Robot Learning Seminar

COURSE LEARNING GOALS
The objective of the class is to:
(1) learn about robotics and control,
(2) understand why machine learning is a necessary tool for building autonomous and intelligent robots,  
(3) get familiar with recent research articles on robot learning,
(4) learn advanced machine learning techniques for robotics and control, and
(5) provide experience in implementing such techniques on representative challenges.

The course is intended for computer science graduate students, who have been exposed to artificial intelligence material in the past. Experience in programming in Python/C++ is needed for a project with a Baxter robot.

INSTRUCTOR
Abdeslam Boularias

OFFICE HOURS 

Abdeslam Boularias: Fridays 2:00-3:00 PM in CBIM 07

TOPICS

The class presents recent developments in machine learning that are related to robotics . Example topics include:

(a) Classical Robotics and Optimal Control: Kinematics, Dynamics, Representing Trajectories, Control in Joint Space and in Task Space
(b) Reinforcement Learning, Learning from Demonstrations, Model Learning
(c) Grasping and Manipulation
(d) Robot Vision

BOOKS
No particular textbook will be used in the course. The material will be primarily based on research papers. Some suggested classical background reading:
  • on robotics: B. Siciliano, L. Sciavicco: Robotics: Modelling, Planning and Control, Springer, 2009 
  • on machine learning: C.Bishop: Pattern Recognition and Machine Learning, Springer, 2006. 
  • on reinforcement learning: R. Sutton, S. Barto: Reinforcement Learning, MIT Press, 1998.

EXPECTED WORK

Regular readings and homework, written and oral presentations, projects.

GRADING SCHEME
Participation: 10%
Written presentation: 15%
Oral presentation: 15%
Homework: 20%
Project: 40%

TENTATIVE SCHEDULE (subject to changes)
Lecture 1 : Introduction and Overview
Lecture 2 : Classical Robotics
Lecture 3 : Optimal Control
Lecture 4 : Machine Learning
Lecture 5 : Model Learning
Lecture 6 : Reinforcement Learning
Lecture 7 : Learning from Demonstrations
Lecture 8 : Policy Search
Lecture 9 : Grasping and Manipulation
Lecture 10 : Robot Vision
Lectures 11-13 : Paper presentations

list of topics for presentations

Topic 1: Reinforcement Learning in Brain-Machine Interfaces
Assigned to: Mingwen Dong

      Topic 2: Deep Reinforcement Learning
      Assigned to: Raghav Bhardwaj
          Topic 3: Active Vision for Object Search
          Assigned to: TBD
          Topic 4: Model Learning
          Assigned to: TBD
          Topic 5: Belief Space Planning
          Assigned to: TBD
          Topic 6: Learning to Grasp
          Assigned to:  TBD
            Topic 7: Learning to Manipulate
            Assigned to: TBD
                Topic 8: Learning to Walk
                Assigned to: TBD
                  Topic 9: Inverse Reinforcement Learning
                  Assigned to: Poornima Suresh
                      Topic 10: Interactive Segmentation
                      Assigned to: TBD
                      Topic 11: Translating Commands in Natural Language into Plans
                      Assigned to: TBD
                      Topic 12: High-speed Robots
                      Assigned to: TBD
                      Topic 13: Autonomous Driving
                      Assigned to: TBD
                      Topic 14: Imitation Learning I
                      Assigned to: TBD
                      Topic 15: Imitation Learning II
                      Assigned to: TBD
                      Topic 16: Robot Reinforcement Learning I
                      Assigned to: TBD
                      Topic 17: Robot Reinforcement Learning II
                      Assigned to: TBD
                          Topic 18: Human-Robot Interaction
                          Assigned to: Zhe Chang

                                Presentations date: TBD on December, 2017
                                Comments