Academics
  /  
Courses
  /  
Descriptions
COMP_SCI 469: Machine Learning and Artificial Intelligence for Robotics


VIEW ALL COURSE TIMES AND SESSIONS

Prerequisites

Graduate-level standing (or permission of instructor) for the maths, some programming experience (in Matlab okay).

Description

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 COMP_SCI 348 or COMP_SCI 349. Course evaluation will be largely project-based.

Cross-listed with MECH_ENG 469

COURSE COORDINATORProf. Brenna Argall

PREREQUISITES: Graduate-level standing (or permission of instructor) for the maths, some programming experience (in Matlab okay).

REQUIRED TEXTS: Xandu has created a special textbook comprised of custom reprints, available at the bookstore.

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, Expertsstyle
  • Week 3 : ML: Programming, Genetic Algorithms
  • Week 4 : ML: InstancebasedLearning
  • Week 5 : ML: Reinforcement Learning
  • Week 6 : AI: Planning
  • Week 7 : AI: Search, BehaviorbasedRobotics
  • Week 8 : Project presentations
  • Week 9 : Project presentations, Special topics