首页|George Mason University Reports Findings in Robotics (Human perceptions of socia l robot deception behaviors: an exploratory analysis)
George Mason University Reports Findings in Robotics (Human perceptions of socia l robot deception behaviors: an exploratory analysis)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Robotics is the subjec t of a report. According to news reporting originating in Fairfax, Virginia, by NewsRx journalists, research stated, “Robots are being introduced into increasin gly social environments. As these robots become more ingrained in social spaces, they will have to abide by the social norms that guide human interactions.” The news reporters obtained a quote from the research from George Mason Universi ty, “At times, however, robots will violate norms and perhaps even deceive their human interaction partners. This study provides some of the first evidence for how people perceive and evaluate robot deception, especially three types of dece ption behaviors theorized in the technology ethics literature: External state de ception (cues that intentionally misrepresent or omit details from the external world: e.g., lying), Hidden state deception (cues designed to conceal or obscure the presence of a capacity or internal state the robot possesses), and Superfic ial state deception (cues that suggest a robot has some capacity or internal sta te that it lacks). Participants (N = 498) were assigned to read one of three vig nettes, each corresponding to one of the deceptive behavior types. Participants provided responses to qualitative and quantitative measures, which examined to w hat degree people approved of the behaviors, perceived them to be deceptive, fou nd them to be justified, and believed that other agents were involved in the rob ots’ deceptive behavior. Participants rated hidden state deception as the most d eceptive and approved of it the least among the three deception types. They cons idered external state and superficial state deception behaviors to be comparably deceptive; but while external state deception was generally approved, superfici al state deception was not. Participants in the hidden state condition often imp licated agents other than the robot in the deception. This study provides some o f the first evidence for how people perceive and evaluate the deceptiveness of r obot deception behavior types. This study found that people people distinguish a mong the three types of deception behaviors and see them as differently deceptiv e and approve of them differently.”
FairfaxVirginiaUnited StatesNorth and Central AmericaEmerging TechnologiesMachine LearningNano-robotRobotRobotics
NETL
NSTL
