DocumentCode :
2957151
Title :
Human-Robot Interaction in an Unknown Human Intention Scenario
Author :
Awais, Muhammad ; Henrich, Dagmar
Author_Institution :
Coll. of Comput. Sci. & Inf. Studies, Gov. Coll. Univ. Faisalabad, Faisalabad, Pakistan
fYear :
2013
fDate :
16-18 Dec. 2013
Firstpage :
89
Lastpage :
94
Abstract :
In this paper an approach is introduced to human robot interaction in a known scenario with unknown human intentions. Initially, the robot reacts by copying the human action. As the human-robot interaction proceeds, the level of human-robot interaction improves. Before each reaction, the robot hypothesizes its potential actions and selects one that is found most suitable. The robot may also use the human-robot interaction history. Along with the history, the robot also considers the action randomness and heuristic based action predictions. As solution, a general reinforcement Learning (RL) based algorithm is proposed that suggests learning of human robot interaction in an unknown human intention scenario. A Particle Filter (PF) based algorithm is proposed to support the probabilistic action selection for human-robot interaction. The experiments for human-robot interaction are performed by a robotic arm involving the arrangement of known objects with unknown human intention. The task of the robot is to interact with the human according to the estimated human intention.
Keywords :
human-robot interaction; learning (artificial intelligence); particle filtering (numerical methods); PF based algorithm; RL based algorithm; action randomness; heuristic based action predictions; human action; human intention scenario; human-robot interaction; particle filter; potential actions; probabilistic action selection; reinforcement learning; History; Human-robot interaction; Probabilistic logic; Robot kinematics; Service robots; Trajectory; Human-Robot interaction; intention estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Frontiers of Information Technology (FIT), 2013 11th International Conference on
Conference_Location :
Islamabad
Print_ISBN :
978-1-4799-2293-2
Type :
conf
DOI :
10.1109/FIT.2013.24
Filename :
6717232
Link To Document :
بازگشت