Hostname: page-component-5db58dd55d-688nx Total loading time: 0 Render date: 2026-06-08T12:21:52.830Z Has data issue: false hasContentIssue false
  • English
  • Français

Parental scaffolding as a bootstrapping mechanism for learning grasp affordances and imitation skills

Published online by Cambridge University Press:  19 August 2014

Emre Ugur ,
Yukie Nagai ,
Hande Celikkanat  and
Erhan Oztop
Emre Ugur*
Affiliation:
Institute of Computer Science, University of Innsbruck, Innsbruck, Austria Advanced Telecommunications Research Institute, Kyoto, Japan
Yukie Nagai
Affiliation:
Graduate School of Engineering, Osaka University, Osaka, Japan
Hande Celikkanat
Affiliation:
Department of Computer Engineering, Middle East Technical University, Turkey
Erhan Oztop
Affiliation:
Advanced Telecommunications Research Institute, Kyoto, Japan Department of Computer Science, Ozyegin University, Istanbul, Turkey
*
*Corresponding author. E-mail: emre.ugur@uibk.ac.at
Get access Rights & Permissions [Opens in a new window]

Summary

Parental scaffolding is an important mechanism that speeds up infant sensorimotor development. Infants pay stronger attention to the features of the objects highlighted by parents, and their manipulation skills develop earlier than they would in isolation due to caregivers' support. Parents are known to make modifications in infant-directed actions, which are often called “motionese”7. The features that might be associated with motionese are amplification, repetition and simplification in caregivers' movements, which are often accompanied by increased social signalling. In this paper, we extend our previously developed affordances learning framework to enable our hand-arm robot equipped with a range camera to benefit from parental scaffolding and motionese. We first present our results on how parental scaffolding can be used to guide the robot learning and to modify its crude action execution to speed up the learning of complex skills. For this purpose, an interactive human caregiver-infant scenario was realized with our robotic setup. This setup allowed the caregiver's modification of the ongoing reach and grasp movement of the robot via physical interaction. This enabled the caregiver to make the robot grasp the target object, which in turn could be used by the robot to learn the grasping skill. In addition to this, we also show how parental scaffolding can be used in speeding up imitation learning. We present the details of our work that takes the robot beyond simple goal-level imitation, making it a better imitator with the help of motionese.

Keywords

Developmental roboticsAffordanceImitationParental scaffoldingMotionese

Information

Type
Articles
Information
Robotica , Volume 33 , Special Issue 5: Robotics in the Alpe-Adria-Danube Region (RAAD 2013) , June 2015 , pp. 1163 - 1180
Copyright
Copyright © Cambridge University Press 2014 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

1. Argall, B. D., Sauser, E. L. and Billard, A. G., “Tactile Guidance for Policy Refinement and Reuse,” Proceedings of the 9th IEEE International Conference on Development and Learning (2010) pp. 7–12.Google Scholar
2. Babic, J., Hale, J. and Oztop, E., “Human sensorimotor learning for humanoid robot skill synthesis,” Adapt. Behav. 19, 250–263 (2011).Google Scholar
3. Barrett, T. M. and Needham, A., “Developmental differences in infants' use of an object's shape to grasp it securely,” Developmental Psychobiology 50 (1), 97–106 (2008).CrossRefGoogle ScholarPubMed
4. Berk, L. E. and Winsler, A., “Scaffolding Children's Learning: Vygotsky and Early Childhood Education,” National Assoc. for Education (1995).Google Scholar
5. Bicchi, A. and Kumar, V., “Robotic Grasping and Contact: A Review,” Proceedings of the IEEE International Conference on Robotics and Automation (2000) pp. 348–353.Google Scholar
6. Billard, A., “Learning motor skills by imitation: A biologically inspired robotic model,” Cybern. Syst. 32, 155–193 (2000).Google Scholar
7. Brand, R. J., Baldwin, D. A. and Ashburn, L. A., “Evidence for ‘motionese’: Modifications in mothers' infant-directed action,” Developmental Sci. 5 (1), 72–83 (2002).Google Scholar
8. Breazeal, C., Learning by Scaffolding PhD Thesis, Elec. Eng. Comp. Sci. (MIT, Cambridge, MA, 1999).Google Scholar
9. Calinon, S., Guenter, F. and Billard, A., “On learning, representing, and generalizing a task in a humanoid robot,” IEEE Trans. Syst. Man Cybern. 37 (2), 286–298 (2007).Google Scholar
10. Carpenter, M., Call, J. and Tomasello, M., “Understanding ‘prior intentions’ enables two-year-olds to imitatively learn a complex task,” Child Dev. 73 (5), 1431–1441 (2002).Google Scholar
Şahin, E., Çakmak, M., Doğar, M. R., Ugur, E. and Üçoluk, G., “To afford or not to afford: A new formalization of affordances toward affordance-based robot control,” Adapt. Behav. 15 (4), 447–472 (2007).Google Scholar
12. Detry, R., Baçeski, E., Popović, M., Touati, Y., Krüger, N., Kroemer, O., Peters, J. and Piater, J., “Learning Continuous Grasp Affordances by Sensorimotor Exploration,” In: From Motor Learning to Interaction Learning in Robots (Springer, Berlin, 2010) pp. 451–465.Google Scholar
13. Detry, R., Kraft, D., Kroemer, O., Bodenhagen, L., Peters, J., Krüger, N. and Piater, J., “Learning grasp affordance densities,” Paladyn, 2 (1), 1–17 (2011).Google Scholar
14. Fernald, A., “Four-month-old infants prefer to listen to motherese,” Infant Behav. Dev. 8, 181–195 (1985).Google Scholar
15. Fischer, K., Foth, K., Rohlfing, K. J. and Wrede, B., “Mindful tutors: Linguistic choice and action demonstration in speech to infants and a simulated robot,” Interact. Stud. 12 (1), 134–161 (2011).Google Scholar
16. Gams, A., Ijspeert, A. J., Schaal, S. and Lenarcic, J., “On-line learning and modulation of periodic movements with nonlinear dynamical systems,” Auton. Robots 27 (1), 3–23 (2009).CrossRefGoogle Scholar
17. Gergely, G., Bekkering, H. and Kiraly, I., “Rational imitation in preverbal infants,” Nature 415, 755 (2002).Google Scholar
18. Goubeta, N., Rochat, P., Maire-Leblond, C. and Poss, S., “Learning from others in 9–18-month-old infants,” Infant Child Dev. 15, 161–177 (2006).Google Scholar
19. Haralick, R. M. and Shapiro, L. G., Computer and Robot Vision, Volume I (Addison-Wesley, New York, 1992).Google Scholar
20. Herzog, A., Pastor, P., Kalakrishnan, M., Righetti, L., Bohg, J., Asfour, T. and Schaal, S., “Learning of grasp selection based on shape-templates,” Auton. Robots 36 (1-2), 51–65 (2014).Google Scholar
21. Hodapp, R. M., Goldfield, E. C. and Boyatzis, C. J., “The use and effectiveness of maternal scaffolding in mother-infant games,” Child Dev. 55 (3), 772–781 (1984).Google Scholar
22. Kawato, M. and Samejima, K., “Efficient reinforcement learning: Computational theories, neuroscience and robotics,” Curr. Opin. Neurobiology 17, 205–212 (2007).Google Scholar
23. Koterba, E. A. and Iverson, J. M., “Investigating motionese: The effect of infant-directed action on infants' attention and object exploration,” Infant Behav. Dev. 32 (4), 437–444 (2009).Google Scholar
24. Kushida, D., Nakamura, M., Goto, S. and Kyura, N., “Human direct teaching of industrial articulated robot arms based on force-free control,” Artif. Life Robot. 5 (1), 26–32 (2001).Google Scholar
25. Masakata, N., “Motherese in a signed language,” Infant Behav. Dev. 15, 453–460 (1992).Google Scholar
26. Moore, B. and Oztop, E., “Robotic grasping and manipulation through human visuomotor learning,” Robot. Auton. Syst. 60, 441–451 (2012).Google Scholar
27. Murata, A., Gallese, V., Luppino, G., Kaseda, M. and Sakata, H.. “Selectivity for the shape, size, and orientation of objects for grasping in neurons of monkey parietal are AIP,” J. Neuropyhsiology 83 (5), 2580–2601, (2000).Google Scholar
28. Nagai, Y. and Rohlfing, K. J. “Computational analysis of motionese toward scaffolding robot action learning,” IEEE Trans. Auton. Mental Dev. 1 (1), 44–54 (2009).Google Scholar
29. Nagai, Y., Nakatani, A. and Asada, M., “How a RobotS Attention Shapes the Way People Teach,” Proceedings of the 10th International Conference on Epigenetic Robotics (2010), pp. 81–88.Google Scholar
30. Nagai, Y. and Rohlfing, K. J., “Can Motionese Tell Infants and Robots: What to Imitate?,” Proceedings of the 4th International Symposium on Imitation in Animals and Artifacts, AISB (2007) pp. 299–306.Google Scholar
31. Nagai, Y. and Rohlfing, K. J., “Parental Action Modification Highlighting the Goal versus the Means,” Proceedings of the IEEE 7th International Conference on Development and Learning (2008).Google Scholar
32. Nakanishi, J., Morimoto, J., Endo, G., Cheng, G., Schaal, S. and Kawato, M., “Learning from demonstration and adaptation of biped locomotion,” Robot. Auton. Syst. 47 (2), 79–91 (2004).Google Scholar
33. Nehaniv, C. L. and Dautenhah, D., “Like me? Measures of correspondence and imitation,” Cybern. Syst. 32, 11–51 (2011).Google Scholar
34. Pastor, P., Righetti, L., Kalakrishnan, M. and Schaal, S., “Online Movement Adaptation Based on Previous Sensor Experiences,” Proceedings of the 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE (2011) pp. 365–371.Google Scholar
35. Paulus, M., Hunnius, S., Vissers, M. and Bekkering, H., “Imitation in infancy: Rational or motor resonance?,” Child Dev. 82 (4), 1047–1057 (2011).CrossRefGoogle ScholarPubMed
36. Peters, J., Vijayakumar, S. and Schaal, S., “Reinforcement Learning for Humanoid Robotics,” Proceedings of the Third IEEE-RAS International Conference on Humanoid Robots (2003) pp. 1–20.Google Scholar
37. Rohlfing, K. J., Fritsch, J., Wrede, B. and Jungmann, T., “How Can Multimodal Cues from Child-Directed Interaction Reduce Learning Complexity in Robots?,” Adv. Robot. 20 (10), 1183–1199 (2006).Google Scholar
38. Saunders, J., Nehaniv, C., Dautenhahn, K. and Alissandrakis, A., “Self-imitation and environmental scaffolding for robot teaching,” Int. J. Adv. Robot. Syst. 4 (1), 109–124 (2007).Google Scholar
39. Saunders, J., Nehaniv, C. L. and Dautenhahn, K., “Teaching Robots by Moulding Behavior and Scaffolding the Environment,” Proceedings of the ACM SIGCHI/SIGART Conference on Human-robot Interaction (2006) pp. 118–125.Google Scholar
40. Saxena, A., Driemeyer, J. and Ng, A. Y., “Robotic grasping of novel objects using vision,” Int. J. Robot. Res. 27 (2), 157–173 (2008).Google Scholar
41. Schaal, S., “Is imitation learning the route to humanoid robots?,” Trends Cogn. Sci. 3 (6), 233–242 (1999).Google Scholar
42. Schaal, S., “Dynamic Movement Primitives-a Framework for Motor Control in Humans and Humanoid Robotics,” In: Adaptive Motion of Animals and Machines. (Springer, 2006) pp. 261–280.Google Scholar
43. Tamis-LeMonda, C. S., Kuchirko, Y. and Tafuro, L., “From action to interaction: Infant object exploration and mothers' contingent responsiveness (june 2013),” IEEE Trans. Auton. Mental Dev. 5 (3) (2013).Google Scholar
44. Tomasello, M., “Do Apes Ape?,” In: Social Learning in Animals: The Roots of Culture(Heyes, C. M. and Galef, B. G., eds.) (Academic Press, Inc., San Diego, CA, 1996) pp. 319–346.Google Scholar
45. Ude, A., Gams, A., Asfour, T. and Morimoto, J., “Task-specific generalization of discrete and periodic dynamic movement primitives,” IEEE Trans. Robot. 26 (5), 800–815 (2010).Google Scholar
46. Ugur, E., Celikkanat, H., Nagai, Y. and Oztop, E., “Learning to Grasp with Parental Scaffolding,” Proceedings of the IEEE International Conference on Humanoid Robotics (2011a) pp. 480–486.Google Scholar
47. Ugur, E., Oztop, E. and Sahin, E., “Goal emulation and planning in perceptual space using learned affordances,” Robot. Auton. Syst. 59 (7–8), 580–595 (2011b).Google Scholar
48. Ugur, E., Sahin, E. and Oztop, E., “Affordance Learning from Range Data for Multi-Step Planning,” Proceedings of the 9th International Conference on Epigenetic Robotics (2009) pp. 177–184.Google Scholar
49. Ugur, E., Sahin, E. and Oztop, E., “Self-discovery of Motor Primitives and Learning Grasp Affordances,” IEEE/RSJ International Conference on Intelligent Robots and Systems (2012) pp. 3260–3267.Google Scholar
van Elk, M., van Schie, H. T., Hunnius, S., Vesper, C. and Bekkering, H., “You'll never crawl alone: Neurophysiological evidence for experience-dependent motor resonance in infancy,” Neuroimage, 43 (4), 808–814 (2008).Google Scholar
51. Vandermeer, A., Vanderweel, F. and Lee, D., “The functional-significance of arm movements in neonates,” Science 267, 693–695 (1995).Google Scholar
52. Wood, D., Bruner, J. S. and Ross, G., “The role of tutoring in problem-solving,” J. Child Psychol. Psychiatry 17, 89–100 (1976).Google Scholar
53. Zukow-Goldring, P. and Arbib, M. A., “Affordances, effectivities, and assisted imitation: Caregivers and the directing of attention,” Neurocomputing 70, 2181–2193 (2007).Google Scholar