[robotics-worldwide] Final CFP: AAAI 2011 Robotics Program

Andrea Thomaz athomaz at cc.gatech.edu
Wed Feb 23 11:50:00 PST 2011

The AAAI 2011 Robotics Program
Robotics Challenge Events & Education Track
Submit your proposal by March 1st, 2011

This information in this CFP can also be found here: 

The robotics program at AAAI has a long tradition of demonstrating 
innovative research at the intersection of robotics and artificial 
intelligence.  It strives to be a venue that pushes the science of 
embodied AI forward. Over the past few years a central point of the 
event has been the discussion of common research platforms and 
software, with the primary goal of focusing the research community’s 
energy toward common challenge tasks.

This year we are soliciting participation in three challenge events:
Learning from Demonstration, Small-scale Manipulation, and 
Miniature Humanoid Obstacle Avoidance. These are described in detail below. 

Participants should submit a letter of intent that includes the 
following information:
- Organization
- Team name and list of members
- Designated contact person (physical address, phone, and email)
- Which track you will enter (one of the three challenges or the edu track)
- Additional details (e.g., for the manipulation challenge will you
	be in mobile manipulation or unlimited)
- Brief description of robot to be used in the challenge, or approach 
	that will be demonstrated, or exhibit that will be made.

Submissions will be accepted through the following website: 
The submission deadline is March 1st, 2011.

Learning from Demonstration Challenge: 

Robot learning from demonstration research focuses on the 
development of algorithms that enable humans to teach robots 
new tasks by showing the robot what to do instead of by programming.   
The 2011 Robot Learning from Demonstration Challenge, held in 
conjunction with the AAAI Conference and Robotics Exhibition, 
is the premier forum for the presentation of advanced demonstration 
learning systems. The challenge is designed as an annual, 
multi-day event that enables participants to showcase their latest 
findings through presentations and live interactive demos.

The broad aim of the Learning from Demonstration Challenge is to 
promote technological innovation in this research area by facilitating 
discussion of the latest developments, providing a venue for showcasing
cutting edge research, and encouraging comparative assessment through 
a series of organized challenges.  Toward this goal, this year's event 
will include a single challenge task focused on food preparation.  
The task will require a combination of low-level skills, such as picking 
up and manipulating objects, and high-level task reasoning.  Participants 
will be asked to demonstrate a robot's ability to learn the task through 
interaction with a human teacher.  

Since not all interested participants may have access to robotic 
hardware that meets the requirements of the task with respect to sensing 
and manipulation, researchers will be provided with access to a Willow 
Garage PR2 robot through the Bosch PR2 Remote Lab facility.

More information at: http://www.lfd-challenge.org 

Organizing Committee:
Sonia Chernova, Worcester Polytechnic Institute, soniac at cs.wpi.edu

Small-Scale Manipulation Challenge: Robot Chess
The AAAI-2011 Small-Scale Manipulation Challenge focuses on perception
and dextrous manipulation of small, light-weight objects, so that robots
of any size can compete.  This year the domain will again be chess.
There will be two divisions: a mobile manipulation division for robots
that can navigate on a tabletop, and an unlimited division for
fixed-base arms and human-scale mobile platforms.

Qualification materials are due April 1, 2011.  These consist of a two
page abstract describing the robot platform and technical approach being
used, and a brief video demonstrating that the robot is able to move a
chess piece.

Rules for the competition will be worked out with the qualified
competitors, but will be similar to those used in 2010. 

More information at: http://Chiara-Robot.org/Challenge

Organizing Committee:

David S. Touretzky, Carnegie Mellon University, dst at cs.cmu.edu
Mike Stilman, Georgia Institute of Technology, mstilman at cc.gatech.edu

Miniature Humanoid Obstacle Challenge

The first "Miniature Humanoid Obstacle Challenge" was hosted at AAAI 2010 
in Atlanta.  The Challenge demanded a humanoid to reach a goal position 
on a 6-foot field that was cluttered with colored obstacles.  Multiple 
rounds were held over the 3-days and received enthusastic audiences.  
The participants are collaborators on an NSF-sponsored project that 
works on simulated and miniature humanoids, respectively called virtual-Hubo
and mini-Hubo.  Based on the enthusiasm of the 2010 Challenge, we 
propose a "Virtual Humanoid Manipulation Challenge".  Here, virtual-Hubo 
will be provided to all those interested in participating.  The simulated
world will demand manipulation (e.g. push gates, lift bars, etc) and 
whole-body motions (e.g. pick up boxes, crawl under desks, etc).  The 
exciting element is that code developed for virtual-Hubo runs on 
mini-Hubo.  This platform independence thus enables one to see outcomes 
from the simulation on a real miniature humanoid.  As such, a real-world 
facsimile of the simulated world will be erected at AAAI 2011.  Code from 
winning teams will be uploaded to our mini-Hubo and executed in the 
real-world.  The net effect is a challenge that is not limited by 
electro-mechanical hardware but opens the opportunity for many groups, 
to get involved with humanoid research, and see their work perform on a 
real humanoid.

Organizing Committee:

Paul Oh, Drexel University, paul at coe.drexel.edu

Robotics Education Track

Robots - and the AI algorithms that control them - are quickly maturing as resources that help convey computer science, engineering, and many other curricula. This venue offers an accessible and flexible opportunity for undergraduate, early graduate, or pre-college student teams to design, implement, and demonstrate an autonomous robotic system. The tasks involved can span physically-embodied AI: exploration, interaction, and learning within an unknown environment. In the long run, we hope to motivate hands-on AI robotics investigation both for its own sake and in service to other academic disciplines and educational goals.

More information at: http://www.cs.hmc.edu/aaairoboted

Organizing Committee:

Zach Dodds, Harvey Mudd, dodds at cs.hmc.edu

Andrea Thomaz
Asst. Professor, Interactive Computing
Georgia Institute of Technology

More information about the robotics-worldwide mailing list