GRASP Seminar Series: Spring 2006

March 31, 12:00 p.m., Wu & Chen Auditorium (View Online)

Peter Stone
The University of Texas at Austin

"Machine learning on physical robots"

Abstract: As robot technology advances, we are approaching the day when robots will be deployed prevalently in uncontrolled, unpredictable environments: the proverbial "real world." As this happens, it will be essential for these robots to be able to adapt autonomously to their changing environment. For a robot to learn to improve its performance based entirely on real-world environmental feedback, the robot's behavior specification and learning algorithm must be constructed so as to enable data-efficient learning. This talk presents 3 examples of machine learning on physical robots.

First, for a robot, the ability to get from one place to another is one of the most basic skills. However, locomotion on legged robots is a challenging multidimensional control problem. We present a machine learning approach to legged locomotion, with all training done on the physical robots. The resulting learned walk is considerably faster than all previously reported hand-coded walks for the same robot platform.

Second, robots whose main sensor is a digital camera are often equipped with a color map that maps each pixel value to an associated color label. Typically, these color maps are created with the help of extensive and time-consuming manual labeling, and they are sensitive to illumination changes. We present a method for automatic color-map learning and illumination invariance on camera-based mobile robots.

Third, we present a technique for Autonomous Sensor and Actuator Model Induction (ASAMI) on a mobile robot. While previous approaches to calibration make use of an independent source of feedback, ASAMI is unsupervised, in that it does not receive any well-calibrated feedback about its location. Starting with only an inaccurate action model, it learns accurate relative action and sensor models. Furthermore, ASAMI is fully autonomous, in that it operates with no human supervision.

All of these methods are fully implemented and tested on a Sony Aibo ERS-7 robot.

Biography:
Peter Stone is an Alfred P. Sloan Research Fellow and Assistant Professor in the Department of Computer Sciences at the University of Texas at Austin. He received his Ph.D in Computer Science in 1998 from Carnegie Mellon University. From 1999 to 2002 he was a Senior Technical Staff Member in the Artificial Intelligence Principles Research Department at AT&T Labs - Research. Peter's research interests include machine learning, multiagent systems, robotics, and e-commerce. In 2003, he won a CAREER award from the National Science Foundation for his research on learning agents in dynamic, collaborative, and adversarial multiagent environments. In 2004, he was named an ONR Young Investigator for his research on machine learning on physical robots.

Full Seminar schedule...

GRASP Laboratory
Site maintained by graspadm@grasp.cis.upenn.edu
Last update: 1 May, 2006