Rebellion and Disobedience in AI
(RaD-AI)

May 19 or 20, 2025
8:30 am -6:00 pm  EST
as part of AAMAS 2025


Rethinking the desired abilities and responsibilities of collaborative embodied agents: when and how should a robot rebel or disobey?

Important Dates :

TBD: Submissions deadline

TBD: Notifications

May 19 or 20, 2025: Workshop Day


Invited Speakers

Sarath Sreedharan

Department of Computer Science

Colorado State
University

Johnathan Mell

Department of Computer Science

University of Central Forida

In order to determine whether or not to follow a particular command, a RaD-AI agent must be able to assess what is the core objective of the human it serves and align its values accordingly.  For this purpose, knowing the human's current plan is highly relevant, thus making methods from the plan recognition and goal reasoning communities potentially useful. We accept submissions directly addressing RaD-AI, as well as other topics relevant for the development of RaD-AI, including but not limited to: 

- Plan Recognition

- Goal Reasoning 

- Value Alignment 

- Human-agent Interaction

- AI Safety

The Venue

Cordis Hotel Auckland

83 Symonds Street, Grafton

Auckland

New Zealand