Spring 2019 Course Descriptions

COMP 150-08 Probabilistic Robotics for HRI

J. Sinapov
TR 1:30-2:45, Halligan Hall 111B
H+ Block

This graduate-level course will introduce various techniques for probabilistic state estimation and examine their application to problems such as robot localization, mapping, perception, and planning in the context of Human-Robot Interaction. The course will also provide a problem-oriented introduction to relevant machine learning and computer vision techniques that are commonly used by robots interacting with humans. Topics include: Overview of mobile robotics (hardware, software architectures, sensors), probabilistic models of sensing and acting, Bayesian state estimation and filtering (e.g., Kalman and particle filters), localization and mapping, computer vision for robot perception (e.g., human activity recognition), and models of robot decision making and learning (e.g., Markov decision processes, reinforcement learning). The main components of the course include several programming assignments along with a final project. You will be able to use Turtlebot2 robots for homework and projects, along with any other robots (or robot simulators) you have access to through your current research activities.

Prerequisite: The course is programming-intensive and at a minimum, you should have 2+ years of solid C++ programming experience. Formal background in probability, statistics, and linear algebra is strongly recommended. For CS undergraduates, you are expected to have taken COMP 40 and another robotics course (e.g,, COMP 50: Autonomous Intelligent Robotics). For ME undergraduates, you are expected to have taken ME 80 Controls. If you're unsure whether you meet the requirements, talk to your instructor to decide if this course is right for you.


Back to Main Courses Page