Students in 16.412 complete two projects. For the 'Advanced Lecture', students research a topic in the field of cognitive robotics, and deliver a lecture in-class on their selection. For the 'Final Project', teams expand the field through innovative methods or applications. Students report on the project through individual papers and a brief team presentation. All work is courtesy of the students named, and used with permission.

Advanced Lecture Information

The following advanced lecture summary is excerpted, in part, from the Advanced Lecture Proposal Guidelines (PDF)


The purpose of the advanced lecture is to identify one to two advanced research methods, and to present these clearly and pedagogically, through a 45 minute oral presentation, through a written tutorial, and in the case of a three person team, with a demonstration. An additional objective is to learn to develop an understanding of the literature in a collaborative context, through one to two partners.

Advanced lectures improve the class' awareness of current research in the field of cognitive robotics. The instructors often re-use them in future semesters to keep the course up to date. A list of suggested topics is linked at the bottom of this section.


Advanced lectures are prepared by students and presented during scheduled lecture sessions. Students perform a 'dry-run' in advance of their in-class presentation. The dry-run is an opportunity for students to exchange feedback on their presentations. The revised lecture, delivered in-class, is subject to the following scoring scheme:

Scoring Guidelines for Technical Presentations (PDF)


In previous semesters, this project was introduced through a sequence of assignments: a warm-up literature review, and an advanced lecture proposal. Although the warm-up exercise was not assigned in Spring 2004, it introduces the advanced lecture project itself, which was undertaken by all students this semester.

Advanced Lecture Warm-Up Exercise (PDF)

Advanced Lecture Proposal Guidelines (PDF)

Advanced Lecture Submission Guidelines (PDF)

Suggested Topics and Readings for Advanced Lecture and Project (PDF)

2005 Advance Lectures

Lawrence Bush, Antonio Jimenez, and Brian Bairstow Solving POMDPs Through Macro Decomposition (PDF - 3.7 MB)
Jennifer Novosad, Justin Fox, and Jeremie Pouly Cognitive Game Theory (PDF - 2.8)
James Lenfestey, Thomas Temple, and Ethan Howe Introduction to Probablisitic Relational Models (This resource may not render correctly in a screen reader.PDF)
Kaijen Hsiao, Henry Lefebvre de Plinval-Salgues, and Jason Miller Particle Filters and their Applications (PDF - 1.3 MB)
Brian Mihok and Michael Terry Statistical Learning and Inference Methods for Reasoning in Games (PDF)
Thomas Coffee, Shannon Dong, and Shen Qu Human-Computer Interaction (PDF - 1.1 MB)

Final Project Information

The following final project summary is excerpted, in part, from the Final Project Guidelines (PDF)


The purpose of the project is to develop a deep understanding of one or two methods for creating cognitive robots and intelligent embedded systems, and to innovate upon these methods, to lend novel insight into their behavior through analysis or to apply the method in an innovative manner.

More specifically, you should demonstrate the ability to:

  • Clearly state and motivate an interesting, focused innovation to intelligent embedded systems. An innovation may be an important analytical question, a novel algorithmic extension or an innovative application.
  • Extract and evaluate the relevant literature using the Web and library resources.
  • Provide a simple explanation for the algorithms used in your project, using pedagogical examples to highlight key features of the algorithm.
  • If a design project, describe the design of the intelligent embedded systems you are creating and the rationale for the method applied in the context of the project. If this is an analysis project, then described the experimental method that you are pursuing.
  • Implement and demonstrate an algorithm or application in support of your project goals.
  • Evaluate the approach analytically and/or empirically.


  • A - represents mastery: the ability to analyze and extend existing methods in a way that is novel and insightful; the ability to explain and motivate in a manner that is particularly intuitive.
  • B - represents solid competence: the ability to articulately motivate, explain, implement and evaluate a focused set (i.e., 1 or 2) of intelligent embedded systems methods.
  • C - represents partial competence of the above.

Report Guidelines

The report should reveal a depth of understanding. It should communicate the objectives, core description, developments and results of your project. Three main elements to present in your report:

  1. Articulation of the set of methods upon which your project is built, in a pedagogical (tutorial-like) manner.
  2. Empirical and/or analytical evaluation and insights.
  3. Innovation that involves applying and/or extending methods in a novel way.

Presentation Guidelines

Each team gives a presentation (approximately 5 minutes/group member). Selected student work from Spring 2005 and Spring 2004 are linked in the tables below. A list of suggested topics is linked at the bottom of this section.

2005 Final Projects


Lawrence Bush, Antonio Jimenez, and Brian Bairstow

Adaptable Mission Planning for Kino-Dynamic Systems



Thomas Coffee, Shuonan Dong, and Shen Qu

Spatial Intent Recognition Using Optimal Margin Classifiers



Ethan Howe and Jennifer Novosad

Extending SLAM to Multiple Robots


Kaijen Hsiao, Henry Lefebvre de Plinval-Salgues, and Jason Miller

Mapping Contoured Terrain: A Comparison of SLAM Algorithms for Radio-Controlled Helicopters


(PDF - 1.1 MB)

James Lenfestey

A SIFT-based Pictorial Image Model


Brian Mihok and Michael Terry

A Bayesian Net Inference Tool for Hidden State in Texas Hold'em Poker



Jeremie Pouly and Justin Fox

An Empirical Investigation of Mutation Parameters and Their Effects on Evolutionary Convergence of a Chess Evaluation Function



Thomas Temple

GPS Integrity Monitoring



2004 Final Projects


Alexander Omelchenko

Autonomous Visual Tracking Algorithms


Lars Blackmore and Steve Block

Cooperative Q Learning

Report by Block
Report by Blackmore

Seung H. Chung, Robert T. Effinger, Thomas Léauté, and Steven D. Lovell

Model-based Programming for Cooperating Vehicles

Report by Léauté (PDF)
Report by Chung (PDF)
Report by Effinger (PDF)
Report by Lovell

Morten Rufus Blas and Søren Riisgaard

SLAM for Dummies

Presentation (PDF - 1.5 MB)
Report (This resource may not render correctly in a screen reader.PDF)
Personal comments by Blas (PDF)
Personal comments by Riisgaard (PDF)

Vikash K. Mansinghka

Towards Visual SLAM in Dynamic Environments

Presentation (PDF)
Report (PDF)