ICML 2011 Machine Learning & Robotics Tutorial
 Slides
 11RoboticsAndMLICMLtutorial.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 environmentsand learning what is relevant for behavior in natural environmentsis 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 introducein ML lingobasics 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 aboutin my opinionmore fundamental problems in learning higherlevel 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 (modelbased RL)
2. Value learning (modelfree RL)
3. Policy search
4. Imitation learning
5. Inverse RL  ...plus two more:
6. Exploration
7. Probabilistic Inference for Control & Planning
 Introduce to some basics
 Part II: Interacting with a world of objects & Discussion

 Statistical Relational Learning for Robots
 Discussion