This course explores the interdisciplinary field of Embodied AI, where intelligent agents interact with and learn from physical environments through perception, action, and adaptation. Students will dive into SOTA technologies in robotics, reinforcement learning, and multi-modal learning, with a focus on physical applications such as autonomous navigation, manipulation, and human-robot collaboration. The course integrates theoretical foundations with hands-on projects using simulation platforms and real robotic systems, while examining recent trends like foundation models for robotics, sim-to-real transfer, and humanoid robotic system. By the end, students will design and implement an Embodied AI system addressing a real-world challenge.

Final Exam

The examination will cover the general understanding for the whole technical theory and methodology and evaluate the student's problem-solving ability for the embodiment AI tasks.

Intended Students:

- Upper-level undergraduates or graduate students in computer science, robotics, electrical engineering, or related fields.

- Professionals seeking to transition into Embodied AI or robotics research and development.