As we grow more reliant on AI systems for an increasing variety of applications in our lives, the need to understand such systems also becomes more a necessity, be it for improvement, trust, or legal liability.
AI planning is a subfield of artificial intelligence (AI) that focuses on developing algorithms and techniques for automatically generating plans or sequences of actions to achieve a specific goal.
AI planning has applications in various domains such as robotics, manufacturing, transportation, and logistics.
Despite its pervasive use AI generated plans can be difficult to understand and analyse due to their high level of complexity.
While there are many recent techniques to support plan explanation, visual aids for navigating this data are quite limited, often creating a barrier between users and techniques focused on abstract planning concepts and domain-related explanations.
In this session, we would like to show a visual analytics tool designed to help summarize and interact with plans, focusing on robotics domains. We will show how through the means of sophisticated visual encoding, designed with the user in mind, it is possible to quickly grasp vital information about the intricate interaction of all parts involved in a plan execution and how they link and relate to each other.
The demonstration is being run by Dr Gabriel Dias Cantareira, Visual Analytics Research Associate at King’s College London, and Dr Rita Borgo, Head of Human Centred Computing Group, Department of Informatics, King's College London.
This event is in-person only. Registration is not required.
This event is part of the King's Festival of Artificial Intelligence, running from Wednesday 24 to Sunday 28 May 2023, which brings together speakers, exhibits, demos and screenings in an exciting programme of events. Take a look at the other events here.