HRI Pioneers Workshop 2007
Updates
Details on the keynote address by Dr. Henrik Christensen of Georgia Tech below.
Background
The field of human-robot interaction is new but growing rapidly. While there are now several established researchers in the field, many of the current human-robotic interaction practitioners are students or recently graduated. This workshop, to be held in conjunction with the HRI 2007 conference, aims to bring together this group of researchers to discuss their work, talk about the important upcoming issues in the field, and hear about what their colleagues are doing.

The workshop is the second annual workshop for junior researchers in HRI held in conjunction with the HRI conference. Those who have not attended a previous session are highly encouraged to submit to this workshop. Previous attendance will be considered for acceptance as well.

Keynote Talk: Evaluation of Robots for Human-Robot Interaction
We would like to announce Dr. Henrik Christensen of the Georgia Institute of Technology as our keynote speaker. Dr. Christensen is the KUKA Chair of Robotics at Georgia Institute of Technology and director of the Center for Robotics and Intelligent Machines at the same institution. He has earlier been director of Autonomous Systems at the Royal Institute of Technology, Sweden and coordinator of European Robotics (1998-2006). He earned an initial degree in Mechanical Engineering before earning M.Sc. and Ph.D degrees from Aalborg University - Denmark, 1987 and 1989 respectively. His research is focussed on robotics systems and in particular systems integration, embedded in real applications. Henrik Christensen has published more than 200 contributions in AI, Robotics, and Computer Vision and is the co-foundered of 3 companies. Henrik serves on the editorial board of AI Magazine, Autonomous Robots, Intl Jour of Robotics Research, and Service Robotics. Further information is available on his web site.

ABSTRACT: Robotics is gradually maturing as a discipline which also implies an increased need for comparative R&D. At the same time robots are increasingly deployed to serve as assistants to humans, be it for search and rescue or as part of normal daily chores in the home. To enable evaluation of progress in research it is essential that rigorous methodologies for evaluation and performance characterisation are adopted. Often a number of objections are put forward as to why such rigorous experimental protocols are not well suited for robotics. Some of the typical objections will be discussed in the presentation. To illustrate the value and strategy of experimental evaluation two example applications will be presented. Both applications are closely tied to robots that serve as assistants to people as part of daily operations.

A Wizard-of-Oz study has been used for the design of a strategy for joint human-robot mapping of domestic setting as part of creation of a cognitive robots for assistance to people in their homes. The Wizard-of-Oz study clearly illustrate some of the challenges that a robot has to cope with and indicate a number of important issues to be considered in the design of dialog behaviours and associated autonomous functionality. We will here discuss the use of initial exploratory system designs to ensure early integration of the end-user. The study has later been complemented with real implementations and a number of observations on dialogue and physical interaction are presented.

Another study has considered the deployment of PackBot systems for assistance to soldiers as part of urban intervention. Integration of robots into a unit of soldiers poses a number of interesting challenges. There is a here a need to consider the impact of the system on the robot operator and to re-consider the entire strategy for urban intervention when a unit is equipped with a light-weight robot for scouting. Results from a study with the international brigade from the Swedish military are presented and a number of important lessons from a long-term (12 month) study is reported.

Experience from prior studies clearly illustrate the value of a careful design for evaluation and characterisation of systems, which goes beyond the simple verification of theoretical models. Observations and lessons from an extensive set of studies are summarised.

Format
The format of the workshop will have participants presenting their work in short talks, hearing from an expert in the field on the important problems in HRI, and meeting in small group sessions to discuss common research themes.

The workshop will take place on Thursday, March 8, 2007, in Washington, DC in conjunction with the HRI 2007 Conference to be held in DC March 9-11. Potential participants are encouraged to submit an abstract of their current research, a 1 paragraph statement of motivation for attending the workshop, and a letter of support from their research advisor by September 30, 2006 to hri-workshop@media.mit.edu. Please limit abstracts to two pages.

We have accepted approximately 30 students and young researchers to the workshop. Twelve will be asked to give a brief (10 minute) talk to the workshop about their work. The remainder will be expected to talk about their work during breakout sessions and meals.
Attendees
Link
Organizers
Program Committee
Dates