SS08LappingCarrM

SS08LappingCarrM - Wiimote Interfaces for Lifelong Robot...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Wiimote Interfaces for Lifelong Robot Learning Micah Lapping - Carr Odest Chadwicke Jenkins Daniel H. Grollman Jonas N. Schwertfeger Theodora R. Hinkle Department of Computer Science Brown University Providence, RI, USA 02912-1910 mlapping|cjenkins|dang|js|[email protected] Abstract We believe that one of the major impediments to involvement in the field of robotics and AI is the difficulty end-users face in creating viable robot control policies. We seek to address this difficulty with lifelong robot learning and have developed an intuitive robot control interface using the Nintendo Wii remote to aid in this task. From three large public demos and several smaller ones, we have gotten a multitude of positive responses on the interface. We also believe that others can find similar successes in the field of HRI using undergraduate researchers. Introduction I was nearing the end of my sophomore year and eagerly trying to find a summer internship. I had limited experience with robotics, having worked with the Robocup team for a semester, yet found the topic fascinating. Therefore, I asked the professor in charge if he would hire me for the summer. He did, and I began on the road that has brought me to where I am today, authoring my first paper. My name is Micah Lapping - Carr, and this is my story of how I joined and embraced the world of AI and robotics. The state of robotics is constantly changing, but there is one barrier that will continue to impede its success if not ad- dressed. For most commercial robots, only the “technically elite” (programmers and engineers) are currently able to cre- ate the robot control policies they want, while the rest of the population must make do using the built-in policies (such as those on the iRobot Roomba, or WowWee Robotics’ line of Robosapiens) included by the robot’s creators. Through lifelong robot learning , we aim to provide users of con- sumer robot technologies with a medium for transforming desired behaviors into robot control policies. Specifically, given the same situational awareness, a robot should make a decision similar to the one the creator of the policy would make. While several paradigms exist for such policy trans- fer (e.g. continuous teleoperation, speech and gesture-based instruction, text-based and visual computer programming, Copyright c ± 2008, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Figure 1: Nintendo Wii Remote and Nunchuk controlling a Sony Aibo playing robot soccer. optimization/search), we remain confronted by a human- robot divide . This divide refers to the disparity between the needs and ideas of users in society, a population with a diverse set of technical abilities and creative design sensi- bilities, and their ability to instantiate robot control to meet their desired ends. If a personal robotics revolution is to come, similar to that of personal computing, there will need to exist applications that will make new forms of personal
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 6

SS08LappingCarrM - Wiimote Interfaces for Lifelong Robot...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online