Abstract
In the March 1942 issue of “Astounding Science Fiction”, Isaac Asimov for the first time enumerated his three laws of robotics. Decades later, researchers in agents and multiagent systems have begun to examine these laws for providing a useful set of guarantees on deployed agent systems. Motivated by unexpected failures or behavior degradations in complex mixed agent-human teams, this paper for the first time focuses on applying Asimov’s first two laws to provide behavioral guarantees in such teams. However, operationalizing these laws in the context of such mixed agent-human teams raises three novel issues. First, while the laws were originally written for interaction of an individual robot and an individual human, clearly, our systems must operate in a team context. Second, key notions in these laws (e.g. causing “harm” to humans) are specified in very abstract terms and must be specified in concrete terms in implemented systems. Third, since removed from science-fiction, agents or humans may not have perfect information about the world, they must act based on these laws despite uncertainty of information. Addressing this uncertainty is a key thrust of this paper, and we illustrate that agents must detect and overcome such states of uncertainty while ensuring adherence to Asimov’s laws. We illustrate the results of two different domains that each have different approaches to operationalizing Asimov’s laws.
Keywords
- Multiagent System
- Team Performance
- Human User
- Disaster Response
- Human Input
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Allen, J.F., Schubert, L.K., Ferguson, G., Heeman, P., Hwang, C.H, Kato, T., Light, M., Martin, N.G., Miller, B.W., Poesio, M., Traum, D.R.: The trains project: A case study in defining a conversational planning agent. Technical report, Rochester, NY, USA (1994)
Asimov, I.: Robot Visions (collection of robot stories). Byron Preiss Visual Publications Inc, New York (1990)
Crandall, J.W., Nielsen, C.W., Goodrich, M.A.: Towards predicting robot team performance. In: SMC (2003)
Gordon, D.F.: Asimovian adaptive agents. JAIR 13, 95–153 (2000), citeseer.ist.psu.edu/gordon00asimovian.html
CALO: Cognitive Agent that Learns and Organizes (2003), http://www.ai.sri.com/project/CALO , http://calo.sri.com
Littman, M.L., Kaelbling, L.P., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. AI Journal (1998)
Myers, K.: Advisable planning systems. In: Advanced Planning Technology (1996), citeseer.nj.nec.com/143915.html
Pynadath, D.V., Tambe, M.: Revisiting asimov’s first law: A response to the call to arms. In: Meyer, J.-J.C., Tambe, M. (eds.) ATAL 2001. LNCS (LNAI), vol. 2333, Springer, Heidelberg (2002)
Scerri, P., Pynadath, D., Tambe, M.: Towards adjustable autonomy for the real world. Journal of Artificial Intelligence Research 17, 171–228 (2002)
Scerri, P., Pynadath, D.V., Johnson, L., Rosenbloom, P., Schurr, N., Si, M., Tambe, M.: A prototype infrastructure for distributed robot-agent-person teams. In: Alonso, E., Kudenko, D., Kazakov, D. (eds.) Adaptive Agents and Multi-Agent Systems. LNCS (LNAI), vol. 2636, Springer, Heidelberg (2003)
Schurr, N., Marecki, J., Scerri, P., Lewis, J.P., Tambe, M.: The defacto system: Training tool for incident commanders. In: The Seventeenth Innovative Applications of Artificial Intelligence Conference (IAAI) (2005)
Schurr, N., Scerri, P., Tambe, M.: Impact of human advice on agent teams: A preliminary report. In: Workshop on Humans and Multi-Agent Systems at AAMAS (2003)
Varakantham, P., Maheswaran, R., Tambe, M.: Exploiting belief bounds: Practical pomdps for personal assistant agents. In: AAMAS (2005)
Weld, D., Etzioni, O.: The first law of robotics: A call to arms. In: AAAI, Seattle, Washington, AAAI Press, Menlo Park (1994), citeseer.ist.psu.edu/weld94first.html
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schurr, N., Varakantham, P., Bowring, E., Tambe, M., Grosz, B. (2007). Asimovian Multiagents: Applying Laws of Robotics to Teams of Humans and Agents. In: Bordini, R.H., Dastani, M., Dix, J., Seghrouchni, A.E.F. (eds) Programming Multi-Agent Systems. ProMAS 2006. Lecture Notes in Computer Science(), vol 4411. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71956-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-540-71956-4_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-71955-7
Online ISBN: 978-3-540-71956-4
eBook Packages: Computer ScienceComputer Science (R0)