Leveraging human inputs in interactive machine learning for human robot interaction

Senft, Emmanuel and Lemaignan, Severin and Baxter, Paul E. and Belpaeme, Tony (2017) Leveraging human inputs in interactive machine learning for human robot interaction. In: ACM/IEEE International Conference on Human-Robot Interaction - HRI '17, 6 - 9 March 2017, Vienna, Austria.

Documents
17 HRI-LBR Emmanuel.pdf
[img]
[Download]
[img]
Preview
PDF
17 HRI-LBR Emmanuel.pdf - Whole Document

284kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

A key challenge of HRI is allowing robots to be adaptable, especially as robots are expected to penetrate society at large and to interact in unexpected environments with non- technical users. One way of providing this adaptability is to use Interactive Machine Learning, i.e. having a human supervisor included in the learning process who can steer the action selection and the learning in the desired direction. We ran a study exploring how people use numeric rewards to evaluate a robot's behaviour and guide its learning. From the results we derive a number of challenges when design- ing learning robots: what kind of input should the human provide? How should the robot communicate its state or its intention? And how can the teaching process by made easier for human supervisors?

Keywords:human-robot interaction, machine learning, interactive learning, learning robots
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:30192
Deposited On:02 Feb 2018 11:58

Repository Staff Only: item control page