DocumentCode :
38862
Title :
Synthesizing Anticipatory Haptic Assistance Considering Human Behavior Uncertainty
Author :
Medina, Jose Ramon ; Lorenz, Tamara ; Hirche, Sandra
Author_Institution :
Dept. of Electr. Eng. & Inf. Technol., Tech. Univ. Munchen, Munich, Germany
Volume :
31
Issue :
1
fYear :
2015
fDate :
Feb. 2015
Firstpage :
180
Lastpage :
190
Abstract :
Intuitive and effective physical assistance is an essential requirement for robots sharing their workspace with humans. Application domains reach from manufacturing and service robotics via rehabilitation and mobility aids to education and training. In this context, assistance based on human behavior anticipation has shown superior performance in terms of human effort minimization. However, when a robot´s expectations mismatch a human intentions, undesired interaction forces appear incurring safety risks and discomfort. Human behavior prediction is, therefore, a crucial issue: It enables effective anticipation but potentially produces disagreements when prediction errors occur. In this paper, we present a novel control scheme for anticipatory haptic assistance where robot behavior adapts to prediction uncertainty. Following a data-driven stochastic modeling approach, robot assistance is synthesized solving a risk-sensitive optimal control problem, where the cost function and plant dynamics are affected by model uncertainty. The proposed approach is objectively and subjectively evaluated in an experiment with human users. Results indicate that our method outperforms other assistive control approaches in terms of perceived helpfulness and human effort minimization.
Keywords :
control system synthesis; haptic interfaces; human-robot interaction; optimal control; stochastic systems; anticipatory haptic assistance synthesis; assistive control approaches; control scheme; cost function; data-driven stochastic modeling approach; effective physical assistance; human behavior prediction; human behavior uncertainty; human effort minimization; intuitive physical assistance; model uncertainty; plant dynamics; prediction uncertainty; rehabilitation robotics; risk-sensitive optimal control problem; robot assistance; robot behavior; service robotics; stochastic optimal control; Cost function; Dynamics; Haptic interfaces; Robots; Trajectory; Uncertainty; Haptic assistance; learning by demonstration; physical human–robot interaction (pHRI); physical human???robot interaction (pHRI); risk-sensitive control; stochastic optimal control;
fLanguage :
English
Journal_Title :
Robotics, IEEE Transactions on
Publisher :
ieee
ISSN :
1552-3098
Type :
jour
DOI :
10.1109/TRO.2014.2387571
Filename :
7024134
Link To Document :
بازگشت