Difference between revisions of "CISC849 S2018"
From class_wiki
(→Schedule) |
(→Schedule) |
||
| Line 234: | Line 234: | ||
|Reinforcement learning | |Reinforcement learning | ||
| | | | ||
| − | |[http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html UCL Silver course]: [http://nameless.cis.udel.edu/class_data/849_s2018/intro_RL.pdf RL slides] (7-42), [https://www.youtube.com/watch?v=2pWv7GOvuf0 RL video] (contains movies missing from PDF); [http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture14.pdf Stanford deep | + | |[http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html UCL Silver course]: [http://nameless.cis.udel.edu/class_data/849_s2018/intro_RL.pdf RL slides] (7-42), [https://www.youtube.com/watch?v=2pWv7GOvuf0 RL video] (contains movies missing from PDF); [http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture14.pdf Stanford deep-Q lecture slides] (23-62); [https://www.nature.com/articles/nature14236.pdf original deep-Q paper] |
|- | |- | ||
|style="background:rgb(102, 204, 255)"|17 | |style="background:rgb(102, 204, 255)"|17 | ||
Revision as of 09:48, 5 April 2018
Contents
Course information
| Title | CISC849 Robot Vision and Learning |
| Shortened URL | https://goo.gl/ektJij |
| Description | Survey of image-based 2-D and 3-D sensing algorithms for mobile robot navigation and interaction, including motion estimation, obstacle segmentation, terrain modeling, and object recognition, with a particular focus on deep learning techniques to dramatically improve performance. |
| When | Tuesdays and Thursdays, 11 am-12:15 pm |
| Where | Smith 102A |
| Instructor | Christopher Rasmussen, 446 Smith Hall, cer@cis.udel.edu |
| Office hours | Wednesdays, 10 am -- 12 pm |
| Grading |
|
| Academic policies | Programming projects are due by midnight of the deadline day (with a grace period of a few hours afterward...after sunrise is definitely late). A late homework is a 0 without a valid prior excuse. To give you a little flexibility, you have 6 "late days" to use on homeworks to extend the deadline by one day each without penalty. No more than three late days may be used per assignment. Late days will automatically be subtracted, but as a courtesy please notify the instructor in an e-mail of your intention to use late days before the deadline. See submission instructions below.
Students can discuss problems with one another in general terms, but must work independently on programming assignments. This also applies to online and printed resources: you may consult them as references (as long as you cite them), but the words and source code you turn in must be yours alone. The University's policies on academic dishonesty are set forth in the student code of conduct here. |
| Homeworks | Assignment submissions should consist of a directory containing all code (your .cpp files, makefile, etc.), any output data generated (e.g., images, movies, etc.), and an explanation of your approach, what worked and didn't work, etc. contained in a separate text or HTML file. Do not submit executables or .o files, please! The directory you submit for each assignment should be packaged by tar'ing and gzip'ing it or just zip'ing it. The resulting file should be submitted through Canvas.
You may develop your C/C++ code in any fashion that is convenient--that is, with any compiler and operating system that you want. However, we will be grading your homework on a Linux system with a makefile, and so you must avoid OS- and hardware-specific functions and provide a makefile for us that will work (like one of the templates above). |
Possible Papers to Present (not a complete list)
- Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours, Pinto and Gupta, ICRA 2016
- Learning real manipulation tasks from virtual demonstrations using LSTM, Rahmatizadeh et al., AAAI 2018
- Learning to Fly by Crashing, Gandhi, Pinto, and Gupta, IROS 2017
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition, Maturana and Scherer, IROS 2015
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation, Qi, Su, Mo, and Guibas, CVPR 2017
- Real-Time Navigation in 3D Environments Based on Depth Camera Data, D. Maier, A. Hornung, and M. Bennewitz, Humanoids 2012
- Robotic Grasping of Novel Objects using Vision, A. Saxena, J. Driemeyer, A. Ng, IJRR 2008
- DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning, X. Peng, G. Berseth, K. Yin, and M. van de Panne, SIGGRAPH 2017
- High fidelity day/night stereo mapping with vegetation and negative obstacle detection for vision-in-the-loop walking, M. Bajracharya et al., IROS 2013
Instructions for Homeworks
| Software |
|
| Note |
|
Schedule
Note: The blue squares in the "#" column below indicate Tuesdays.
| # | Date | Topic | Links/Readings/videos | Assignments/slides |
|---|---|---|---|---|
| 1 | Feb. 6 | Background | slides | |
| 2 | Feb. 8 | Finish background | slides | |
| 3 | Feb. 13 | Introduction to DARPA Urban Challenge (UC), Robotics Challenge (DRC) and algorithm components |
|
slides |
| 4 | Feb. 15 | Introduction to ROS; PCL tutorial |
ARGOS challenge overview (8:00) |
slides |
| 5 | Feb. 20 Register/add deadline Feb. 19 |
Plane/obstacle/object segmentation (3-D) | RANSAC background | HW #1 plane_fit.cpp (No ROS required) |
| 6 | Feb. 22 | Finish plane segmentation, clustering, ICP | slides | |
| 7 | Feb. 27 | Image classification background<!849 --Clustering, normal estimation--> | Stanford CS231n Image classification slides (6-61), | |
| 8 | Mar. 1 | NO CLASS Instructor away |
HW #1 due | |
| 9 | Mar. 6 | More classification background | Loss/optimization slides (8-10, 37-77, finish with web demo), Intro to NN (83-88) | |
| 10 | Mar. 8 | Introduction to convolutional neural networks | Stanford CS231n Convolutional Neural Networks slides (15-63, 71-78), CNN architectures (8-36), Detection and Segmentation slides (15-27) | |
| 11 | Mar. 13 | Finish detection & segmentation background, introduction to TensorFlow library | YOLOv2, Redmon and Farhadi (CVPR 2017) | Stanford CS231n Detection and Segmentation slides (44-49, 53-85), deep learning software slides (21-33, 40-59) TensorFlow code sample from Stanford lecture HW #2 |
| 12 | Mar. 15 | More on TensorFlow programming | ||
| 13 | Mar. 20 | Perception for stepping | "Learning Locomotion over Rough Terrain using Terrain Templates", M. Kalakrishnan, J. Buchli, P. Pastor, and S. Schaal, IROS 2009 | slides DeepLoco highlights video (6:23) |
| 14 | Mar. 22 | NO CLASS | HW #2 due Friday, March 23 | |
| Mar. 27 | NO CLASS Spring break |
|||
| Mar. 29 | NO CLASS Spring break |
|||
| 15 | Apr. 3 | Imitation learning |
|
Berkeley Levine course IL slides (DAgger defined on slide 14); CMU Fragkiadaki IL slides (1-29) Paper presentation choice due |
| 16 | Apr. 5 | Reinforcement learning | UCL Silver course: RL slides (7-42), RL video (contains movies missing from PDF); Stanford deep-Q lecture slides (23-62); original deep-Q paper | |
| 17 | Apr. 10 Withdraw deadline Apr. 9 |
Student paper presentations; project kick-off | ||
| 18 | Apr. 12 | Student paper presentations | Project proposal due Sunday, April 15 | |
| 19 | Apr. 17 |
Student paper presentations | ||
| 20 | Apr. 19 | Early project review; student paper presentation |
|
|
| 21 | Apr. 24 | Student paper presentations | ||
| 22 | Apr. 26 | Student paper presentations | ||
| 23 | May 1 | Miscellaneous | ||
| 24 | May 3 | Final project review | ||
| 25 | May 8 | "Bonus" material | ||
| 26 | May 10 | Miscellaneous | ||
| 27 | May 15 | Final project presentations | Final project due |
