Announcements
General Information
Times & Places
TuTh 3:30PM - 4:50PM, HSS 1315
Course Staff
| Name | ||
|---|---|---|
| Instructor | Hao Su | haosu@ucsd.edu |
| Co-Instructor | Jiayuan Gu | jigu@ucsd.edu |
| Co-Instructor | Tongzhou Mu | t3mu@ucsd.edu |
| Co-Instructor | Stone Tao | stao@ucsd.edu |
| Course Assistant | Minghua Liu | minghua@ucsd.edu |
Office Hours
- Instructor's Office Hour: For questions related to lectures, homework, etc. (starting April 11)
Thursday, 5:00 PM - 6:00 PM, CSE 4109. - TA's Office Hour: For general questions related to logistics, grading, etc. (starting April 17)
Wednesday, 5:00 PM - 6:00 PM, CSE 4109.
Overview
This is a course for senior undergrads and graduate students, covering core concepts and algorithms in classical robotics and the more modern learning-based methods for robotics. We assume that the course takers have already taken certain deep learning courses, and are interested in how to train a robot that can interact with the physical world by machine learning methods. The first half of this course covers basic concepts and algorithms of robotics, and the second half introduces the basic concepts, algorithms, and research trends of reinforcement learning.
One feature of this course is that, we will instruct the students to build an armed robot in a simulated virtual environment through programming assignments. For the final project, we ask students to compete in a table-top object organization challenge using the built robot.
Prerequisites
- Strong background in calculus and linear algebra.
- Project experience in deep learning.
- Familiar with Newtonian mechanics.
- Proficient with Python.
- Experience in physical simulation is a plus.
Enrollment
To apply for enrollment, you need to fill in the Google Form at the course announcement page of CSE.Grading (tentative)
The course includes mandatory homeworks, course projects, and optional homeworks. The load of the course will be relatively heavy.Syllabus
The planned syllabus is as below. Certain contents may be added or removed based upon the interactions in class and other situations.
- Reinforcement Learning
- Concepts of RL
- RL as Optimization
- Long-horizon RL
- Generalizable RL
- Classic Robotics
- SE(3) Geometry
- Robot kinematics
- Robot-Object Interaction
- Optimal Control
- Physical Simulation
Acknowledgements
Thank Sapien for support.