16-843 Manipulation Algorithms

12 units, Carnegie Mellon University

This is an advanced graduatelevel class on the theory and algorithms that enable robots to physically manipulate their world, on their own or in collaboration with people. The class will first focus on functional aspects of manipulation, such as synthesizing robust and stable grasps for dexterous hands and motion planning in these spaces, as well as learning for manipulation, such as how to predict stable grasps from demonstration and experience. Moving forward, we will discuss additional requirements that arise from performing manipulation tasks collaboratively with people moving from purely functional aspects of motion to incorporating the human into the loop, and coordinating human and robot actions via understanding and expressing intent.

Prerequisites: none listed

Courseweave needs JavaScript to show sections, workloads and planning tools.