The Roboceptionist Project

 

Tank the Roboceptionist is the most recent addition to Carnegie Mellon’s Social Robots Project. A permanent installation in the entranceway to Newell-Simon Hall, the robot combines useful functionality—giving directions, looking up weather forecasts, etc.—with an interesting and compelling character. We are using Tank to investigate human-robot social interaction, especially long-term human-robot “relationships.” We have found that many visitors continue to interact with Tank's predecessor, Valerie the robot on a daily basis, but that few of the individual interactions last for more than 30 seconds. Our analysis of the data has indicated several design decisions that should facilitate more natural human-robot interactions.

While many researchers are investigating human-robot social interaction, one area that remains relatively unexplored is that of continued long-term interaction. The Roboceptionist (“robot receptionist”) Project, part of the Social Robots Project, is investigating how a social robot can remain compelling over a long period of time—days, weeks, and even years. Our approach is to create a robot that can provide useful services, but that also exhibits personality and character. The robot was designed for ease of interaction without requiring any training or expertise, and to be compelling enough to encourage multiple visits over extended periods of time. The character we have designed, named Tank, is built from a mobile base with a moving flat-panel monitor mountedon top, which displays a graphical human-like face. Tank remains stationary inside a small booth near the main entrance of Newell-Simon Hall at Carnegie Mellon University. Anyone who walks through the building, including students, faculty, and visitors, can interact with the robot.

The Social Robots Project began with the goal of investigating human-robot social interaction. Experiments with the robot Vikia studied the effects of attentive movement and an animated face on people’s willingness to engage in a short interaction with a robot [1]. These experiments confirmed the group’s intuitions that both movement and a recognizable face have a positive impact on human-robot social interaction. Grace, a joint project by our group and a number of other research institutions, has participated in the AAAI robot challenge for several years [2]. The challenge requires a robot to register for the conference, find the room it is scheduled to speak in, and give a short talk about its own capabilities. Social interaction is vital to performing these tasks successfully. Grace uses conversational capabilities similar to Tank’s to interact with workers at the registration desk in a socially appropriate manner. A number of other research groups are also using robots to explore social interaction. Kismet [3] and Sparky [4] both used facial expression and movement to interact with humans. Unlike Tank, these robots engaged in only short-term, nonverbal interactions, and their purpose was not to provide users with useful information. On the other hand, a number of robots have been designed over the years to serve as tour guides for museum visitors [5]–[7]. Like Tank and Valerie, their purpose is to inform as well as to entertain. These robots also use speech capabilities to provide users with useful information, and they use facial and emotional expressions to improve the quality of interaction. However, these interactions are fairly structured and primarily one-way—people do not actively converse with the robots. The Nursebot [8] is another robot that uses social competence to improve task performance. That project’s goals were similar to our own in that it aimed to create a robot that engaged in repeated interactions with people over an extended period of time. Robovie, an interactive humanoid robot, has been used in long-term interaction studies with children, but its designers noted that it “failed to keep most of the children’s interest after the 1st week” [9]. With Tank, we hope to maintain interest over longer periods.

The Roboceptionist Project is the product of a collaboration between the Robotics Institute and the School of Drama at Carnegie Mellon. Planning and design was conducted for almost a year prior to Valerie’s (Tank’s predecessor) deployment. Some of the major design decisions are detailed below.

We wanted the robot to be familiar and non-threatening to people who access the building (primarily non-roboticists).We chose a receptionist as Valerie’s role for several reasons:
• Receptionists have frequent interaction with the public, and people have well-understood expectations for how to interact with receptionists.
• Tank and Valerie are capable of handling some of the tasks that a receptionist would perform, such as looking up office numbers and providing directions.
• We could station the robot in a public space in order to maximize the number of interactions with humans. In addition, the robot could be located behind a desk, which provides some security for the hardware.

In order to make the robot a compelling presence, we elected to make it human-like in its interactions. The Drama group helped to imbue the robot with human characteristics by giving him a name, a personality, a back-story, and several storylines that unfold over time. Events in his life are related in “conversation” to visitors who stop to chat with her. In addition, people can keep up with Tank’s life online at http://www.roboceptionist.com.

Tank and Valerie before him, enable a new form of storytelling. His entire story, as well as character-related vocalizations and behaviors, were scripted by students in the School of Drama. Complex storylines interweave and evolve over a period of several months. For example, he has a checkered past with organizations like NASA and the CIA and he has a bad relationship with his father. Writers and designers must deal with a character that has no vocal intonation, no natural facial expressions, and no form of natural movement. Fundamental assumptions regarding the creation of live storytelling had to be reviewed; what works with humans often does not work with robots.

Tank’s “head” is a flat-screen LCD monitor mounted on pan-tilt unit. His “face” is a graphically
rendered 3D model. Her facial modeling and expressions were created by members of the Drama group. Choosing a graphical, rather than mechanical, face was a significant design decision. The flat-screen face offers several advantages over a mechanical face:
• The graphical face is very expressive, with the ability to move individual muscles to generate a wide range offacial expressions.
• A mechanical face is less reliable than a graphical one, due to its many moving parts.
• Changes can easily be made to the graphical face. For example, as part of one story, Valerie’s hairstyle changed. A physical mechanism would be more difficult to modify. The greatest disadvantage of the graphical face is that it lacks the physical embodiment of a mechanical face. In particular, although the head rotates to face visitors, it can be difficult to determine exactly where the robot is looking.

Decisions about the mode and structure of interactions were driven by a desire to ensure that visitors do not become frustrated with the system and are satisfied with the interactions.

1) Storytelling: One of Tank’s primary interaction modes is storytelling. Tank’s story is told in a very human way: subjectively and evolving over time. His story is revealed through monologues, which are styled as phone conversations with characters in her life. The writers from Drama crafted storylines that evolved over the school year. Storytelling was chosen in order to make the robot appear more human-like and thus to allow visitors to interact easily with him. Tank’s evolving life stories follow a well-known model—that of the soap opera, or of the currently popular “reality” show. By making Tank a compelling character, we hope to encourage people to visit the robot repeatedly over time, in the same way that they might eagerly tune in to each episode of Desperate Housewives, As the World Turns or Survivor.

2) Keyboard Input: Both speech and keyboard input modalities were considered for visitors’ interactions with Tank. Speech is more natural for most people, but keyboard input is easier to control and more reliable than any general speech recognition systems, which typically require either training for individual users or a drastic reduction in the allowable vocabulary [10]. In addition, having visitors interact vocally was unlikely to be robust due to the placement of the robot ina busy hallway. Speech recognition systems are generally poor at handling noise and echoes in the environment. While a head-worn microphone can reduce the effect of ambient noise, we felt that requiring visitors to first don a headset would detract significantly from the overall experience.

3) Chatbot: For handling natural language input, the decision to use a pattern-matching “chatbot” rather than a grammatical parser was based on the ease of adding information and being be able to recognize novel sentences. Grammatical parsing would make new sentences difficult to add, requiring additions to the dictionary and to the grammar, and few existing systems can handle sentence fragments well. The rule-based pattern-matching system that was chosen.
Adapted from:
Designing Robots for Long-Term Social Interaction for 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems


Rachel Gockley, Allison Bruce, Jodi Forlizzi, Marek Michalowski, Anne Mundell,
Stephanie Rosenthal, Brennan Sellner, Reid Simmons, Kevin Snipes, Alan C. Schultz †, and Jue Wang
Carnegie Mellon University, Pittsburgh PA
†Naval Research Laboratory, Washington DC

Copyright property of the IEEE

[1] A. Bruce, I. Nourbakhsh, and R. Simmons. The role of expressiveness
and attention in human-robot interaction. In IEEE Conference on
Robotics and Automation, 2002.
[2] R. Simmons et al. Grace: An autonomous robot for the AAAI robot
challenge. AAAI Magazine, 42:2:51–72, Summer 2003.
[3] C. Breazeal. and B. Scassellati. How to build robots that make
friends and influence people. In IEEE/RSJ International Conference
on Intelligent Robots and Systems (IROS1999) Kyonju, Korea., 1999.
[4] M. Scheeff. Experiences with Sparky: A social robot, 2000.
[5] Wolfram Burgard et al. Experiences with the interactive museum tourguide
robot. Artificial Intelligence, 114(1-2):3–55, 1999.
[6] T. Willeke, C. Kunz, and I. Nourbakhsh. The history of the mobot
museum robot series: An evolutionary study, 2001.
[7] R. Siegwart et al. Robox at Expo.02: A large scale installation of
personal robots. Robotics and Autonomous Systems, Special issue on
Socially Interactive Robots, 42:203–222, 2003.
[8] M. Montemerlo, J. Pineau, N. Roy, S. Thrun, and V. Verma. Experiences
with a mobile robotic guide for the elderly, 2002.
[9] Takayuki Kanda, Takayki Hirano, Daniel Eaton, and Hiroshi Ishiguro.
Interactive robots as social partners and peer tutors for children: A field
trial. Human-Computer Interaction, 19:61–84, 2004.
[10] R. Cole, J. Mariani, H. Uszkoreit, A. Zaenen, and V. Zue. Survey of the
state of the art in human language technology, 1995.

Tank at work in Newell-Simon