Teaching robots social autonomy from in situ human guidance

Senft, Emmanuel, Lemaignan, Séverin, Baxter, Paul , Bartlett, Madeleine and Belpaeme, Tony (2019) Teaching robots social autonomy from in situ human guidance. Science Robotics, 4 (35). eaat1186. ISSN 2470-9476

Full content URL: http://doi.org/10.1126/scirobotics.aat1186

Teaching robots social autonomy from in situ human guidance
Accepted Manuscript
[img] PDF
ScienceRoboticsFinalSubmission.pdf - Whole Document

Item Type:Article
Item Status:Live Archive


Striking the right balance between robot autonomy and human control is a core challenge in social robotics, in both technical and ethical terms. On the one hand, extended robot autonomy offers the potential for increased human productivity and for the off-loading of physical and cognitive tasks. On the other hand, making the most of human technical and social expertise, as well as maintaining accountability, is highly desirable. This is particularly relevant in domains such as medical therapy and education, where social robots hold substantial promise, but where there is a high cost to poorly performing autonomous systems, compounded by ethical concerns. We present a field study in which we evaluate SPARC (supervised progressively autonomous robot competencies), an innovative approach addressing this challenge whereby a robot progressively learns appropriate autonomous behavior from in situ human demonstrations and guidance. Using online machine learning techniques, we demonstrate that the robot could effectively acquire legible and congruent social policies in a high-dimensional child-tutoring situation needing only a limited number of demonstrations while preserving human supervision whenever desirable. By exploiting human expertise, our technique enables rapid learning of autonomous social and domain-specific policies in complex and nondeterministic environments. Last, we underline the generic properties of SPARC and discuss how this paradigm is relevant to a broad range of difficult human-robot interaction scenarios.

Keywords:human-robot interaction, SPARC, interactive machine learning, educational robotics, autonomous robots
Subjects:G Mathematical and Computer Sciences > G760 Machine Learning
G Mathematical and Computer Sciences > G440 Human-computer Interaction
Divisions:College of Science > School of Computer Science
ID Code:38234
Deposited On:01 Nov 2019 14:49

Repository Staff Only: item control page