Robot Trustworthiness: Guidelines for Simulated Emotion
Well-justified human evaluations of autonomous robot trustworthiness require evidence from a variety of sources, including observation of robot behavior. Displays of affect by a robot that reflect important internal states not otherwise overtly visible could provide useful evidence for evaluation of robot agent trustworthiness.
As an analogy, the human limbic system, sometimes described as an ancient sub-cognitive system, drives human display of affect in a manner that is largely independent of purposeful behavior arising from cognition. Such displays of affect and corresponding attributions of emotion provide important social information that aids understanding and prediction of human behavior. Could the notion of an “artificial limbic system” provide similar useful insight into a robot’s internal state?
The value of affect signals for evaluation of robot trustworthiness depends on three crucial factors that require investigation:
- Correlation of affective signals to trust-related, measurable attributes of robot agent internal state;
- Fidelity in portrayal of emotion by the robot agent such that affective signals evoke human anthropomorphic social recognition;
- Correct human interpretation of the affective signals for justifiable modulation of beliefs about the robot agent.
This research topic explores these principles for robotic simulation of emotion with the goal of increasing human ability to make reasonable assessments of robot trustworthiness that result in appropriate reliance. This will require new methods for unobtrusive automatic internal assessment of robot cognitive states that are reflected dynamically and naturally in robot behavior just as they are in humans.
Atkinson, D.J. Robot Trustworthiness: Guidelines for Simulated Emotion. In HRI '15: ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts Proceedings. ACM (2015).
HRI-15 Poster Atkinson, Robot Trustworthiness: Guidelines for Simulated Emotion