Skip to main content

Machine Learning and Artificial Intelligence for Robotics (469-0-1)

Instructors

Brenna Dee Argall
847/467-0862
Technological Institute, Rm A290, 2145 Sheridan Rd, EV CAMPUS

Meeting Info

Technological Institute L150: Tues, Thurs 12:30PM - 1:50PM

Overview of class

A coverage of artificial intelligence, machine learning and statistical estimation topics that are especially relevant for robot operation and robotics research. The focus is on robotics-relevant aspects of ML and AI that are not covered in depth in CS 348-0 or CS 349-0. Course evaluation will be largely project-based.

DETAILED COURSE TOPICS:

I. Introduction: Crash course in robotics: sensors and sensing, effectors and actuators, probability basics

II. State estimation and uncertainty filters

1. Bayes filters

2. Gaussian filters : Kalman, Information...

3. Nonparametric filters: Histogram, Particle...

III. Machine Learning

1. Neural Nets : perceptron, multi-layered networks...

2. Genetic Algorithms

3. Instance-based Learning : nearest neighbors, regression (linear, locally-weighted, kernel-based)...

4. Reinforcement Learning : Bellman, Q-learning, T-D learning, actor-critic...

5. Demonstration-based Learning

IV. Artificial Intelligence

1. Search

1. Uninformed

2. Informed : Greedy, A*, D*, heuristic functions...

3. Local/optimizing : gradient descent, hill-climbing, simulated annealing...

2. Planning

1. Navigational

2. Motion

WEEKLY SCHEDULE:

Week 0 : Introduction
Week 1 : State estimation and uncertainty filters
Week 2 : ML: Bayesian Learning, Linear Classifiers, Experts style
Week 3 : ML: Programming, Genetic Algorithms
Week 4 : ML: Instance-based Learning
Week 5 : ML: Reinforcement Learning
Week 6 : AI: Planning
Week 7 : AI: Search, Behavior based Robotics
Week 8 : Project presentations
Week 9 : Project presentations, Special topics

Registration Requirements

Graduate-level standing or permission of instructor. Some programming experience (MatLab is okay).