The Dynamics of Human-Agent Trust with POMDP-Generated Explanations
暂无分享,去创建一个
Partially Observable Markov Decision Processes (POMDPs) enable optimized decision making by robots, agents, and other autonomous systems. This quantitative optimization can also be a limitation in human-agent interaction, as the resulting autonomous behavior, while possibly optimal, is often impenetrable to human teammates, leading to improper trust and, subsequently, disuse or misuse of such systems [1].
[1] Ning Wang,et al. The Impact of POMDP-Generated Explanations on Trust and Performance in Human-Robot Teams , 2016, AAMAS.
[2] Raja Parasuraman,et al. Humans and Automation: Use, Misuse, Disuse, Abuse , 1997, Hum. Factors.
[3] David V. Pynadath,et al. Building Trust in a Human-Robot Team with Automatically Generated Explanations , 2015 .