Effects of Transparent Robot Intentions on Human Trust and Compliance in Decision-Making: The Role of Benevolent and Ulterior Intentions of Robots

Humans are more commonly relying on the assistance of advanced robots in decision-making processes and may follow robots’ suggestions depending on their understanding of how such suggestions are generated. To enhance human understanding, robots can communicate their (simulated) intentions, influencing the trust placed upon them. However, it remains uncertain whether and under what conditions robots’ simulated intentions could also negatively impact trust and compliance. Therefore, we conducted a laboratory experiment with 182 participants, exploring whether information about a robot’s potential benevolent intentions and ulterior motives increased or decreased trust and compliance with the robot’s suggestions, while also altering participants’ involvement levels in a decision task. The results of two 2x2x2 ANOVAs revealed that, regardless of the involvement level, the robot’s simulated ulterior motives decreased trust and compliance, while benevolent intentions did not significantly affect these outcomes. Thus, simulated intentions should be considered in the design of collaborative decision-making between humans and robots.