TY - JOUR
T1 - Improving user specifications for robot behavior through active preference learning
T2 - framework and evaluation
AU - Wilde, Nils
AU - Blidaru, Alexandru
AU - Smith, Stephen L.
AU - Kulić, Dana
PY - 2020/5
Y1 - 2020/5
N2 - An important challenge in human–robot interaction (HRI) is enabling non-expert users to specify complex tasks for autonomous robots. Recently, active preference learning has been applied in HRI to interactively shape a robot’s behavior. We study a framework where users specify constraints on allowable robot movements on a graphical interface, yielding a robot task specification. However, users may not be able to accurately assess the impact of such constraints on the performance of a robot. Thus, we revise the specification by iteratively presenting users with alternative solutions where some constraints might be violated, and learn about the importance of the constraints from the users’ choices between these alternatives. We demonstrate our framework in a user study with a material transport task in an industrial facility. We show that nearly all users accept alternative solutions and thus obtain a revised specification through the learning process, and that the revision leads to a substantial improvement in robot performance. Further, the learning process reduces the variances between the specifications from different users and, thus, makes the specifications more similar. As a result, the users whose initial specifications had the largest impact on performance benefit the most from the interactive learning.
AB - An important challenge in human–robot interaction (HRI) is enabling non-expert users to specify complex tasks for autonomous robots. Recently, active preference learning has been applied in HRI to interactively shape a robot’s behavior. We study a framework where users specify constraints on allowable robot movements on a graphical interface, yielding a robot task specification. However, users may not be able to accurately assess the impact of such constraints on the performance of a robot. Thus, we revise the specification by iteratively presenting users with alternative solutions where some constraints might be violated, and learn about the importance of the constraints from the users’ choices between these alternatives. We demonstrate our framework in a user study with a material transport task in an industrial facility. We show that nearly all users accept alternative solutions and thus obtain a revised specification through the learning process, and that the revision leads to a substantial improvement in robot performance. Further, the learning process reduces the variances between the specifications from different users and, thus, makes the specifications more similar. As a result, the users whose initial specifications had the largest impact on performance benefit the most from the interactive learning.
KW - Cognitive HRI
KW - motion planning
UR - http://www.scopus.com/inward/record.url?scp=85082112880&partnerID=8YFLogxK
U2 - 10.1177/0278364920910802
DO - 10.1177/0278364920910802
M3 - Article
AN - SCOPUS:85082112880
VL - 39
SP - 651
EP - 667
JO - International Journal of Robotics Research
JF - International Journal of Robotics Research
SN - 0278-3649
IS - 6
ER -