Designing Human-Agent Collaborations: Commitment, responsiveness, and support

Cila, N.

doi:10.1145/3491102.3517500

Designing Human-Agent Collaborations

Title

Designing Human-Agent Collaborations: Commitment, responsiveness, and support

Author

Cila, N. (TU Delft Human Information Communication Design)

Contributor

Lampe, Cliff (editor)
Barbosa, Simona (editor)

Date

2022

Abstract

With the advancements in AI, agents (i.e., smart products, robots, software agents) are increasingly capable of working closely together with humans in a variety of ways while benefiting from each other. These human-agent collaborations have gained growing attention in the HCI community; however, the field lacks clear guidelines on how to design the agents' behaviors in collaborations. In this paper, the qualities that are relevant for designers to create robust and pleasant human-agent collaborations were investigated. Bratman's Shared Cooperative Activity framework was used to identify the core characteristics of collaborations and survey the most important issues in the design of human-agent collaborations, namely code-of-conduct, task delegation, autonomy and control, intelligibility, common ground, offering help and requesting help. The aim of this work is to add structure to this growing and important facet of HCI research and operationalize the concept of human-agent collaboration with concrete design considerations.

Subject

autonomous agent
design
human-agent collaboration
Shared Cooperative Activity

To reference this document use:

http://resolver.tudelft.nl/uuid:b1f003cf-24f1-4eca-b78d-7fb2fc3458d0

DOI

https://doi.org/10.1145/3491102.3517500

Publisher

Association for Computing Machinery (ACM), New York, NY, USA

ISBN

978-1-4503-9157-3

Source

CHI 2022 - Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems