16-782 Planning and Decision-making in Robotics

Planning and Decision-making are critical components of autonomy in robotic systems. These components are responsible for making decisions that range from path planning and motion planning to coverage and task planning to taking actions that help robots understand the world around them better. This course studies underlying algorithmic techniques used for planning and decision-making in robotics and examines case studies in ground and aerial robots, humanoids, mobile manipulation platforms and multi-robot systems. Students in the class will learn these algorithms and implement them in a series of programming-based projects.

To take the class students should have a good knowledge of programming and data structures.

Fall 2020 Course Information

Announcements

Dates/times

Class meetings: Mondays, Wednesdays, 1:30-2:50PM, Online

Instructor

Who Email
Maxim Likhachev

Teaching Assistants

Who Email
Ramkumar Natarajan
Shivam Vats

Office Hours

Who Location Hours
Instructor Online By appointment
TA Ramkumar Natarajan Online Wed, 5-6PM
TA Shivam Vats Online Mon, 10:30-11:30AM

Grading

The criteria used to compute the final grade will consist of a combination of scores obtained on the exam, three programming assignments (homeworks), pop quizzes, final project and class participation:

Three homeworks 33%
Exam 20%
In-class pop quizzes 10%
Final project 32%
Participation 5%

Each student has a total of 3 free late days that may be used as needed for homeworks. No late days may be used for the final project!
Additional details: A late day is defined as a 24-hour period after the deadline. After the free late days are used up, each additional late day will incur a 10% penalty on the maximum achievable score. For example, if the assignment is worth 100 points, your maximum score will drop to 90 points for 1 additional late day and to 80 points for 2 additional late days, etc.

Class lectures/notes:

Tentative schedule posted here (PDF)

Date Topic Slides Homeworks Additional Info
8/31 (Mon) Introduction, What is Planning, Role of planning in Robots. slides
-
-
9/2 (Wed) Planning Representations: Implicit vs. Explicit Graphs; Skeletonization, Cell decomposition, Lattice-based Graphs slides
-
-
9/7 (Mon) LABOR DAY: NO CLASS -
-
-
9/9 (Wed) Search Algorithms: A*, Weighted A*, Backward A* slides
-
-
9/14 (Mon) Search Algorithms: A*, Weighted A*, Backward A* (cont'd) -
-
9/16 (Wed) Search Algorithms: Heuristic Functions, Multi-Heuristic A* slides
-
-
9/21 (Mon) Search Algorithms: Heuristic Functions, Multi-Heuristic A* (cont'd) -
-
-
9/23 (Wed) Search Algorithms: Multi-goal A* slides
-
-
9/28 (Mon) Interleaving Planning and Execution: Anytime and Incremental A* slides
-
-
9/30 (Wed) Interleaving Planning and Execution: Anytime and Incremental A* (cont'd) -
-
-
10/5 (Mon) Interleaving Planning and Execution: Real-time Heuristic Search slides
-
-
10/7 (Wed) Case Study: Planning for Autonomous Driving slides
-
-
10/12 (Mon) Planning Representations: Probabilistic Roadmaps for Continuous Spaces slides
-
10/14 (Wed) Planning Representations/Search Algorithms: RRT, RRT-Connect, RRT* slides
-
-
10/19 (Mon) Planning Representations/Search Algorithms: RRT, RRT-Connect, RRT* (cont'd) -
-
-
10/21 (Wed) Planning Representations/Search Algorithms: RRT, RRT-Connect, RRT* (cont'd) -
-
-
10/26 (Mon) Planning Representations/Search Algorithms: BIT* (lecture by Shivam Vats) slides
-
-
10/28 (Wed) Planning Representations/Search Algorithms: Trajectory Optimization Techniques (lecture by Ramkumar Natarajan), updated slides
-
-
11/2 (Mon) Case Study: Planning for Mobile Manipulators and Legged Robots slides
-
-
11/4 (Wed) Case Study: Planning for Coverage, Mapping and Surveyal slides
-
-
11/9 (Mon) Presentation of Final Project Ideas -
-
-
11/11 (Wed) Planning Representations: Symbolic Representation for Task Planning slides
-
11/16 (Wed) Search Algorithms: Planning on Symbolic Representations slides
-
-
11/18 (Wed) Planning under Uncertainty: Minimax Formulation slides
-
-
11/23 (Mon) Planning under Uncertainty: Expected Cost Formulation, Solving MDPs slides
-
-
11/25 (Wed) NO CLASS, Happy Thanksgiving! -
-
-
11/30 (Mon) Planning under Uncertainty: Partially-Observable Markov Decision Processes slides
-
-
12/2 (Wed) Planning under Uncertainty: Partially-Observable Markov Decision Processes (cont'd) -
-
-
12/7 (Mon) Multi-Robot Planning slides
-
-
12/9 (Wed) Multi-Robot Planning (cont'd) -
-
-