ECE 59500 - Architectures and Algorithms for Autonomy
Course Details
Lecture Hours: 1 Credits: 1
Areas of Specialization:
- Automatic Control
Counts as:
- EE Elective
- CMPE Selective - Special Content
Experimental Course Offered:
Spring 2025
Campus/Online:
On-campus and online
Requisites:
ECE 20875
Requisites by Topic:
Python
Catalog Description:
This one-credit course will provide an introduction to some key architectures and algorithms for autonomous and automated systems. It begins with a treatment of logical representations (i.e., finite state machines and decision trees). A number of planning algorithms are then introduced at a high level, and the foundational mathematical concepts of optimization-based methods for planning are presented in more detail. Last, the course presents an introduction to some common algorithms for supervised and unsupervised machine learning in the context of autonomous systems.
Required Text(s):
None.
Recommended Text(s):
- Engineering Design Optimization , Martins, J. R. R. A. and Ning, A. , Cambridge University Press , 2022
- Introduction to Autonomous Mobile Robots , Siegwart, R. and Nourbaksh, I. R. , The MIT Press , 2004
- Planning Algorithms , LaValle, S. M. , Cambridge University Press , 2006
Learning Outcomes
A student who successfully fulfills the course requirements will have demonstrated an ability to:
- An ability to define and analyze finite state machines
- An ability to define and implement common graph-based path planning algorithms
- An ability to implement and apply sampling-based planning algorithms
- An ability to implement supervised and unsupervised learning algorithms to enable autonomous operation
Lecture Outline:
Week | Lecture Topics |
---|---|
1.5 | Logical Architectures: Motivation, Theory and Application of Finite State Machines and Decision Trees |
2.5 | Planning Algorithms: Foundations (i.e., Depth-First vs. Breadth-First, Shortest Path Algorithms, etc.), Common Planning Algorithms (e.g., Graph- Based Methods, Rapidly Exploring Random Trees, Potential Field Methods), and Optimization |
1 | Machine Learning: Supervised Learning (e.g., K-Nearest Neighbor Algorithm), Unsupervised Learning (e.g., K-Means Clustering Algorithm) |
Assessment Method:
Homework (11/2024)