Monterey Bay Aquarium Research Institute

Daniel Borrajo, Ph.D.

Universidad III Carlos de Madrid

Incorporating Planning and Learning into Robots


Wednesday, March 12, 2008
Pacific Forum – 3:00 p.m.


The goal of the subfield of Artificial Intelligence called Planning & Scheduling is the development of software tools that generate plans of actions for physical (humans or robots) or software agents. Examples of successful deployment of this technology have been shown in tasks such as: robotics, military operations, and civil emergencies. Very efficient general algorithms exist that work independently of the task. However, in order to apply them to real-world tasks, such as robotics, there are two major configuration tasks that have to be performed manually: defining the actions model of the domain (what actions the robot can execute and what the effects of those actions are), and defining the domain specific knowledge to make the software efficient for that domain (when is it convenient to perform one action instead of another one). And this is what machine learning techniques can help with. I will cover some of these approaches as applied to robotics during the talk.


Next: April 2- John Hocevar