Calendar

Topics: Robot Motion 1 [Slides]

• Introduction and overview
• Braitenberg vehicles
  • Reading on Braitenberg vehicles & simulator

Topics: Robot Perception 1 [Slides]

• Image processing fundamentals
  • Siegwart et al. Book: Chapter 4.3
• Filtering, convolution, edge detection
  • Correll Book: Chapter 6.3
• Hough transforms, RANSAC
  • Correll Book: Chapter 7.3
  • Siegwart et al. Book: Chapter 4.7

CANCELLED

Topics: Robot Motion 2 [Slides]

• Coordinate transforms
  • Correll Book: Chapter 3.1
• Kinematics
  • Correll Book: Chapter 3.2 and 3.4
  • Siegwart et al. Book: Chapter 3.2
• Feedback control
  • Correll Book: Chapter 3.5

Topics: Robot Perception 2 [Slides]

• State estimation, Bayes filters, Localization
  • Thrun et al. Book: Chapter 2.3, 2.4, 7.2, and 7.3
  • Correll Book: Chapter 9.2
• The Kalman filter
  • Thrun et al. Book: Chapter 3.2
  • Correll Book: Chapter 9.4
• The Particle filter
  • Thrun et al. Book: Chapter 4.2
  • Correll Book: Chapter 9.3

Topics: Robot Decision Making 1 [Slides]

• Path planning, Map representations, C-space
  • Siegwart et al. Book: Chapter 5.5 and 6.3
  • Correll Book: Chapter 4.1
• Graph-based planning algorithms
  • Correll Book: Chapter 4.2
• Sampling-based planning algorithms
  • Correll Book: Chapter 4.3

Topics: Robot Perception 3 [Slides]

• Detection, classification, tracking
• Clustering, supervised learning, classification, regression

Topics: Robot Decision Making 2 [Slides]

• Markov Decision Processes
  • Thrun et al. Book: Chapter 15.1 and 15.2
  • Sutton & Barto Book: Chapter 3
  • Russel & Norvig Book: Chapter 16.1, 16.2, 16.3
• Value iteration, policy iteration
  • Thrun et al. Book: Chapter 15.3
  • Russel & Norvig Book: Chapter 17.1, 17.2, 17.3

Guest lecture by Siddhartha Srinivasa

Topics: Robot Learning [Notes]

• Reinforcement learning
  • Sutton & Barto Book: Chapter 6.1, 6.2, 6.5
  • Russel & Norvig Book: Chapter 21.1, 21.2, 21.3

Guest lecture by Mike Chung

Topics: Human-Robot Interaction [Slides]

• Human-in-the-loop reinforcement learning
  • Knox & Stone, AI Magazine paper on reward shaping
  • Abbeel & Ng, ICML paper on inverse reinforcement learning
• References for the TAMER algorithm
  • Knox & Stone, KCAP paper on Human Reinforcement, 3.2 - 4.1.
  • Knox & Stone, ICDL paper on TAMER algorithm, 4--5.B.

Final exam