UIUC CS-588 Autonomous Vehicle System Engineering Outline

This page contains what we've done

Texts:

Applied Machine Learning D.A. Forsyth, Springer, 2019

This is purely for background material on deep learning and other useful data tricks.

Important The PDF is a free download from the UIUC library (you have to be on the intranet to download it, I think). Or you could buy a paper copy.
The New Computer Vision D.A. Forsyth, Some publisher, The distant future

This is the source of various compact enrichment notes. They've been proofread, but not particularly carefully, and anyhow I'm a lousy proofreader. But they're at a point where they should be helpful.

Records

Week of	Topic	Reading Materials	Movie List
18 Jan	18 Jan: Admin+intro 21 Jan: Safety lookout training at High Bay	My intro slides Vehicle safety rules	Old safety lookout video, for reference
25 Jan	25 Jan: ROS and start PID control 27 Jan: I'm absent Simple neural networks Deep nets: Units; AML: 16.1 Deep nets: Gradients; AML: 16.2 Deep nets: Backpropagation; AML 16.3 Deep nets: Gradient tricks; AML 16.4 Deep nets: Convolutional layers; AML 17.1 Deep nets: More conv. layers; AML 17.1, 17.2 Basic object detection: AML 19	ROS and PACMOD: "My" ROS and PACMOD slides Original detailed slides, with examples, etc.from Roi Yehoshua at Bar-Ilan U. The Simulator Lecture on the simulator in 2021 by Xiaoming Zhao Basic control: Intro to PID control	25 Jan we're on mediaspace; the movie of 25 Jan is here. For routine class movies, I won't post link - look them up on mediaspace. Movies for 27 Jan Units Gradients Backprop Gradient tricks Convolutional layers More conv layers Image classifiers Object detectors
1 Feb	1 Feb: Finish PID control, start motion planning 3 Feb: more simple motion planning	Basic control: Intro to PID control (these are the slides I used 25 Jan, but I've skipped some) Simple motion planning
8 Feb	8 Feb: Point set registration and IRLS 10 Feb: Cameras	Basic Registration: Simple point set registration and iterated closest points Robustness and iteratively reweighted least squares Maps and very simple bundle adjustment Cameras: Basic camera properties Mathematical models of cameras	Enrichment movie Compact movie on M-estimators and IRLS Enrichment notes Compact notes on registration Compact notes on basic camera models Compact notes on camera geometry Weighted least squares solutions for rotation translation; very nice notes from Olga Sorkine-Hornung and Michael Rabinovitch see also Notes on robustness and iteratively reweighted least squares see also Robust registration of point sets using iteratively reweighted least squares P. Bergstrom and A.Edlund, Computational Optimization and Applications July 2014, Volume 58, Issue 3, pp 543–561 (click from inside UIUC intranet!) Geometrically Stable Sampling for the ICP AlgorithmN. Gelfand; L. Ikemoto; S. Rusinkiewicz; M. Levoy, (3DIMPVT) 2003 Efficient Variants of the ICP AlgorithmS.Rusinkiewicz and M. Levoy, (3DIMPVT), 2001 Translation Synchronization via Truncated Least SquaresX Huang, Z Liang, C. Bajaj, Q. Huang, NeurIPS17 Uncertainty quantification for multi-scan registration X Huang, Z Liang, Q Huang ACM Transactions on Graphics (TOG) 39 (4), 130: 1-130: 24
15 Feb	15 Feb: Camera Calibration, start pairs of cameras 17 Feb: Pairs of cameras and Visual Odometry	Calibration: A sketch of camera calibration Pairs of Cameras: The Geometry of two cameras, with fundamental and essential matrices and RANSAC Simple odometry from two views or getting something out of the fundamental matrix and calibration Interest points or what to match	Enrichment notes Compact notes on camera calibration Multiple View Geometry in Computer Vision Second Edition Richard Hartley and Andrew Zisserman, Cambridge University Press, March 2004. Tutorial on visual slam at CVPR2014 I found the following particularly helpful Visual odometry Stephan Weiss Stereo Visual odometryChris Beall Dense odometryRichard Newcombe
22 Feb	22 Feb: Filtering and Kalman Filter 24 Feb: I'm on Travel - review notes	Filtering A simple, important example; filtering in 1D The general story of filtering The Kalman filter in ND