Posts Tagged ‘scrutable autonomous systems’

The Scrutable Autonomous Systems (SAsSy) project aims to enable the scrutiny of autonomous systems by allowing agents to generate plans through argument and dialogue, while justifying the purpose of each step within the joint plan. Humans or agent can then critique these plans by suggesting and justifying alternative courses of actions as needed, thus driving the planning process. In this way, a scrutable autonomous system can allow for both the collaborative generation of a plan, and for its simultaneous verification.

To achieve its goals, the SAsSy project seeks a post-doctoral researcher who will investigate argumentation and dialogue based approaches to generate, represent and reason about plans, factoring in explicit norms and goals. Argumentation provides a natural way of explaining the rationale for decisions and their justifications, while dialogue will allow for their incremental generation and modification. (more…)

Read Full Post »