MTRE 4820: Machine Learning for Robot Perception

3 Credit Hours

Prerequisite: MTRE 2710 and MATH 2203 and MATH 3260 and Engineering Standing Requirements
This course introduces the most important topics in the areas of machine learning and computer vision and their specific applications in robotics and mechatronics. The machine learning and computer vision algorithms are extensively verified with simulated and physical robots in the mechatronics lab. Students are trained for developing physical or virtual intelligent robot systems through integrating robot control and machine learning algorithms. Significant programming effort and lab hardware experience are expected.

Course Learning Outcomes
Students who successfully complete this course will be able to:
1. Develop a deep learning model to implement visual object recognition.
2. Have the ability to develop a computer vision software to acquire, modify and transform digital images.
3. Employ the clustering algorithm to classify a group of data or images.
4. Develop a robot decision-making system using the reinforcement learning algorithm.
5. Demonstrate how to integrate robot control with computer vision and machine learning algorithms to develop intelligent robot systems.