RBE 550

Offered Fall2023, Fall2024

Motion planning is the study of algorithms that reason about the movement of physical or virtual entities. These algorithms can be used to generate sequences of motions for many kinds of robots, robot teams, animated characters, and even molecules. This course will cover the major topics of motion planning including (but not limited to) planning for manipulation with robot arms and hands, mobile robot path planning with non-holonomic constraints, multi-robot path planning, high-dimensional sampling-based planning, and planning on constraint manifolds. Students will implement motion planning algorithms in open-source frameworks, read recent literature in the field, and complete a project that draws on the course material. The PR2 robot will be available as a platform for class projects. Physical robot platforms will be available for class projects.

Prerequisites: Undergraduate Linear Algebra, experience with 3D geometry, and significant programming experience.

RBE 577 (New!)

Offered Spring2024

This graduate-level course delves into the intersection of machine learning and robotics. The curriculum will explore the integration of contemporary learning techniques in robotic areas such as manipulation, navigation, planning, control, decision-making, and other pertinent challenges in robotics. Advanced deep learning techniques and their applications in robotics will be covered, including supervised learning (e.g., behavioral cloning, state prediction), reinforcement learning (e.g., actor-critic, visual foresight), and unsupervised/self-supervised methods (e.g., world model construction, learning forward dynamic models). In addition, the generalizability of these methods will be discussed, recent, and experimental studies will be conducted, examining the challenges of applying these techniques on physical systems.

Prerequisites: RBE 500 (Robotic Fundamendals) or equivalent.