TY - JOUR
T1 - Online Learning to Approach a Person with No Regret
AU - Ahn, Hyemin
AU - Oh, Yoonseon
AU - Choi, Sungjoon
AU - Tomlin, Claire J.
AU - Oh, Songhwai
N1 - Funding Information:
Manuscript received February 15, 2017; accepted July 6, 2017. Date of publication July 20, 2017; date of current version August 17, 2018. This letter was recommended for publication by Associate Editor M. Howard and Editor D. Lee upon evaluation of the reviewers’ comments. This work was supported in part by the Basic Science Research Program through the National Research Foundation of Korea funded by the Ministry of Science, ICT & Future Planning (NRF-2017R1A2B2006136) and in part by the NSF CPS: Large: ActionWebs, Award 0931843. (Corresponding author: Songhwai Oh.) H. Ahn, Y. Oh, S. Choi, and S. Oh are with the Department of Electrical and Computer Engineering and the Automation and Systems Research Institute, Seoul National University, Seoul 08826, South Korea (e-mail: hyemin.ahn@cpslab.snu.ac.kr; yoonseon.oh@cpslab.snu.ac.kr; sungjoon. choi@cpslab.snu.ac.kr; songhwai@snu.ac.kr).
Publisher Copyright:
© 2016 IEEE.
PY - 2018/1
Y1 - 2018/1
N2 - Each person has a different personal space and behaves differently when another person approaches. Based on this observation, we propose a novel method to learn how to approach a person comfortably based on the person's preference while avoiding uncomfortable encounters. We propose a personal comfort field to learn each person's preference about an approaching object. A personal comfort field is based on existing theories in anthropology and personalized for each user through repeated encounters. We propose an online method to learn a personal comfort field of a user, i.e., personalized learning, based on the concept from the Gaussian process upper confidence bound and show that the proposed method has no regret asymptotically. The effectiveness of the proposed method has been extensively validated in simulation and real-world experiments. Results show that the proposed method can gradually learn the personalized approaching behavior preferred by the user as the number of encounters increases.
AB - Each person has a different personal space and behaves differently when another person approaches. Based on this observation, we propose a novel method to learn how to approach a person comfortably based on the person's preference while avoiding uncomfortable encounters. We propose a personal comfort field to learn each person's preference about an approaching object. A personal comfort field is based on existing theories in anthropology and personalized for each user through repeated encounters. We propose an online method to learn a personal comfort field of a user, i.e., personalized learning, based on the concept from the Gaussian process upper confidence bound and show that the proposed method has no regret asymptotically. The effectiveness of the proposed method has been extensively validated in simulation and real-world experiments. Results show that the proposed method can gradually learn the personalized approaching behavior preferred by the user as the number of encounters increases.
KW - Human robot interaction
KW - motion and path planning
KW - personalized learning
UR - http://www.scopus.com/inward/record.url?scp=85063309904&partnerID=8YFLogxK
U2 - 10.1109/LRA.2017.2729783
DO - 10.1109/LRA.2017.2729783
M3 - Article
AN - SCOPUS:85063309904
SN - 2377-3766
VL - 3
SP - 52
EP - 59
JO - IEEE Robotics and Automation Letters
JF - IEEE Robotics and Automation Letters
IS - 1
M1 - 7987073
ER -