Modeling Active Learning in a Robot Collective

In this research, we model an active learning method on real robots that can visually learn from each other. For this purpose, we initially design an experiment scenario in which a teacher robot presents a simple classification task to a learner robot through which the learner robot can discriminate different colors based on a predefined lexicon. It is shown that, with passive learning, the learner robot is able to partially achieve the given task. Afterwards, we design an active learning procedure in which the learner robot can manifest what it understand from the presented information. Based on this manifestation, the teacher robot determines which parts of the classification system are misunderstood and it rephrases those parts. It is shown that, with the help of active learning procedure, the robots achieve a higher success rate in learning the simple classification task. In this way, we qualitatively analyze how active learning works and why it enhances learning.Keywords: Active Learning, Learning by Demonstration, Multi-Robot Group, Robot Learning.

PDF

___

[1] C. C. Bonwell, and J. A. Eison. “Active Learning: Creating Excitement in the Classroom,” 1991 ASHE-ERIC Higher Education Reports. ERIC Clearinghouse on Higher Education, The George Washington University, 1991.
[2] C. Kyriacou, “Active learning in secondary school mathematics,” British Educational Research Journal, vol. 18, no. 3, pp. 309- 318, 1992.
[3] A. Renkl, R. K. Atkinson, U. H. Maier, and R. Staley, “From example study to problem solving: Smooth transitions help learning,” The Journal of Experimental Education, vol. 70, no. 4, pp.293-315, 2002.
[4] C. L. Konopka, M. B. Adaime, and P. H. Mosele, “Active teaching and learning methodologies: some considerations,” Creative Education, vol. 6, no. 14, p.1536- 1545, 2015.
[5] M. Prince, “Does active learning work? A review of the research,” Journal of engineering education, vol. 93, no. 3, pp.223-231, 2004.
[6] D. R. Barnes, “Active learning,” Leeds University TVEI Support Project, 1989.
[7] R. M. Felder, and R. Brent, “Active learning: An introduction,” ASQ higher education brief, vol. 2, no. 4, pp.1-5, 2009.
[8] P. Laws, D. Sokoloff, and R. Thornton, “Promoting active learning using the results of physics education research,” UniServe Science News, 13, pp.14-19, 1999.
[9] S. Freeman, S. L. Eddy, M. McDonough, M. K. Smith, N. Okoroafor, H. Jordt, and M. P. Wenderoth, “Active learning increases student performance in science, engineering, and mathematics,” Proceedings of the National Academy of Sciences, vol. 111, no. 23, pp.8410-8415 2014.
[10] F. K. Marcondes, M. J. Moura, A. Sanches, R. Costa, P. O. de Lima, F. C. Groppo, M. E. Amaral, P. Zeni, K. C. Gaviao, and L. H. Montrezor, “A puzzle used to teach the cardiac cycle,” Advances in Physiology Education, vol. 39, no. 1, pp.27-31, 2015.
[11] M. Borrego, S. Cutler, M. Prince, C. Henderson, and J. E. Froyd, “Fidelity of implementation of research‐based instructional strategies (RBIS) in engineering science courses,” Journal of Engineering Education, vol. 102, no. 3, pp.394-425, 2013.
[12] R. S. Sutton, and A. G. Barto, “Introduction to reinforcement learning,” Cambridge: MIT press, 1998.
[13] R. Caruana, and A. Niculescu-Mizil, “An empirical comparison of supervised learning algorithms,” In Proceedings of the 23rd international conference on Machine learning, pp. 161-168, 2006.
[14] C. G. Atkeson, and S. Schaal, “Robot learning from demonstration,” In ICML vol. 97, pp. 12-20, 1997.
[15] Y. LeCun, Y. Bengio, and G. Hinton, G., “Deep learning,” Nature, vol. 521, no: 7553, pp.436-444, 2015.
[16] S. Kirby, “Spontaneous evolution of linguistic structure-an iterated learning model of the emergence of regularity and irregularity,” IEEE Transactions on Evolutionary Computation, vol. 5, no. 2, pp.102-110, 2001.
[17] F. Mondada, M. Bonani, X. Raemy, J. Pugh, C. Cianci, A. Klaptocz, S. Magnenat, J. C. Zufferey, D. Floreano, and A. Martinoli, “The e-puck, a robot designed for education in engineering,” In Proceedings of the 9th conference on autonomous robot systems and competitions, pp. 59-65. IPCB: Instituto Politécnico de Castelo Branco.
[18] M. D. Erbas, “The development of a robust symbolic communication system for robots via embodied iterated imitation,” Adaptive Behavior, vol. 27, no. 2, pp.137-156, 2019.
[19] L. Chen, and R. Ng, “On the marriage of lpnorms and edit distance,” In Proceedings of the Thirtieth international conference on Very large data bases, pp. 792-803, 2004.