TrustworthinessExplainabilitySafetycs.RO
Proceedings of the AI-HRI Symposium at AAAI-FSS 2020
Shelly Bagchi, Jason R. Wilson, Muneeb I. Ahmad, Christian Dondrup, Zhao Han, Justin W. Hart, Matteo Leonetti, Katrin Lohan, Ross Mead, Emmanuel Senft, Jivko Sinapov, Megan L. Zimmerman
October 26, 2020
arXiv.org
1 citations
Key Takeaways
-
Trust is essential for real-world AI and robot adoption. The proceedings emphasize that trust is "crucial for adoption of both AI and robotics, particularly when transitioning technologies from the lab to industrial, social, and consumer applications," indicating that building user confidence is not optional but fundamental to successful deployment.
-
Trust in AI and robotics requires a shared understanding. While trust is commonly associated with "predictability, reliability, inciting confidence, and meeting expectations," the symposium highlights that there is "no consensus definition" of trust, suggesting that stakeholders need clearer frameworks for what trustworthy AI-robot systems should actually look like in practice.
-
Explainability is a key component of trustworthy human-robot interaction. The proceedings dedicate a focused sub-session to explainable AI (XAI) for HRI, recognizing that helping humans understand how AI systems make decisions is critical to building appropriate trust in collaborative human-robot environments.
-
Trust at the intersection of AI and HRI is distinct and understudied. The symposium identifies a "growing need for research that lives directly at the intersection of AI and HRI," suggesting that trust in systems combining both AI and robotics may differ from trust in either technology alone and deserves dedicated research attention.