COMP 790-099: Motion Planning in Real and Virtual Worlds

Spring 2010

Time: Tuesdays, Thursdays 3:30pm - 4:45pm

Location: SN 115

Instructor: Prof. Ron Alterovitz

Office hours: Tuesdays 4:45pm - 6:00pm or by appointment, 223 Sitterson Hall

Overview

Animating movies, automating laboratories, controlling medical devices, and many other tasks depend on planning the motions of real or virtual objects. Motion planning algorithms compute sequences of motions that achieve a particular goal, such as maneuvering a robot arm in an automation task, controlling an autonomous vehicle, or simulating a character's movement in a game or virtual environment. Developing motion planning algorithms is both technically broad and theoretically deep, raising a unique combination of questions in algorithm design, computational geometry, control theory, and robotics.

The course will begin by introducing the fundamentals of motion planning algorithms and then lead to discussions on current research and applications. The topics to be covered, which may be modified based on the interests of enrolled students, include:

• Path planning for autonomous agents/robots
• Learning motion policies in uncertain environments
• Manipulating deformable objects
• Collision detection
• Multi-agent/robot collaboration and interaction
• Motion capture and learning from demonstrations
• Theoretical underpinnings of motion planning
• Applications to medicine, surgical planning, autonomous vehicles, entertainment, graphics, protein folding, virtual worlds, games, laboratory automation, and other areas

Who should attend: Students with interests in motion planning algorithms, graphics, robotics, and computational geometry, as well as application areas such as those listed above. Students from Computer Science as well as other departments are welcome. For students in Computer Science, the course project report could serve as a basis for the MS Program Product requirement and/or the department technical writing requirement.

Credit Hours: Variable (see below).

Grading: For 3 credit hours: 40% course project, 20% presentation, 20% assignments, 20% participation. Each student will select the topic of his/her course project. Each student will also present a topic based on a research paper of his or her choice from the research literature and complete a pair of written/programming assignments. For 1 credit hour: 50% paper presentation, 50% participation.

Prerequisites: Knowledge of undergraduate level calculus, linear algebra, and programming (any language, such as Java, Matlab, C, C++, etc.). Prior coursework in motion planning, robotics, or graphics is not required. Both graduate and undergraduate students are welcome to enroll.

Textbook: There is no textbook for this course. Course notes, in-class handouts, and links to relevant papers will be provided.

Tentative Schedule (subject to change)

Suggested Papers for Category 1: The Basic Motion Planning Problem and Uncertainty

• Samuel Prentice and Nicholas Roy, "The Belief Roadmap: Efficient Planning in Belief Space by Factoring the Covariance," The International Journal of Robotics Research, July 2009. (pdf)
• Jan Rosell and Pedro Iniguez, "Path planning using Harmonic Functions and Probabilistic Cell Decomposition," Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2005. (pdf)
• Pieter Abbeel, Dmitri Dolgov, Andrew Y. Ng and Sebastian Thrun, "Apprenticeship Learning for Motion Planning with Application to Parking Lot Navigation," Proceedings of the International Conference on Intellegent RObots and Systems (IROS), 2008. (pdf)
• Markus Rickert, Oliver Brock, and Alois Knoll, "Balancing Exploration and Exploitation in Motion Planning," Proc. IEEE Int. Conf. Robotics and Automation (ICRA), May 2008, pp. 2812-2817. (pdf)
• B. Burns and O. Brock, "Toward optimal configuration space sampling," in Proc. Robotics: Science and Systems, (Cambridge, MA), June 2005. (pdf)
• K. Hauser and J.-C. Latombe, "Multi-modal planning for non-expansive configuration spaces," in Workshop on the Algorithmic Foundations of Robotics, 2008. (pdf)
• M. Zucker, J. Kuffner, and M. Branicky, "Multipartite RRTs for Rapid Replanning in Dynamic Environments," in Proc. IEEE Int. Conf. on Robotics and Automation, 2007, pp. 1603-1609.(pdf)
• Andrew M. Ladd and Lydia E. Kavraki, "Motion Planning in the Presence of Drift, Underactuation and Discrete System Changes," Robotics: Science and Systems I, MIT Press, Boston, MA, p. 233-241, 2005. (pdf)
• Samuel Rodriguez, Jyh-Ming Lien, N. M. Amato, "Planning Motion in Completely Deformable Environments," in Proc. IEEE Int. Conf. Robot. Autom. (ICRA), pp. 2466-2471, May 2006. (pdf)
• M. Moll and L. E. Kavraki, "Path Planning for Deformable Linear Objects," vol. 22, no. 4, pp. 625-636, Aug. 2006.

Suggested Papers for Category 2: Other Topics in Motion Planning

• Philipp Reist and Russ Tedrake. Simulation-based LQR-trees with input and state constraints. In To appear in the Proceedings of the International Conference on Robotics and Automation (ICRA), 2010 (pdf)
• L. J. Guibas, D. Hsu, H. Kurniawati, and E. Rehman, "Bounded uncertainty roadmaps for path planning," in Proc. Int. Workshop on the Algorithmic Foundations of Robotics (WAFR), 2008. (pdf)
• Russ Tedrake, "LQR-Trees: Feedback motion planning on sparse randomized trees," In Proceedings of Robotics: Science and Systems (RSS), page 8, 2009. (pdf)
• B. Tovar, A. Yershova, J. M. O'Kane, and S. M. LaValle, "Information spaces for mobile robots," In Proceedings International Workshop on Robot Motion and Control (RoMoCo 2005), 2005. (pdf)
• Thrun, S. and Burgard, W. and Fox, D., "A Real-Time Algorithm for Mobile Robot Mapping With Applications to Multi-Robot and 3D Mapping," Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2000. (pdf)
• David B. Grimesm, Rawichote Chalodhorn, and Rajesh P. N. Rao, "Dynamic Imitation in a Humanoid Robot through Nonparametric Probabilistic Inference," Proc. Robotics: Science and Systems, 2006. (pdf)
• Jeremy Schiff, Erik B. Sudderth, and Ken Goldberg, "Nonparametric Belief Propagation for Distributed Tracking of Robot Networks with Noisy Inter-Distance Measurements," IEEE International Conference on Intelligent Robots and Systems (IROS), 2009. (pdf)
• Jur van den Berg, Ming C. Lin, Dinesh Manocha, "Reciprocal Velocity Obstacles for Real-Time Multi-Agent Navigation" Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2008. (pdf)
• J. Zico Kolter, Pieter Abbeel and Andrew Y. Ng, "Hierarchical Apprenticeship Learning with Application to Quadruped Locomotion," in NIPS 20, 2008. (pdf)
• Zhang, J., Wei, W., Roland, J., Manolidis, S., Simaan, N., "Path Planning and Workspace Determination for Robot-Assisted Insertion of Steerable Electrode Arrays for Cochlear Implant Surgery," MICCAI'2008, the 11th International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 692-700, 2008. (pdf)
• H. Mayer, I. Nagy, A. Knoll, E. Braun, R. Bauernschmitt. "Adaptive control for human-robot skill transfer: trajectory planning based on fluid dynamics," Proc. IEEE Int. Conf. on Robotics and Automation, 2007. (pdf)

Relevant Textbooks

There is no textbook for this course. Below are standard textbooks in the field that you may find useful or interesting.

• S. M. LaValle, Planning Algorithms. Cambridge, U.K.: Cambridge University Press, 2006. (Available online for free)
• H. Choset, K. M. Lynch, S. Hutchinson, G. Kantor, W. Burgard, L. E. Kavraki, and S. Thrun, Principles of Robot Motion: Theory, Algorithms, and Implementations. MIT Press, 2005.
• Dimitri P. Bertsekas, Dynamic Programming and Optimal Control, Athena Scientific, 2007.

Advice on Presentations

Giving an Academic Talk by Jonathan Shewchuk