CS226 Statistical Techniques in Robotics

Overview

CS 226 is a graduate-level course that introduces students to the fascinating world of probabilistic robotics.

Probabilistic robotics is a hot research area in robotics. In the 1980, the dominant paradigm in robotics software research was model-based. In the 1990s, the paradigm shifted to behavior-based. Now one of the key new direction in robotics takes place at the intersection of statistics and robotics. Statistical techniques define the state of the art in many robotic applications. They are robust in practice, and they also have a sound mathematical basis.

The goal of this course is to expose students to the basics in probabilistic robotics. Successful students will be able to understand the mainstream literature, derive and prove the correctness of statistical algorithms, and have gained in-depth experience with practical probabilistic algorithms.

As in past years, we seek to leverage student projects to a conference-publishable level.

Who Should Attend?

The course should be of interest to anyone seeking to develop robust robot software, and anyone who is interested in real-world applications of statistical theory. Students participating in this course will acquire the skill of developing robust software for robots operating in real-world environments, and understanding the mathematical underpinnings of their software. Even though this course focuses on mobile robotics, the techniques covered in this course apply to a much brooder range of embedded computer systems, equipped with sensor and actuators.

Prerequisites

This is a graduate-level course. Familiarity with basic statistical concepts (Bayes rule, PDFs, Kalman filters, continuous distributions...) will be helpful for this course, as will be hands-on experience with software development in C or C++. However, the most important prerequisite will be creativity and enthusiasm, and a desire to explore.