Model-based and model-free RL for robot control

Markov Decision Process (MDP)

Learning-based grasping and manipulation

Shared autonomy

Imitation learning

Grasping and Manipulation

Interaction-aware learning

TensorFlow

Reinforcement learning (RL)

Interactive Perception

Neural network

Learning-based perception

Reinforcement Learning from Human Feedback (RLHF)

AA 174B / AA 274B / CS 237B / EE 260B Principles of Robot Autonomy II Stanford University Winter 2023 This course provides a deeper understanding of robot autonomy principles, focusing on learning new skills and physical interaction with the environment and humans. It requires familiarity with programming, ROS, and basic robot autonomy techniques. This course teaches advanced principles for endowing mobile autonomous robots with capabilities to autonomously learn new skills and to physically interact with the environment and with humans. Concepts that will be covered in the course are: Reinforcement Learning (RL) and its relationship to optimal control, contact and dynamics models for prehensile and non-prehensile robot manipulation, as well as imitation learning and human intent inference. Students will learn the theoretical foundations for these concepts. With this course, students will obtain a fundamental understanding of
advanced principles of robot autonomy, including robot learning, physical interaction with
the environment, and interaction with humans. - Familiarity with ROS and basic techniques for robot autonomy (e.g., AA274A or
equivalent).
- Familiarity with programming (e.g., CS 106A or equivalent) and Python.
- College calculus, linear algebra (e.g., CME 100 or equivalent).
- Basic probability and statistics (e.g., CME 106 or equivalent).  There is no required textbook.

AA 174B / AA 274B / CS 237B / EE 260B Principles of Robot Autonomy II

Artificial Intelligence

Robotics

Model-based and model-free RL for robot control

1 courses cover this concept

AA 174B / AA 274B / CS 237B / EE 260B Principles of Robot Autonomy II