Go to: course materials, projects
Lectures
Note: The notes posted below may not be include all the material covered in the class. Please refer to what was discussed in the actual class.
| # | DATE | TOPIC | NOTES | |
|---|---|---|---|---|
| 1 | Jan 24 | Introduction | Overview, Topics Overview. Robot Kinematics. | |
| 2 | Jan 26 | Supervised Learning. | Gradient descent | slides, pdf (part of notes) |
| 3 | Jan 31 | Supervised Learning | Linear Regression, Cross-val testing. | knn, linear regression 1, 2. (Slides from Piyush Rai.) (No slides for train/test cross validation.) |
| 4 | Feb 2 | Robot survival kit | Robot Kinematics overview. ROS+Gazebo+PR2 simulator (Perez). | slides. Also see Piazza. |
| 5 | Feb 7 | Supervised Learning | Logistic Regression. Newton's method. | slides, optional notes |
| 6 | Feb 9 | Supervised Learning | Robotic Perception, Basic Operations, 3D Features. | PCL slides |
| 7 | Feb 14 | Supervised Learning | Bag of features (shape-words), 3D algorithms, Point-cloud library PCL (Anand) | slides, Also see Piazza. |
| 8 | Feb 16 | Reinforcement Learning | Decision making, MDP, Bellman eqns, Value Iteration | |
| 9 | Feb 21 | Reinforcement Learning | Policy Iteration, estimating robot transitions. | (see previous) |
| 10 | Feb 28 | Reinforcement Learning | Fitted Value Iteration, Value Function approximation | (see previous) |
| 11 | Mar 1 | Kalman Filters | Discrete Time Linear Systems.- | |
| 12 | Mar 8 | Kalman Filters | observations, applications to tracking | (see previous) |
| 13 | Mar 13 | Kalman Filters | Extended Kalman Filters. | |
| 14 | Mar 15 | Path Planning (by Kress-Gazit). | Potential Field, RRT. | |
| 15 | Mar 27 | Control | Linear systems controllability, PID control. | |
| 16 | Mar 29 | Learning | Markov Process, discrete HMM | |
| 17 | April 3 | Learning | HMM: Inference and Learning | (see previous), paper |
| 18 | April 10 | Applications | Kalman and HMM application examples | pdf, more |
| 19 | April 12 | Learning | Particle filters. | |
| 20 | April 17 | Particle Filters | derivation from Bayes filters | (see previous) |
| 19 | Apr 19 | Review | Testing, Evaluation and Applications | - |
| Apr 19 | Prelim | 7:30-10pm. Open notes midterm / no electronic devices. | PHL101 | |
| 24 | April 24 | Learning | Particle Filters | (previous) |
| 21 | April 26 | Supervised Learning | Kernels | none |
| 22 | May 1 | Supervised Learning | Large Margin classifiers: SVM. | extended notes (not everything in the notes is in the course) |
| 23 | May 3 | POMDPs | ppt | |
| May 10, 2-5pm | Final poster presentation / demo | (reports due latest by May 15) | - | |
| May 15, 5pm | Final written reports due | - |
Some of these lecture notes have been taken from the following classes: CS223A by Oussama Khatib, CS229 by Andrew Ng.