CS296-3 Robot Learning and Autonomy
Instructor: Prof. Chad Jenkins
This course attempts to address the question "What are the driving applications of robotics?" How will robots move out of structured laboratory settings into real-world applications where a diversity of users, environments, and tasks abound. Towards this end, CS296-3 is a seminar course that covers current research topics related to perceiving and acting in the real world. These topics will be pursued through independent reading, class discussion, and project implementations. Papers covered will be drawn from robotics, computer vision, animation, machine learning, and neuroscience. Special emphasis will be given to developing autonomous control from human demonstration and video game style interfaces.
Grading for individual enrolled students is broken down as follows:
20% Attendance and participation
40% Paper presentations
40% Contribution towards final project
Students are expected to attend all class meetings (unless an exception is given beforehand), actively participate in discussion, present 2 papers to the class, and significantly contribute towards the development and implemenation of a final project.
For paper presentations, student presenters must have a rough draft prepared and consult with the instructor at least 2 days before the presentation date.
Each class meeting will consist of 2 paper presentations given by students. This should take between 1-2 hours. The remaining time will be devoted to a collaborative hacking session to implement and try-out new ideas.
Discussion: "What are the driving applications of robotics?"
iRobot Create and Player/Stage demo
Discussion: "Project Ideas"
Roomba/Create Open Interface
2/7 Papers Fast Forward
2/14 Autonomous control architectures
- RRT-Connect: An efficient approach to single-query path planning.
J.J. Kuffner and S.M. LaValle
In Proc. IEEE Int'l Conf. on Robotics and Automation (ICRA'2000), pages 995-1001, San Francisco, CA, April 2000.
- A Robust Layered Control System for a Mobile Robot
Rodney A. Brooks
IEEE Transactions on Robotics and Automation, 2(1), pages 14-23, April 1986.
- On Three-Layer Architectures
Artificial Intelligence and Mobile Robotics, in D. Kortenkamp, R. P. Bonnasso and R. Murphy (eds.), AAAI Press, pages 195-210, 1998.
- Behavior-based Robotics
Ronald C. Arkin
MIT Press, 1998.
- "Intelligence Without Reason"
Rodney A. Brooks
Proceedings of 12th International Joint Conference on Artificial Intelligence (IJCAI-91), Sydney, Australia, pages 569-595, August 1991.
2/21 Motor learning and neuroscientific models
- Computational aspects of motor control and motor learning
Handbook of Perception and Action: Motor Skills, H. Huer and S. Keele, eds, 1993.
- Action recognition in the premotor cortex
G. Rizzolatti, L. Gadiga, V. Gallese, L. Fogassi
Brain, 119(2):593-609, 1996.
- Motor learning through the combination of primitives
F. Mussa-Ivaldi, E. Bizzi
Phil. Trans. R. Soc. Lond. B 355:1755-1769, 2000.
- Sensory-Motor Primitives as a Basis for Learning by Imitation: Linking Perception to Action and Biology to Robotics
Imitation in Animals and Artifacts, MIT Press, 2002, 392-422.
- Is imitation learning the route to humanoid robots?
Trends in Cognitive Sciences, 3, 6, pp.233-242, 1999.
2/28 Robot learning: nonparametric regression
- Robot learning from demonstration
C.G. Atkeson, S. Schaal
Proceedings of the Fourteenth International Conference (ICML '97), pp.12-20, Morgan Kaufmann, 1999.
- Information Theory, Inference and Learning Algorithms (Chapter 45)
D. J. C. MacKay
Cambridge University Press, Cambridge, UK, 2003.
- Dogged Learning for Robots
D.H. Grollman, O.C. Jenkins
IEEE International Conference on Robotics and Automation (ICRA 2007), 2007.
3/7 Interfaces for Robot Teleoperation
3/14 Robot learning: reinforcement learning
- Effective Reinforcement Learning for Mobile Robots
William D. Smart and Leslie Pack Kaelbling
Proceedings of IEEE International Conference on Robotics and Automation (ICRA 2002), volume 4, pages 3404-3410, 2002.
- Reinforcement Learning with Human Teachers: Evidence of feedback and guidance with implications for learning performance
A. L. Thomaz C. Breazeal
Proceedings of the 21st National Conference on Artificial Intelligence (AAAI), 2006.
- Humanoid Robot Learning and Game Playing Using PC-Based Vision
Darrin C. Bentivegna, Ales Ude, Christopher G. Atkeson, and Gordon Cheng
IROS 2002, Swiss Federal Institute of Technology Lausanne (EPFL), Switzerland, October, 2002.
- Natural Methods for Robot Task Learning: Instructive Demonstration, Generalization and Practice
Monica Nicolescu, Maja J Mataric
Second International Joint Conference on Autonomous Agents and Multi-Agent Systems, Melbourne, AUSTRALIA, July 14-18, 2003.
- Value Function Approximation using Diffusion Wavelets and Laplacian Eigenfunctions
Sridhar Mahadevan and Mauro Maggioni
Neural Information Processing Systems (NIPS), 2006.
3/21 Manifold learning and dynamical systems
- A Global Geometric Framework for Nonlinear Dimensionality Reduction
J. B. Tenenbaum, V. de Silva and J. C. Langford
Science 290 (5500): 2319-2323, 22 December 2000
- Graph Laplacian Regularization for Large-Scale Semidefinite Programming
K. Q. Weinberger, F. Sha, Q. Zhu and L. K. Saul
Advances in Neural Information Processing Systems 19. MIT Press: Cambridge, MA, 2006.
- A spatio-temporal extension to isomap nonlinear dimension reduction
O. C. Jenkins and M. J. Mataric
International Conference on Machine Learning (ICML 2004), pages 441-448, Banff, Alberta, Canada, Jul 2004
- Gaussian Process Dynamical Models
J.M. Wang, D.J. Fleet, A. Hertzmann
NIPS 2005, December, 2005. Vancouver, Canada. pp. 1441-1448.
- Nonlinear dynamical systems for imitation with humanoid robots
A.J. Ijspeert, J. Nakanishi, T. Shibata, and S. Schaal
Proceedings of the IEEE/RAS International Conference on Humanoids Robots (Humanoids2001), pages 219-226, 2001.
3/28 Spring Break
4/4 Image features and object recognition
4/11 Social robotics
- Theory of mind for a humanoid robot
Autonomous Robots, vol. 12, p. 13-24, 2002.
- A survey of socially interactive robots
T. Fong, I. Nourbakhsh, K. Dautenhahn
Robotics and Autonomous Systems, Special issue on Socially Interactive Robots 42 (3-4), pp 143-166, 2003.
- A Bayesian model of imitation in infants and robots
R. Rao, A. Shon and A. Meltzoff
Imitation and Social Learning in Robots, Humans, and Animals, Cambridge University Press, 2005
- Experiments in Adjustable Autonomy
M.A. Goodrich, D.R. Olsen Jr., J.W. Crandall, and T.J. Palmer
IJCAI01 workshop on Autonomy, Delegation, and Control: Interacting with Autonomous Agents.
- Challenges in building robots that imitate people
C. Breazeal and B. Scassellati
Imitation in Animals and Artifacts, MIT Press, 2002.
4/18 Group behavior and task allocation
- Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork
Peter Stone and Manuela Veloso
Artificial Intelligence, 110(2), pages 241-273, 1998.
- A formal analysis and taxonomy of task allocation in multi-robot systems
Brian P. Gerkey and Maja J Mataric
Intl. Journal of Robotics Research, 23(9):939-954, September 2004.
- Opportunistic Optimization for Market-Based Multirobot Control
M.B. Dias and A. Stentz
International Conference on Intelligent Robots and Systems (IROS '02), Vol. 3, September, 2002, pp. 2714 - 2720.
- Understanding Belief Propagation and Its Generalizations
J.S. Yedidia, W.T. Freeman W.T., Y. Weiss
IJCAI 2001 Distinguished Lecture trac
- Manipulation Gaits: Sequences of Grasp Control Tasks
R. Platt, A.H. Fagg, R. Grupen
Proceedings of the 2004 IEEE Conference on Robotics and Automation (ICRA), New Orleans, Louisiana, April 2004
- Manipulation in Human Environments
A. Edsinger, C. Kemp.
Proceedings of the IEEE/RSJ International Conference on Humanoid Robotics, 2006.
- Closure and Quality Equivalence for Efficient Synthesis of Grasps from Examples
N. S. Pollard
International Journal of Robotics Research, 23(6), 595--614, June 2004.
5/2: Open for paper selections
5/9: Final project demos