16.412J | Spring 2016 | Graduate
Cognitive Robotics


In this class, students are given the following problem sets to perform modeling exercises, use existing autonomy tools, and implement algorithms. All problem sets, if available, are provided below.

Problem Sets

The Cognitive Robotics Virtual Machine (VM) needed to complete the problem sets is provided in the “Related Resources” section. Please follow the instructions provided in Assignment 1 to install it.

Problem sets # TOPICS / INSTRUCTIONS / supporting files
1 Conflict-Directed A* (PDF)
2 Scheduling—All instructions are in the course virtual machine (OVA - 2GB) under the pset2 folder. Follow them inline in the IPython notebook.
3 PDDL Modeling (PDF)
4 Hybrid State Estimation Modeling (PDF - 1.2MB)
5 Iterative Risk Allocation

Advanced Lecture and Mini Problem Sets

In addition, students will select a research topic following the guidelines provided below and deliver an advanced lecture to the class in groups of five to six students.

Assignment for Advanced Lecture: Request for Topics (PDF)

Assignment for Advanced Lecture & Implementation (PDF)

To copmlete this assignment, students also need to choose one additional mini problem set from below and turn it in.

Mini Problem sets # TOPICS / INSTRUCTIONS / supporting files
1 Incremental Path Planning (ZIP file)
2 Semantic Localization (ZIP file)
3 Image Classification via Deep Learning (ZIP file, 45MB)
4 Monte Carlo Tree Search (ZIP file, 3.6MB)
5 Reachability (ZIP file)
6 Planning with Temporal Logic (ZIP file, 32.1MB)
7 Mini Problem Set 5: Probablistic and Infinite Horizon Planning (ZIP file)

Final Project – Grand Challenge

Students will deliver the Grand Challenge Assignment (PDF) at the end of semester. This group project involves modeling, algorithm implementation, and debugging in a simulation environment.

Additional tools and resources are provided in the “Related Resources” section.

Learning Resource Types
theaters Lecture Videos
assignment Programming Assignments
notes Lecture Notes
co_present Instructor Insights