Robotics and Reinforcement Learning
Course Code: Y2B2
ECTS Credits: 7.0
Course Description
This course introduces the foundations and real-world applications of robotics and reinforcement learning (RL). Students learn how autonomous agents can perceive, decide, and act within complex environments using reward-driven learning strategies. The course emphasizes practical, hands-on development of control policies for simulated robotic systems, blending key robotics principles with modern RL techniques.
Through guided self-study, coding exercises, and control tasks in a simulated digital twin of a robotic system, students explore how algorithms like PPO can be used to train agents to perform tasks such as grasping, navigation, and object interaction.
Course Content
- Introduction to Robotics and Autonomous Systems
- Components of Robotic Systems (Sensors, Actuators, Controllers)
- Coordinate Systems, Degrees of Freedom, and Kinematics
- Practical Applications of Robotics in Industry and Daily Life
- Introduction to Reinforcement Learning
- Key RL Concepts: Rewards, Policies, MDPs, Exploration vs. Exploitation
- Deep Reinforcement Learning with PPO and Stable Baselines 3
- Training Agents in Simulated Environments
- PID Control Fundamentals and Application
- Control System Tuning and Performance Evaluation
- Robotics and RL Integration for Real-World Tasks
Prerequisites
- Completion of all Year 1 courses in the Applied Data Science & AI programme.
Recommended Reading
- Reinforcement Learning: An Introduction by R. Sutton and A. Barto (2nd Ed.)