Alle Publikationen

Erweiterte Suche öffnen

Treffer: 2

2016
Ehrlich, S.; Cheng, G. (2016) : A neuro-based method for detecting context-dependent erroneous robot action: 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids): Cancun, Mexico: IEEE, S. 477-482

DOI: https://doi.org/10.1109/HUMANOIDS.2016.7803318

Abstract: Validating appropriateness and naturalness of human-robot interaction (HRI) is commonly performed by taking subjective measures from human interaction partners, e.g. questionnaire ratings. Although these measures can be of high value for robot designers, they are very sensitive and can be inaccurate and/or biased. In this paper we propose and validate a neuro-based method for objectively validating robot behavior in HRI. We propose to detect from the electronencephalo-gram (EEG) of a human interaction partner, the perception of inappropriate / unexpected / erroneous robot behavior. To validate this method, we conducted an EEG experiment with a simplified HRI protocol in which a humanoid robot displayed context-dependent erroneous behavior from time to time. The EEG data taken from 13 participants revealed biologically plausible error-related potentials (ErrP) whose spatio-temporal distributions match well with related neuroscientific research. We further demonstrate that perceived erroneous robot action can reliably be modeled and detected from human EEG signals with classification accuracies on avg. 69.7±9.1%. These findings confirm principal feasibility of the proposed method and suggest that EEG-based ErrP detection can be used for quantitative evaluation and thus improvement of robot behavior.

Keywords: Angemessen(heit) (von Technik), Computers, context-dependent erroneous behavior, context-dependent erroneous robot action, EEG, Electroencephalography, electronencephalogram, error-related potentials, ErrP, HRI protocol, human interaction partners, Humanoid Robots, human-robot interaction, ieee xplore, Magnetic heads, neuro-based method, neurocontrollers, neuroscientific research, Protocols, robot behavior, robot designers, Robot sensing systems, spatio-temporal distributions
2009
Honarvar, A. R.; Ghasem-Aghaee, N. (2009) : An artificial neural network approach for creating an ethical artificial agent: 2009 IEEE International Symposium on Computational Intelligence in Robotics and Automation - (CIRA): Daejeon, Korea: IEEE, S. 290-295

DOI: https://doi.org/10.1109/CIRA.2009.5423190

Abstract: Autonomous robotic systems and intelligent artificial agents’ capability have advanced dramatically. Since the intelligent artificial agents have been developing more autonomous and human-like, the capability of them to make moral decisions becomes an important issue. In this work we developed an artificial neutral network which considered various effective factors for ethical assessment of an action to determine that if a behavior or an action is ethically permissible or not. We integrated this net to the BDI-agent model as a part of its reasoning process to behave ethically in various environments.

Keywords: AMA, Artificial ethical agent, Artificial intelligence, artificial neural network, artificial neural network approach, artificial neural networks, autonomous robotic systems, BDI-Agent, BDI-agent model, ethical artificial agent, ethical reasoning, Ethics, Humanoid Robots, Humans, ieee xplore, intelligent agent, intelligent artificial agents, intelligent robots, Intelligent Systems, machine ethics, Mobile robots, Moral & Ethik, multi-agent systems, neurocontrollers, reasoning process, Software agents, Turning

2016

2009

poliTE