Course positioning
CS 237A (AA 274A/EE 260A/ME 274A) is taught by Marco Pavone and is the core course on robot autonomy. It connects perception, localization, control, planning, and decision-making under uncertainty, with extensive hands-on ROS work.
What it covers
- Perception: sensors, features, vision/lidar
- Localization and SLAM: EKF, particle filters, graph optimization
- Nonlinear control: feedback linearization, MPC basics
- Motion planning: graph search, sampling-based planning, trajectory optimization
- Uncertainty: POMDPs, belief space
- ROS practice
- Project: make a robot complete a task autonomously
Prerequisites
CS 106A; CME 100 (linear algebra); CME 106 (probability).
Assessment & workload
Assignments plus a ROS project. Check the current syllabus for details.
Who it's for
Robotics, autonomous driving, drones, and embodied AI.
Study advice
Take CS 223A first or have rigid-body kinematics basics. Get familiar with ROS early.
Related courses
Official course description
Basic principles for endowing mobile autonomous robots with perception, planning, and decision-making capabilities. Algorithmic approaches for robot perception, localization, and simultaneous localization and mapping; control of non-linear systems, learning-based control, and robot motion planning; introduction to methodologies for reasoning under uncertainty, e.g., (partially observable) Markov decision processes. Extensive use of the Robot Operating System (ROS) for demonstrations and hands-on activities. Prerequisites: CS 106A or equivalent, CME 100 or equivalent (for linear algebra), and CME 106 or equivalent (for probability theory).