A course on creating capable cognitive robots, by combining mobility and decision layers
The goal of this unique summer school is to help catalyze the next generation of researchers in AI and robotics, to work together to develop robots that are capable at both the task and motion levels. Our school will help students become equally conversant in the methods of cognitive systems and robotics, and will help them to build bridges between robotics and AI methods. The intended audience for this summer school includes top graduate students, postdocs and junior researchers, from both the cognitive AI and Robotics disciplines.
The summer school offers advanced tutorials on major elements of cognitive robotics that are required to develop capable autonomous systems. Tutorials will center around the daily themes of robust execution, motion planning, activity planner, perception and manipulation, and planning under uncertainty and risk. This year, we have a new, transversal theme, which will impact all the others: learning. Five out of the sixteen speakers perform research at the crossover between learning, robotics and AI. Our students will get a chance to gain insight into imitation learning, learning to reach and grasp, hierarchical reinforcement learning and robust deep learning. Because tutorials alone are not enough to have a lasting impact, we complement the tutorials with hands on lab exercises featuring a novel robotic architecture. At the end of the week, students will participate in a Grand Challenge competition that will incorporate aspects of all the labs and allow students to demonstrate what they have learned.
As a feature of our summer school, we will introduce students to the Enterprise system, a decision layer architecture which combines various decision-making components for planning and execution. We will combine this system with the Robotics Operating System (ROS) as a mobility layer to combine the perception and mobility components. Together, Enterprise and ROS will used by the students during the labs and Grand Challenge. Students will also have the opportunity to test their software on different robotic hardware, building up to the use of a fleet of robots during the Grand Challenge.