 | Select the Course Number to get further detail on the course. Select the desired Schedule Type to find available classes for the course. The Schedule Type links will be available only when the schedule of classes is available for the selected term. |
| CS 55800 - Introduction To Robot Learning |
|
Credit Hours: 3.00. Intelligent robot systems are in high demand in many real-world tasks, leading to growing interest in designing scalable robot algorithms for automation. From improving healthcare systems to enhancing the manufacturing capacity of various industrial sectors, the role of Robotics has been acknowledged worldwide. They are now also being considered as necessary tools to build large-scale assistive technologies such as smart vehicles and delivery drones to improve people's quality of life. This course covers topics in robot motion planning, estimation, learning, and control to design algorithms for robots to safely interact with their environments and perform various challenging tasks under constraints. The first part of this course focuses on classical techniques such as search, sampling-based planning, PID control, Model Predictive Control (MPC), and Bayesian Kalman filters. The second part covers modern imitation learning and deep reinforcement learning techniques and their application to planning and decision-making in robotics. The course assumes students are familiar with basic concepts in linear algebra, optimization, elementary probability, statistics, data structures, and algorithms. Students are expected to have good programming and software development skills and have a working knowledge of Python.
3.000 Credit hours Syllabus Available Levels: Undergraduate, Graduate, Professional Schedule Types: Distance Learning, Lecture Offered By: College of Science Department: Computer Science Course Attributes: Upper Division May be offered at any of the following campuses: West Lafayette Learning Outcomes: 1. Formulate the robot motion planning and control problems and solve them using standard tools. (W, P, E) 2. Identify the robot constraints, define their degree of freedom, and formulate their dynamical models for control. (W, P, E) 3. Apply classical and modern robot planning and control techniques to complex robot systems like manipulators, autonomous cars, etc. (W, P, E) 4. Identify limitations in existing classical robot algorithms and understand how to avoid the musing Machine Learning. (W, P) 5. Understand and apply Deep Reinforcement Learning approaches to complex robot systems. (W, P, E) 6. Evaluate and assess current best practices and mechanisms for robot programming. (W, P) 7. Develop a skill for robot programming from perception to low-level control using state-of-the art methods. (W, P) |
 |