Abstract
In recent years, the role of social robots is gaining popularity in our society but still learning from humans is a challenging problem that needs to be addressed. This paper presents an experiment where, after teaching poses to a robot, a group of users are asked several questions whose answers are used to create feature filters in the robot’s learning space. We study how the answers to different types of questions affect the learning accuracy of a social robot when it is trained to recognize human poses. We considered three types of questions: “Free Speech Queries”, “Yes/No Queries”, and “Rank Queries”, building a feature filter for each type of question. Besides, we provide another filter to help the robot to reduce the effects of inaccurate answers: the Extended Filter. We compare the performance of a robot that learned the same poses with Active Learning (using the four feature filters) versus Passive Learning (without filters). Our results show that, despite the fact that Active Learning can improve the robot’s learning accuracy, there are some cases where this approach, using the feature filters, achieves significant worse results than Passive Learning if the user provides inaccurate feedback when asked. However, the Extended Filter has proven to maintain the benefits of Active Learning even when the user answers are not accurate.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
Questions and queries will be used indistinctly in this paper.
OpenNI website: http://structure.io/openni.
The original questions were asked in Spanish. Here we provide their translations.
More details about the evaluation process can be found in a previous contribution [9].
References
Alonso F, Gorostiza J, Salichs M (2013) Preliminary experiments on HRI for improvement the Robotic Dialog System (RDS). In: Robocity2030 11th Workshop: Robots Sociales. Leganes, Spain
Alonso-Martín F, Salichs MA (2011) Integration of a voice recognition system in a socia robot. Cybern Syst 42(4):215–245
Angluin D (1988) Queries and concept learning. Mach Learn 2(4):319–342
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Cakmak M, Chao C, Thomaz AL (2010) Designing interactions for robot active learners. IEEE Trans Auton Ment Dev 2(2):108–118
Cakmak M, Thomaz A L (2012) Designing robot learners that ask good questions. In: Proceedings of the seventh annual ACM/IEEE international conference on Human–Robot Interaction—HRI ’12. ACM Press, p 17
Cawley GC, Talbot NLC (2003) Efficient leave-one-out cross-validation of kernel fisher discriminant classifiers. Pattern Recognit 36(11):2585–2592
Chao C, Cakmak M, Thomaz AL (2010) Transparent active learning for robots. In: 2010 5th ACM/IEEE international conference on Human–Robot Interaction (HRI). IEEE, pp 317–324
Gonzalez-Pacheco V, Malfaz M, Fernandez F, Salichs MA (2013) Teaching human poses interactively to a social robot. Sensors 13(9):12406–12430
Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten I (2009) The WEKA data mining software: an update. ACM SIGKDD Explor Newsl 11(1):10–18
Johnson DO, Agah A (2009) Human robot interaction through semantic integration of multiple modalities, dialog management, and contexts. Int J Soc Robot 1(4):283–305
Johnson DO, Agah A (2013) Learning macro actions from instructional videos through integration of multiple modalities. Int J Soc Robot 5(1):53–73
Quigley M, Gerkey B, Conley K, Faust J, Foote T, Leibs J, Berger E, Wheeler R, Ng A (2009) ROS: an open-source Robot Operating System. In: Open-Source Software workshop of the international conference on robotics and automation (ICRA)
Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kaufmann series in machine learning. Morgan Kaufmann Publishers
Rosenthal S, Dey AK, Veloso M (2009) How robots’ questions affect the accuracy of the human responses. In: RO-MAN 2009—The 18th IEEE international symposium on robot and human interactive communication. IEEE, pp 1137–1142
Rosenthal S, Veloso M, Dey AK (2012) Acquiring accurate human responses to robots’ questions. Int J Soc Robot 4(2):117–129
Salichs M, Barber R, Khamis A, Malfaz M, Gorostiza J, Pacheco R, Rivas R, Corrales A, Delgado E, Garcia D (2006) Maggie: a robotic platform for human-robot social interaction. In: 2006 IEEE Conference on Robotics. Automation and Mechatronics. IEEE, Bangkok, pp 1–7
Settles B (2010) Active Learning Literature Survey. Computer Sciences Technical Report 1648, University of Wisconsin-Madison
Shevade SK, Keerthi SS, Bhattacharyya C, Murthy KRK (2000) Improvements to the SMO algorithm for SVM regression. IEEE Trans Neural Netw 11(5):1188–1193
Thomaz A, Breazeal C (2007) Robot learning via socially guided exploration. In: IEEE 6th international conference on development and learning, 2007. ICDL 2007. IEEE, pp 82–87
Thomaz A, Hoffman G, Breazeal C (2006) Reinforcement learning with human teachers: understanding how people want to teach robots. In: ROMAN 2006—the 15th IEEE international symposium on robot and human interactive communication. IEEE, pp 352–357
Thomaz AL, Breazeal C (2008) Experiments in socially guided exploration: lessons learned in building robots that learn with and without human teachers. Connect Sci 20(2–3):91–110
Acknowledgements
The research leading to these results has received funding from the ROBSEN jproject (Desarrollo de robots sociales para ayuda a mayores con deterioro cognitivo; DPI2014-57684-R) funded by Spanish Ministry of Economy and Competitiveness and from the RoboCity2030-III-CM project (Robtica aplicada a la mejora de la calidad de vida de los ciudadanos. fase III; S2013/MIT-2748), funded by Programas de Actividades I+D en la Comunidad de Madrid and cofunded by Structural Funds of the EU.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Gonzalez-Pacheco, V., Malfaz, M., Castro-Gonzalez, A. et al. Analyzing the Impact of Different Feature Queries in Active Learning for Social Robots. Int J of Soc Robotics 10, 251–264 (2018). https://doi.org/10.1007/s12369-017-0449-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12369-017-0449-0