Human Responsibility for Autonomous Agents
Shneiderman, Ben
University of Maryland, College Park;
This paper appears in: Intelligent Systems, IEEE
Publication Date: March-April 2007
Volume: 22,
Issue: 2
On page(s): 60-61
ISSN: 1541-1672
Digital Object Identifier: 10.1109/MIS.2007.32
Current Version Published: 2007-03-26
Abstract
Automated or autonomous systems can sometimes fail harmlessly, but they can also destroy data, compromise privacy, and consume resources, such as bandwidth or server capacity. What's more troubling is that automated systems embedded in vital systems can cause financial losses, destruction of property, and loss of life. Controlling these dangers will increase trust while enabling broader use of these systems with higher degrees of safety. Obvious threats stem from design errors and software bugs, but we can't overlook mistaken assumptions by designers, unanticipated actions by humans, and interference from other computerized systems. This article is part of a special issue on Interacting with Autonomy.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
