ICML 2011 Machine Learning & Robotics Tutorial

Slides
11-RoboticsAndML-ICMLtutorial.pdf
Overview
Joint research on Machine Learning and Robotics has received increasingly more attention recently. There are two reasons for this trend:

First, robots that cannot learn lack one of the most interesting aspects of intelligence. Much of classical robotics focussed on reasoning, optimal control and sensor processing given models of the robot and its environment. While this approach is successful for many industrial applications, it falls behind the more ambitious goal of Robotics as a test platform for our understanding of artificial and natural intelligence. Learning therefore has become a central topic in modern Robotics research.

Second, Machine Learning has proven very successful on many applications of statistical data analysis, like speech, vision, text, genetics, etc. However, although Machine Learning methods largely outperform humans in extracting statistical models from abstract data sets, our understanding of learning in natural environments---and learning what is relevant for behavior in natural environments---is limited. Therefore, robotics research motivates new and interesting kinds of challenges for Machine Learning.

This tutorial targets at Machine Learning researchers interested in the challenges of Robotics. It will introduce---in ML lingo---basics of Robotics and discuss which kinds of ML research are particularly promising to advance the field of Learning in Robotics.

Target audience
The tutorial targets at Machine Learning researchers, starting with PhD student level, that have basic knowledge of regression methods, Graphical Models, and probabilistic inference. The tutorial will also touch topics of statistical relational learning and Reinforcement Learning.

The participants will learn about existing trends in applying ML methods in Robotics, which are mainly in the context of Reinforcement Learning and Perception. They will also learn about---in my opinion---more fundamental problems in learning higher-level manipulation models in natural environments and how statistical relational learning might become of crucial importance to solve such problems.

Outline
This is the outline of the tutorial. (The second part is longer than suggested by this outline.)
Part I: Learning problems in Robotics - the RL view
  • Introduce to some basics
    - Markov Decision Processes and Stochastic Optimal Control
    - Kinematics and Dynamics
  • Five Approaches to Learning in Robotics
    1. Model learning (model-based RL)
    2. Value learning (model-free RL)
    3. Policy search
    4. Imitation learning
    5. Inverse RL
  • ...plus two more:
    6. Exploration
    7. Probabilistic Inference for Control & Planning
Part II: Interacting with a world of objects & Discussion
  • Statistical Relational Learning for Robots
  • Discussion