Difference between revisions of "CISC849 F2019"
From class_wiki
(→Schedule) |
(→Schedule) |
||
| Line 174: | Line 174: | ||
|12 | |12 | ||
|Oct. 3 | |Oct. 3 | ||
| − | |<!--Particle filters and localization--> | + | |Perception for stepping<!--Particle filters and localization--> |
| − | |<!--[http://www2.informatik.uni-freiburg.de/~wurm/papers/hornung10iros.pdf Humanoid Robot Localization in Complex Indoor Environments], A. Hornung, K. Wurm, M. Bennewitz, IROS 2010--> | + | |"Learning Locomotion over Rough Terrain using Terrain Templates", M. Kalakrishnan, J. Buchli, P. Pastor, and S. Schaal, IROS 2009<!--[http://www2.informatik.uni-freiburg.de/~wurm/papers/hornung10iros.pdf Humanoid Robot Localization in Complex Indoor Environments], A. Hornung, K. Wurm, M. Bennewitz, IROS 2010--> |
|<!--[http://robots.stanford.edu/probabilistic-robotics/ppt/particle-filters.ppt Thrun particle filtering slides]--> | |<!--[http://robots.stanford.edu/probabilistic-robotics/ppt/particle-filters.ppt Thrun particle filtering slides]--> | ||
|- | |- | ||
| Line 181: | Line 181: | ||
|Oct. 8 | |Oct. 8 | ||
|style="background:rgb(255, 102, 0)"|NO CLASS<br>''Instructor away''<!--Motion planning background--> | |style="background:rgb(255, 102, 0)"|NO CLASS<br>''Instructor away''<!--Motion planning background--> | ||
| − | | | + | | |
| − | |[https://docs.google.com/presentation/d/1HQdeZ2JjATrWN7Y7BIgpeiFoIJa0J44P2d0bN_YSwRY/edit?usp=sharing slides]<br> | + | |<!--[https://docs.google.com/presentation/d/1HQdeZ2JjATrWN7Y7BIgpeiFoIJa0J44P2d0bN_YSwRY/edit?usp=sharing slides]<br>--> |
|- | |- | ||
|13 | |13 | ||
|Oct. 10 | |Oct. 10 | ||
| − | | | + | |Imitation learning |
|<!--[http://wiki.ros.org/gmapping gmapping] demos: [http://www.youtube.com/watch?v=7iIDdvCXIFM Pirobot], [http://www.youtube.com/watch?v=_jwBKo0SXng MIT]<br>[http://www.youtube.com/watch?v=F8pdObV_df4 Darmstadt "Hector" mapping]<br> | |<!--[http://wiki.ros.org/gmapping gmapping] demos: [http://www.youtube.com/watch?v=7iIDdvCXIFM Pirobot], [http://www.youtube.com/watch?v=_jwBKo0SXng MIT]<br>[http://www.youtube.com/watch?v=F8pdObV_df4 Darmstadt "Hector" mapping]<br> | ||
Nao 3-D mapping and planning: [http://www.youtube.com/watch?v=srcx7lPoIfw 1], [http://www.youtube.com/watch?v=g2NZ_EasJv0 2]--> | Nao 3-D mapping and planning: [http://www.youtube.com/watch?v=srcx7lPoIfw 1], [http://www.youtube.com/watch?v=g2NZ_EasJv0 2]--> | ||
| − | |<!--ETH SLAM lectures: [http://nameless.cis.udel.edu/class_data/849_s2018/ETH_SLAM_I_2017.pdf 1] [http://nameless.cis.udel.edu/class_data/849_s2018/ETH_SLAM_II_2017.pdf 2]<!--[http://nameless.cis.udel.edu/class_data/cisc829/oct18/thrun_fastslam.pdf Thrun FastSLAM slides] (grids from slide 29)<br>[http://www.youtube.com/watch?v=3Yl2aq28LFQ Accompanying Stachniss lecture]-->''HW #2 due Friday, March 23'' | + | | |
| + | * [http://rpg.ifi.uzh.ch/docs/RAL16_Giusti.pdf A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots], Giusti ''et al.'', ''IEEE Robotics and Automation Letters'', 2016 | ||
| + | * [https://arxiv.org/pdf/1604.07316.pdf End to End Learning for Self-Driving cars], Bojarski ''et al.'', 2016 | ||
| + | * [https://www.youtube.com/watch?v=NJU9ULQUwng Dave-2 driving a Lincoln], [https://www.youtube.com/watch?v=umRdt3zGgpU Quadcopter Navigation in the Forest...], [https://www.youtube.com/watch?v=hNsP6-K3Hn4 DAgger for drones] | ||
| + | * [https://www.youtube.com/watch?v=ZMhO1FO_j0o&t=566s Hal Daume DAgger explanation] (9:26-12:43) | ||
| + | |[http://rll.berkeley.edu/deeprlcourse/ Berkeley Levine course] [http://rll.berkeley.edu/deeprlcourse/f17docs/lecture_2_behavior_cloning.pdf IL slides] (DAgger defined on slide 14); [https://katefvision.github.io/katefSlides/immitation_learning_I_katef.pdf CMU Fragkiadaki IL slides] (1-29) | ||
| + | <!--ETH SLAM lectures: [http://nameless.cis.udel.edu/class_data/849_s2018/ETH_SLAM_I_2017.pdf 1] [http://nameless.cis.udel.edu/class_data/849_s2018/ETH_SLAM_II_2017.pdf 2]<!--[http://nameless.cis.udel.edu/class_data/cisc829/oct18/thrun_fastslam.pdf Thrun FastSLAM slides] (grids from slide 29)<br>[http://www.youtube.com/watch?v=3Yl2aq28LFQ Accompanying Stachniss lecture]--><!--''HW #2 due Friday, March 23''--> | ||
|- | |- | ||
|style="background:rgb(102, 204, 255)"|14 | |style="background:rgb(102, 204, 255)"|14 | ||
|Oct. 15 | |Oct. 15 | ||
| + | |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] (15:40-21:20, 1:02:13-1:04:40 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] |
| − | |||
|- | |- | ||
|15 | |15 | ||
|Oct. 17 | |Oct. 17 | ||
| + | |RL for locomotion | ||
| | | | ||
| | | | ||
| − | + | * [https://www.youtube.com/watch?v=G4lT9CLyCNw DeepLoco highlights video] (6:23) | |
|- | |- | ||
|style="background:rgb(102, 204, 255)"|16 | |style="background:rgb(102, 204, 255)"|16 | ||
|Oct. 22<br>''Withdraw deadline'' | |Oct. 22<br>''Withdraw deadline'' | ||
| − | |||
| | | | ||
| − | + | | | |
| − | + | <!--<br>''Paper presentation choice due''--> | |
| − | |||
| − | |||
| − | |||
|- | |- | ||
|17 | |17 | ||
|Oct. 24 | |Oct. 24 | ||
| − | |||
| | | | ||
| − | | | + | | |
| + | | | ||
|- | |- | ||
|style="background:rgb(102, 204, 255)"|18 | |style="background:rgb(102, 204, 255)"|18 | ||
Revision as of 13:42, 27 August 2019
Course information
| Title | CISC849 Robot Vision and Learning |
| 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, 2-3:15 pm |
| Where | Gore 317 |
| Instructor | Christopher Rasmussen, 446 Smith Hall, cer@cis.udel.edu |
| Office hours | Mondays and Wednesdays, 2-3 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
Schedule
Note: The blue squares in the "#" column below indicate Tuesdays.
| # | Date | Topic | Links/Readings/videos | Assignments/slides | |
|---|---|---|---|---|---|
| 1 | Aug. 27 | Background | slides | ||
| 2 | Aug. 29 | Finish background | |||
| 3 | Sep. 3 | Introduction to DARPA Urban Challenge (UC), Robotics Challenge (DRC) and algorithm components |
|
||
| 4 | Sep. 5 | Current grand challenges | |||
| 5 | Sep. 10 Register/add deadline |
Traditional 2-D/3-D shape/object segmentation, part I | |||
| 6 | Sep. 12 | Traditional 2-D/3-D shape/object segmentation, part II | |||
| 7 | Sep. 17 | Image classification background | Stanford CS231n Image classification slides (6-61), | ||
| 8 | Sep. 19 | More classification background | Loss/optimization slides (8-10, 37-77, finish with web demo), Intro to NN (83-88) HW #1 due | ||
| 9 | Sep. 24 | 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) | ||
| 10 | Sep. 26 | 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 | |
| 11 | Oct. 1 | More on TensorFlow programming and detection/segmentation | HW #2 | ||
| 12 | Oct. 3 | Perception for stepping | "Learning Locomotion over Rough Terrain using Terrain Templates", M. Kalakrishnan, J. Buchli, P. Pastor, and S. Schaal, IROS 2009 | ||
| Oct. 8 | NO CLASS Instructor away |
||||
| 13 | Oct. 10 | Imitation learning |
|
Berkeley Levine course IL slides (DAgger defined on slide 14); CMU Fragkiadaki IL slides (1-29) | |
| 14 | Oct. 15 | Reinforcement learning | UCL Silver course: RL slides (7-42), RL video (15:40-21:20, 1:02:13-1:04:40 contains movies missing from PDF); Stanford deep-Q lecture slides (23-62); original deep-Q paper | ||
| 15 | Oct. 17 | RL for locomotion |
| ||
| 16 | Oct. 22 Withdraw deadline |
||||
| 17 | Oct. 24 | ||||
| 18 | Oct. 29 | Student paper presentation | |||
| 19 | Oct. 31 | Student paper presentation | Project proposal due Sunday, April 15 | ||
| 20 | Nov. 5 | Student paper presentations | |||
| 21 | Nov. 7 | Student paper presentations | |||
| 22 | Nov. 12 | Student paper presentation | |||
| 23 | Nov. 14 | Student paper presentations | |||
| 24 | Nov. 19 | Student paper presentation | |||
| 25 | Nov. 21 | Instructor paper presentation | Rasmussen, "Real-Time SLAM with Octree Evidence Grids for Exploration in Underwater Tunnels", N. Fairfield, G. Kantor, and D. Wettergreen, JFR 2007 | DepthX slides | |
| Nov. 26 | NO CLASS Thanksgiving break |
||||
| Nov. 28 | NO CLASS Thanksgiving break |
||||
| 26 | Dec. 3 | Final project presentations part I | |||
| 27 | Dec. 5 | Final project presentations part II |
