Page 1 |
Save page Remove page | Previous | 1 of 189 | Next |
|
small (250x250 max)
medium (500x500 max)
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
Subset |
MACHINE LEARNING OF MOTOR SKILLS FOR ROBOTICS
by
Jan Reinhard Peters
A Dissertation Presented to the
FACULTY OF THE GRADUATE SCHOOL
UNIVERSITY OF SOUTHERN CALIFORNIA
In Partial Fulfillment of the
Requirements for the Degree
DOCTOR OF PHILOSOPHY
(COMPUTER SCIENCE)
May 2007
Copyright 2007 Jan Reinhard Peters
Object Description
| Title | Machine learning of motor skills for robotics |
| Author | Peters, Jan Reinhard |
| Author email | mail@jan-peters.net |
| Degree | Doctor of Philosophy |
| Document type | Dissertation |
| Degree program | Computer Science |
| School | Viterbi School of Engineering |
| Date defended/completed | 2007-03-21 |
| Date submitted | 2007 |
| Restricted until | Unrestricted |
| Date published | 2007-04-16 |
| Advisor (committee chair) | Schaal, Stefan |
| Advisor (committee member) |
Sukhatme, Gaurav Udwadia, Firdaus Atkeson, Chris |
| Abstract | Autonomous robots have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. Early approaches in the 1980s showed that approaches purely based on reasoning and human insights would not be applicable to all perceptuomotor tasks of future robots. Instead, new hope was put in the growing wake of machine learning. However, to date, learning techniques have yet to fulfill this promise as only few task-independent methods scale into manipulator or humanoid robotics. In order to overcome these difficulties, we investigate steps towards a structured, general approach to motor skill learning based on a theoretically well-founded novel framework for task control and appropriate learning algorithms.; As theoretical basis, we introduce a point-wise optimal control framework that allows the derivation of various well-known robot control laws and which has been applied successfully to task space tracking control for several different metrics on the anthropomorphic SARCOS Master Arm.; To overcome the requirement of accurate models, learning controllers for task space control offers an alternative. However, when learning to control a redundant system, we face the general problem of the non-convexity of the solution space. This problem can be resolved using the point-wise cost function of the analytical framework to ensure global consistency. An immediate reinforcement learning algorithm is derived from the expectation-maximization perspective which leads to a reward-weighted regression technique. We demonstrate the feasibility of the resulting framework in redundant endeffector tracking for simulated robot arms.; While learning to execute tasks in task space is an essential component of motor skill learning, learning the actual task is more important. We focus on learning of elemental tasks represented by parameterized motor primitives. While imitation learning of motor primitives is a well-understood, the self-improvement by interaction of the system with the environment remains a challenging problem, tackled in the fourth chapter of this thesis. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and outline both established and novel algorithms for the gradient-based improvement of parameterized policies. We compare these algorithms in the context of motor primitive learning, and show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. |
| Keyword | motor skills; machine learning; reinforcement learning; robotics; policy gradients; natural policy gradients |
| Language |
English German |
| Part of collection | University of Southern California dissertations and theses |
| Publisher (of the original version) | University of Southern California |
| Place of publication (of the original version) | Los Angeles, California |
| Publisher (of the digital version) | University of Southern California. Libraries |
| Type | texts |
| Legacy record ID | usctheses-m397 |
| Rights | Peters, Jan Reinhard |
| Repository name | Libraries, University of Southern California |
| Repository address | Los Angeles, California |
| Repository email | http://www.usc.edu/isd/libraries/services/ask_a_librarian/email/ |
| Filename | etd-Peters-20070416 |
| Archival file | uscthesesreloadpub_Volume14/etd-Peters-20070416.pdf |
Description
| Title | Page 1 |
| Full text | MACHINE LEARNING OF MOTOR SKILLS FOR ROBOTICS by Jan Reinhard Peters A Dissertation Presented to the FACULTY OF THE GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Fulfillment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (COMPUTER SCIENCE) May 2007 Copyright 2007 Jan Reinhard Peters |
Comments
Post a Comment for Page 1
