Trust-Aware Decision Making for Human-Robot Collaboration: Model Learning and Planning

被引:90
作者
Chen, Min [1 ]
Nikolaidis, Stefanos [2 ]
Soh, Harold [1 ]
Hsu, David [1 ]
Srinivasa, Siddhartha [3 ]
机构
[1] Natl Univ Singapore, 21 Lower Kent Ridge Rd, Singapore 119077, Singapore
[2] Univ Southern Calif, 3710 McClintock Ave, Los Angeles, CA 90089 USA
[3] Paul G Allen Ctr, Box 352350,185 E Stevens Way NE, Seattle, WA 98195 USA
基金
美国国家科学基金会; 美国国家卫生研究院;
关键词
Trust models; human-robot collaboration; partially observable Markov decision process (POMDP); MUTUAL ADAPTATION; PERFORMANCE; TASKS;
D O I
10.1145/3359616
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Trust in autonomy is essential for effective human-robot collaboration and user adoption of autonomous systems such as robot assistants. This article introduces a computational model that integrates trust into robot decision making. Specifically, we learn from data a partially observable Markov decision process (POMDP) with human trust as a latent variable. The trust-POMDP model provides a principled approach for the robot to (i) infer the trust of a human teammate through interaction, (ii) reason about the effect of its own actions on human trust, and (iii) choose actions that maximize team performance over the long term. We validated the model through human subject experiments on a table clearing task in simulation (201 participants) and with a real robot (20 participants). In our studies, the robot builds human trust by manipulating low-risk objects first. Interestingly, the robot sometimes fails intentionally to modulate human trust and achieve the best team performance. These results show that the trust-POMDP calibrates trust to improve human-robot team performance over the long term. Further, they highlight that maximizing trust alone does not always lead to the best performance.
引用
收藏
页数:23
相关论文
共 47 条
[1]  
[Anonymous], 2010, Advances in Neural Information Processing Systems
[2]  
Bai HY, 2015, IEEE INT CONF ROBOT, P454, DOI 10.1109/ICRA.2015.7139219
[3]  
Bandyopadhyay Tirthankar, 2013, ALGORITHMIC FDN ROBO, P475
[4]  
Barber Bernard., 1983, The Logic and Limits of Trust by Bernard Barber
[5]   Communicating with Unknown Teammates [J].
Barrett, Samuel ;
Agmon, Noa ;
Hazon, Noam ;
Kraus, Sarit ;
Stone, Peter .
21ST EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE (ECAI 2014), 2014, 263 :45-+
[6]   Stan: A Probabilistic Programming Language [J].
Carpenter, Bob ;
Gelman, Andrew ;
Hoffman, Matthew D. ;
Lee, Daniel ;
Goodrich, Ben ;
Betancourt, Michael ;
Brubaker, Marcus A. ;
Guo, Jiqiang ;
Li, Peter ;
Riddell, Allen .
JOURNAL OF STATISTICAL SOFTWARE, 2017, 76 (01) :1-29
[7]   Planning with Trust for Human-Robot Collaboration [J].
Chen, Min ;
Nikolaidis, Stefanos ;
Soh, Harold ;
Hsu, David ;
Srinivasa, Siddhartha .
HRI '18: PROCEEDINGS OF THE 2018 ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, 2018, :307-315
[8]   Cortical substrates for exploratory decisions in humans [J].
Daw, Nathaniel D. ;
O'Doherty, John P. ;
Dayan, Peter ;
Seymour, Ben ;
Dolan, Raymond J. .
NATURE, 2006, 441 (7095) :876-879
[9]  
DESAI M, 2012, THESIS
[10]  
Desai M, 2013, ACMIEEE INT CONF HUM, P251, DOI 10.1109/HRI.2013.6483596