CS 4649/7649: RIP - Robot Intelligence - Planning in Action
TR 1:35-2:55, Howey S107
Fall 2011

Instructor: Mike Stilman

Office hours:
CCB 254 by email or appointment.
Tentative Syllabus
Fall 2008 Class Projects
Fall 2009 Class Projects
For Discussion, Group Building and Collaboration on Projects: Course Wiki
We discuss algorithms for robots and other complex systems that make intelligent decisions in high dimensional or continuous spaces of options. Intelligent decisions take into account both present and future constraints on the system. The course will cover methods for planning with symbolic, numerical, geometric and physical constraints. Topics will range from classical and stochastic planning to continuous robot domains and hybrid control of dynamic systems.

Optional Readings:
Specific chapters directly relevant to the course will be posted on the website. The readings are not required but they may help you get better background and deeper understanding into the course topics. In fact, if you have time over breaks etc. these are excellent books to read to get a broad appreciation for planning as a field: Additional readings from papers will also be posted on the course website when they become relevant. Those will be available to you as PDFs.
(PDFs of Slides will be posted During course):

Classical Planning

  • Aug. 23: Introduction, Logic, Situation Calculus: [PDF]

  • Aug. 25: Advantages of SitCalc, STRIPS Operators, First Planner: [PDF]
  • Aug. 30: Properties of State Space Planners: STRIPS: [PDF]

  • Sept. 1: Shakey, State Space vs. Plan Space: [PDF]
  • Sept. 6: GraphPlan, Action Representations: [PDF]
  • Sept. 8: Efficiency in Planning, Basics of Search: [PDF]
  • Sept. 13: Heuristic Planning: [PDF]
  • Sept. 15: Planning as Satisfiability: [PDF]
  • Sept. 20: Classical Applications: [PDF]

    Motion Planning

  • Sept. 22: Motion Planning: Complete Algorithms: [PDF]
  • Sept. 27: (GUEST LECTURE: Martin Levihn) Roadmap Planning: Visibility vs. Voronoi: [PDF]
  • Sept. 29: (GUEST LECTURE: Ana Huaman) Navigation Planning: Cells, Grids and Fields: [PDF]
  • Oct. 4: Articulated Kinematics, Configurations: [PDF]
  • Oct. 6: Inverse Kinematics, Jacobians: [PDF]
  • Oct. 11: No Class - Sponsor Visit - Time to GET SERIOUS on projects!
  • Oct. 13: Potential Fields, Sampling-based Planning, (PRM) Probabilistic Roadmaps: [PDF]
  • Oct. 18: No Class - School Recess
  • Oct. 20: (RRT) Rapidly Exploring Random Trees, Path Improvement, Constraints: [PDF]
  • Oct. 25: Recent Developments in Motion Planning [PDF]
  • Oct. 27: No Class - Humanoids Conference - Time to work on Projects!

    Uncertainty and Dynamics

  • Nov. 1: (GUEST LECTURE: Jon Scholz) Summary, Markov Systems, Matrix Inversion: [PDF]
  • Nov. 3: Markov Decision Processes, Value Iteration: [PDF]
  • Nov. 8: MDP: Applications & Algorithms: [PDF]
  • Nov. 10: Probability Primer: [PDF]
  • Nov. 15: Partially Observable MDP (POMDP): [PDF]
  • Nov. 17: POMDP, Value Iteration: [PDF]
  • Nov. 22: Kalman filter: [PDF]

  • Nov. 29: Linear Control Primer: [PDF]

    Bridging Planning & Control

  • Dec. 1: Linearized and Force Control: [PDF]

  • Dec. 6: LQR Case Study: [PDF]

    Assignments and Projects:


    This course has graduate (7649) and undergraduate (4649) sections. Both sections will participate in two group programming projects related to the two covered aspects of planning. The projects will be graded on algorithm implmementation, analysis and results for a total of 40% of the course grade.

    Classical Planning (30%)
    Motion Planning (30%)

    In order to expose students to research in planning, the course will also have a final project that makes up 40% of the grade. This project will involve the design, implementation and validation of a planning algorithm resulting in a conference-style paper and presentation.

    7649 Graduate Projects:

    Graduate students will work in groups on a project that is relevant to their research goals. The instructor will provide resources such as robot arm/hand hardware and existing algorithms to support this work. Furthermore, students are welcome to use resources or expand on active projects in their own research labs. Final decisions on topics will be made through discussion with the instructor.

    4649 Undegraduate Reviews:

    Undergraduates can take the role of reviewers for the projects. They will be exposed to research in planning and the peer-review process. Undergrads will be required to review project proposals, final projects, suggest alternative algorithms and find references that back up their claims. They will be graded based on the thoroughness of their reviews, understanding of the project topics and relevance of located references. Undergraduates are given the option to participate in the projects directly and be graded as graduate students.