CMSC828F Spring 2006
Advanced Topics in Information Processing: Perceptual Robotics
Instructors: | Cornelia Fermüller and Abhijit Ogale |
Contact: | fer at cfar.umd.edu in AVW 4459
ogale at cs.umd.edu in AVW 4403 |
Time/ Location: | M: 4:00 - 6:45pm CSI 1122 |
This class focuses on the study of spatial representations which a
robot uses to map the environment and execute navigational tasks. In
the Robotics literature this problem is referred to as SLAM
(simultaneous localization and mapping) . It requires the integration
of different cognitive modalities, such as perception, mapping and
planning. The emphasis of this class lies in the exploration of
meaningful visual representations to build with other tools from
Robotics environmental maps. We will study an develop tools for
Control, Visual Localization, Mapping and Planning by means of a number
of projects and finally build SLAM programs.
Books : |
Introduction
to Autonomous Mobile Robots. Roland
Siegwart and Illah R. Nourbakhsh, MIT Press 2004 (recommended) Principles of Robot Motion: Theory, Algorithms and Implementations. H. Choset, K. M. Lynch, S. Hutchinson, G. Kantor, W. Burgard, L. E Kavraki, and S. Thrun, MIT Press, 2005 Probabilistic Robotics. Sebastian Thrun, Wolfram Burgard, and Dieter Fox, MIT Presss 2005 Introduction to AI Robotics. Robin R. Murphy, MIT Press 2000. Planning and Control. Thomas L. Dean and Michael P. Wellman, Morgan Kaufmann Publishers, 1991.
Vehiles: Experiments in Synthetic Psychology. Valentino Braitenberg, MIT Press paperback edition 1986
|
Software :
Matlab software for controlling the ER1, reading the infrared data and reading images : (matlabRobot)
Drivers for ibot-camera : drivers
Infrared sensor code : zip-file
Lectures:
1/30: Introduction
2/6 : Locomotion and Robot Kinematics : Chapter 2 and 3 Siegwart and Nourbakhsh; (powerpoint slides from UPenn 1,2,3)
2/13 : Introduction to Control (Dean and Michael P. Wellman Chapters 1 ,2 and 4, pdf- file ) and Description of Project 1
2/20: Talk by George Kantor on DEPTHX and Introduction to Kalman filtering (pdf-file)
2/27: Bayesian filters and Particle filters ( Chapter 9 from Principles of Robot Motion Theory, Algorithms and Implementations (hand-out)) ,
see also (Fox et. al. pdf), Image calibration (ppt)
3/6 : Vision : Image filtering (filter.ppt, filter2.ppt), Edge detection, Corner detection, Hough transform (ppt), Image motion (ppt)
3/13: Description of Project 2, Summary of papers by B. Kuipers on the Spatial Semantic Hierarchy (ppt)
3/27: Epipolar geometry (ppt), SIFT features (tutorial, paper by Lowe)
4/3: Interpretation of 3D motion fields (ppt) , 3D motion from normal flow (ppt), Stereo
Projects:
Project 1: A simulator for obstacle avoidance (Proj1)
Project2: Localization with particle filters using IR sensor and Vision (Proj2)
Final Exam:
Friday 5/19 : 1:30 - 3:30