Reverse Psychology in Trust-Aware Human-Robot Interaction

To facilitate effective human-robot interaction (HRI), trust-aware HRI has been proposed, wherein the robotic agent explicitly considers human's trust during its planning and decision making. The success of depends on specification a dynamics model trust-behavior model. In this study, we proposed one novel model, namely reverse psychology compared it against commonly used disuse We examined how two models affect robot's optimal policy team performance. Results indicate that robot will deliberately “manipulate” under correct “manipulative” behavior, trust-seeking reward function facilitates establishment without significantly sacrificing