Unintended Behavior: A Security Robot Falls Victim to a Water Fountain - An Example of Safe and Secure AI

July 17, 2017

An instance of the Knightscope K5 security robot exhibited unforeseen behavior, running into a water fountain in Washington, DC. This AI incident underscores the importance of trustworthy AI and highlights the need for robust safety measures in AI systems. This AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM). JOIN US: Want to help prevent such incidents? Join us in shaping responsible AI governance.
Alleged deployer
knightscope
Alleged developer
knightscope
Alleged harmed parties
knightscope

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/68

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.