Publication Details

Mixed-Initiative Negotiation: Facilitating Useful Interaction Between Agent/Owner Pairs

by Berry, P. and Donneau-Golencer, T. and Duong, K. and Gervasio, M. and Peintner, B. and Yorke-Smith, N.

in Proceedings of AAMAS’09 Workshop on Mixed-Initiative Multiagent Systems

Abstract

A mixed-initiative agent for personal time management interacts not only with its human owner but also with other agents and humans that share or depend on the same time commitments. The assistive capabilities of such an agent include the ability to provide information and context for its owner, negotiate on behalf of its owner, and understand when autonomous action is possible, preferred, or expedient. It must operate without losing the trust of its owner or negotiating partners. Since time management is intensely personal, each such human-agent pair will evolve its own characteristics and working practices. This position paper considers how an existing mixed-initiative adaptive time management agent, PTIME, can be extended to the multiagent negotiation setting. We discuss opportunities for facilitating personalized mixed-initiative negotiation protocols and adjustable autonomy through demonstration, instruction, and advice. In addition, we explore user interaction considerations including the provision of explanation to build trust by enabling the owner to understand and correct agent decisions and suggestions.

Electronic Copies

BibTeX

EndNote

Associated Projects

Cognitive Assistant that Learns and Organizes As part of DARPA’s Personalized Assistant that Learns (PAL) program, SRI and team members are working on developing a next-generation "Cognitive Agent that Learns and Organizes" (CALO).

AIC Personnel

	Name	Title	E-mail
	Berry, Pauline M	Alumnus
	Donneau-Golencer, Thierry David	Software Engineer
	Duong, Khang	Software Engineer II
	Gervasio, Melinda	Senior Computer Scientist
	Peintner, Bart	Sr. Computer Scientist
	Yorke-Smith, Neil	Computer Scientist