Abstract
From teaching in labs to training for assembly, a role that robots are expected to play is to instruct their users in completing physical tasks. While instruction requires a range of capabilities, such as use of verbal and nonverbal language, a fundamental requirement for an instructional robot is to provide its students with instructions in a way that maximizes their task performance. In this paper, we present an autonomous instructional robot and investigate how different instructional strategies affect user performance and experience. Our analysis of human instructor–trainee interactions identified two key instructional strategies: (1) groupinginstructions together and (2) summarizing the outcome of subsequent instructions. We implemented these strategies into a humanlike robot that autonomously instructed its users in a pipe-assembly task. To achieve autonomous instruction, we also developed a repair mechanism that enabled the robot to correct mistakes and misunderstandings. An evaluation of the instructional strategies in a human–robot interaction study showed that employing the grouping strategy resulted in faster task completion and increased rapport with the robot, although it also increased the number of task breakdowns. A comparison of our results with the human instructor–trainee interactions revealed many similarities, areas where our model for robot instructors could be improved, and the nuanced ways in which human instructors use training strategies such as summarization. Our findings offer strong implications for the design of instructional robots and directions of future research.
DOI: 10.1007/s10514-015-9461-0
BibTex
@article{Saupp__2015, doi = {10.1007/s10514-015-9461-0}, url = {https://doi.org/10.1007%2Fs10514-015-9461-0}, year = 2015, month = {jul}, publisher = {Springer Science and Business Media {LLC}}, volume = {39}, number = {3}, pages = {313--329}, author = {Allison Saupp{\'{e}} and Bilge Mutlu}, title = {Effective task training strategies for human and robot instructors}, journal = {Autonomous Robots} }