual gestures by human neonates. Science 198 (4312), 75-8 (1977)
74. Merrick, K.E.: Novelty and beyond: Towards combined motivation models and integrated learning architectures. In: Baldassarre, G., Mirolli, M. (eds.) Intrinsically Motivated Learning in Natural and Artificial Systems, pp. 209-233. Springer, Berlin (2012)
75. Meyer, J.A., Wilson, S.W. (eds.): A Possibility for Implementing Curiosity and Boredom in ModelBuilding Neural Controllers. MIT/Bradford Books, Cambridge (1991)
76. Mirolli, M., Baldassarre, G.: Functions and mechanisms of intrinsic motivations: The knowledge versus competence distinction. In: Baldassarre, G., Mirolli, M. (eds.) Intrinsically Motivated Learning in Natural and Artificial Systems, pp. 47-72. Springer, Berlin (2012)
77. Modayil, J., Pilarski, P., White, A., Degris, T., Sutton, R.: Off-policy knowledge maintenance for robots. In: Proceedings of Robotics Science and Systems Workshop (Towards Closing the Loop: Active Learning for Robotics) (2010)
78. Montgomery, K.: The role of exploratory drive in learning. J. Comp. Physiol. Psychol. 47, 60-64 (1954)
79. Moore, A.: Fast, robust adaptive control by learning only forward models. In: Advances in Neural Information Processing Systems, Vol. 4 (1992)
80. Muja, M., Lowe, D.: Fast approximate nearest neighbors with automatic algorithm. In: International Conference on Computer Vision Theory and Applications (VISAPP'09) (2009)
81. Ng, A.Y., Russell, S.: Algorithms for inverse reinforcement learning. In: Proceedings of the 17th International Conference on Machine Learning, pp. 663-670. Morgan Kaufmann, San Francisco (2000)
82. Nguyen, M., Baranes, A., Oudeyer, P.-Y.: Bootstrapping intrinsically motivated learning with human demonstrations. In: Proceedings of IEEE ICDL-Epirob 2011 (2011)
83. Nguyen-Tuong, D., Peters, J.: Model learning in robotics: A survey. Cogn. Process. 12(4), 319-340 (2011)
84. Oudeyer, P.-Y.: On the impact of robotics in behavioral and cognitive sciences: From insect navigation to human cognitive development. IEEE Trans. Auton. Mental Dev. 2(1), 2-16 (2010)
85. Oudeyer, P.-Y. Kaplan, F.: The discovery of communication. Connect. Sci. 18(2), 189-206 (2006)
86. Oudeyer, P.-Y. Kaplan, F.: What is intrinsic motivation? A typology of computational approaches. Front. Neurorobot. 1, 6 (2007)
87. Oudeyer, P.-Y. Kaplan, F.: How can we define intrinsic motivations? In: Proceedings of the 8th Conference on Epigenetic Robotics (2008)
88. Oudeyer, P.-Y., Kaplan, F., Hafner, V.: Intrinsic motivation systems for autonomous mental development. IEEE Trans. Evol. Comput. 11(2), 265-286 (2007)
89. Oudeyer, P.-Y., Ly, O., Rouanet, P.: Exploring robust, intuitive and emergent physical human-robot interaction with the humanoid acroban. In: Proceedings of IEEE-RAS International Conference on Humanoid Robots (2011)
90. Paul, C.: Morphology and computation. In: Proceedings of the International Conference on the Simulation of Adaptive Behaviour (2004)
91. Peters, J., Schaal, S.: Natural actor critic. Neurocomputing 71, 1180-1190 (2008)
92. Pfeifer, R., Bongard, J.C.: How the Body Shapes the Way We Think: A New View of Intelligence. MIT/Bradford Books, Cambridge (2006)
93. Pfeifer, R., Lungarella, M., Iida, F.: Self-organization, embodiment, and biologically inspired robotics. Science 318, 1088-1093 (2007)
94. Pfeifer, R., Scheier, C.: Understanding Intelligence. MIT, Boston (1999)
95. Piaget, J.: The Origins of Intelligence in Childhood. International University Press, New York (1952)
96. Redgrave, P., Gurney, K., Stafford, T., Thirkettle, M., Lewis, J.: The role of the basal ganglia in discovering novel actions. In: Baldassarre, G., Mirolli, M. (eds.) Intrinsically Motivated Learning in Natural and Artificial Systems, pp. 129-149. Springer, Berlin (2012)
97. Ring, M.: Continual learning in reinforcement environments. Ph.D. Thesis, University of Texas at Austin, Austin (1994)
98. Rochat, P.: Object manipulation and exploration in 2- to 5-month-old infants Dev. Psychol. 25, 871-884 (1989)
99. Rolf, M., Steil, J., Gienger, M.: Goal babbling permits direct learning of inverse kinematics. IEEE Trans. Auton. Mental Dev. 2(3), 216-229 (2010)
100. Ryan, R.M., Deci, E.L.: Intrinsic and extrinsic motivations: Classic definitions and new directions. Contem. Educ. Psychol. 25(1), 54-67 (2000)
101. Schaal, S., Atkeson, C.G.: Robot juggling: An implementation of memory-based learning. Control Syst. Mag. 57-71 (1994)
102. Schaal, S., Atkeson, C.G.: Robot learning by nonparametric regression, In: Proceedings of Intelligent Robots and Systems 1994 (IROS 94) pp. 137-153 (1995)
103. Schembri, M., Mirolli, M., Baldassare, G.: Evolving internal reinforcers for an intrinsically motivated reinforcement learning robot. In: Demiris, Y., Scassellati, B., Mareschal, D. (eds.) Proceedings of the 6th IEEE International Conference on Development and Learning (ICDL2007) (2007a)
104. Schembri, M., Mirolli, M., G., B.: Evolution and learning in an intrinsically motivated reinforcement learning robot. In: Springer (ed.) Advances in Artificial Life. Proceedings of the 9th European Conference on Artificial Life, Berlin, pp. 294-333 (2007b)
105. Schlesinger, M.: Heterochrony: It's (all) about time! In: Studies, L.U.C. (ed.) Proceedings of the Eighth International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, Sweden, pp. 111-117 (2008)
106. Schlesinger, M.: Investigating the origins of intrinsic motivations in human infants. In: Baldassarre, G., Mirolli, M. (eds.) Intrinsically Motivated Learning in Natural and Artificial Systems, pp. 367-392. Springer, Berlin (2012)
107. Schmidhuber, J.: Curious model-building control systems. Proc. Int. Joint Conf. Neural Netw. 2, 1458-1463 (1991)
108. Schmidhuber, J.: Exploring the predictable. In: Ghosh, S., Tsutsui, S. (eds.) Advances in Evolutionary Computing: Theory and Applications, pp. 579-612. Springer, New York (2002)
109. Schmidhuber, J.: Optimal artificial curiosity, developmental robotics, creativity, music, and the fine arts. Connect. Sci. 18(2), 173-187 (2006)
110. Schmidhuber, J.: Formal theory of creativity. IEEE Trans. Auton. Mental Dev. 2(3), 230-247 (2010)
111. Schmidhuber, J.: Maximizing fun by creating data with easily reducible subjective complexity. In: Baldassarre, G., Mirolli, M. (eds.) Intrinsically Motivated Learning in Natural and Artificial Systems, pp. 95-128. Springer, Berlin (2012)
112. Scholz, J., Klein, M., Behrens, T., Johansen-Berg, H.: Training induces changes in white-matter architecture. Nat. Neurosci. 12(11), 1367-1368 (2009)
113. Sekuler, R., Blake, R.: Perception. McGraw-Hill, New York (1994)
114. Sigaud, O., Sala͡n, C., Padois, V.: On-line regression algorithms for learning mechanical models of robots: A survey. Robot. Auton. Syst. 59(12), 1115-1129 (2011)
115. Singh, S., Lewis, R., Barto, A., Sorg, J.: Intrinsically motivated reinforcement learning: An evolutionary perspective. IEEE Trans. Auton. Mental Dev. 2(2), 70-82 (2010)
116. Stout, A., Barto, A.: Competence based intrinsic motivation. In: Proceedings of IEEE International Conference on Development and Learning (ICDL 2010) (2010)
117. Sutton, R.: Integrated architectures for learning, planning, and reacting based on approximating integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In: Proceedings of the International Machine Learning Conference, pp. 212-218 (1990)
118. Sutton, R., Barto, A.: Reinforcement learning: An introduction. MIT, Cambridge (1998)
119. Sutton, R., Precup, D., Singh, S.: Between mdpss and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artif. Intell. 112, 181-211 (1999)
120. Szita, I., Lorincz, A.: The many faces of optimism: A unifying approach. In: Proceedings of ICML'08 (2008)
121. Thomaz, A., Breazeal, C.: Experiments in socially guided exploration: Lessons learned in building robots that learn with and without human teachers. Connect. Sci. 20(2-3), 91-110 (2008)
122. Thrun, S.: The role of exploration in learning control. In: White, D., Sofge, D. (eds.) Handbook for Intelligent Control: Neural, Fuzzy and Adaptive Approaches. Van Nostrand Reinhold, Florence (1992)
123. Thrun, S., Moller, K.: Active exploration in dynamic environments. In: J. Moody, S., Hanson, R.L. (ed.) Proceedings of the Advances of Neural Information Processing Systems, Vol. 4 (1992)
124. Ting, L., McKay, J.: Neuromechanics of muscle synergies for posture and movement. Curr. Opin. Neurobiol. 17, 622-628 (2007)
125. Tong, S., Chang, E.: Support vector machine active learning for image retrieval. In: Proceedings of the Ninth ACM International Conference on Multimedia, MULTIMEDIA'01, pp. 107-118. ACM (2001)
126. Turkewitz, G., Kenny, P.: The role of developmental limitations of sensory input on sensory/perceptual organization. J. Dev. Behav. Pediatr. 6(5), 302-306 (1985)
127. Weiss, E., Flanders, M.: Muscular and postural synergies of the human hand. J. Neurophysiol. 92, 523-535 (2004)
128. Weng, J., McClelland, J., Pentland, A., Sporns, O., Stockman, I., Sur, M., Thelen, E.: Autonomous mental development by robots and animals. Science 291, 599-600 (2001)
129. White, R.: Motivation reconsidered: The concept of competence. Psychol. Rev. 66, 297-333 (1959)
130. Whitehead, S.: A Study of Cooperative Mechanisms for Faster Reinforcement Learning. Tr-365, University of Rochester, Rochester (1991)
131. Wiering, M., Schmidhuber, J.: Hq-learning. Adap. Behav. 6, 219-246 (1997)
132. Wundt, W.: Grundzuge der physiologischen Psychologie. Engelmann, Leipzig (1874)
133. Yokoi, H., Hernandez, A., Katoh, R., Yu, W., Watanabe, I., Maruishi, M.: Mutual adaptation in a prosthetics application. In: Embodied Artificial Intelligence. LNAI, Vol. 3139. Springer, Heidelberg (2004)
134. Ziegler, M., Iida, F., Pfeifer, R.: Cheap underwater locomotion: Roles of morphological properties and behavioural diversity. In: Proceedings of the International Conference on Climbing and Walking Robots (2006)