Estimation of User’s Request for Attentive Deskwork Support System

Since the late 1990s, several studies have been conducted on intelligent systems that support daily life in the home or office environments (Sato et al., 1996; Pentland, 1996; Brooks, 1997). In daily life, people spend a significant amount of time at desks to operate computers, read and write documents and books, eat, and assemble objects, among other activities. Therefore it can be said that supporting deskwork by intelligent systems is of extreme importance. Many kinds of intelligent systems have been proposed to provide desktop support. In particular, augmented desk interface systems have been eagerly studied. DigitalDesk is one of the earliest augmented desk interface systems (Wellner, 1993). It requires a CCD camera and a video projector to integrate physical paper documents and electronic documents. Koike et al. proposed EnhancedDesk, which uses an infrared camera instead of a CCD camera to improve sensitivity to changes in lighting conditions and a complex background (Koike et al., 2001). In addition, Leibe et al. proposed one called Perceptive Workbench, which requires both a CCD and an infrared camera (Leibe et al., 2000), and Rekimoto proposed SmartSkin, which is based on capacitive sensing without cameras (Rekimoto, 2002). Raghavan et al. proposed a system that requires a head-mounted display to show how to assemble products (Raghavan et al., 1999). These systems have been limited to show some information to the user. Ishii & Ullmer proposed an idea referred to as "tangible bits (Ishii & Ullmer, 1997)," which seeks to realize a seamless interface among humans, digital information, and the physical environment by using manipulable objects. Based on this idea, they proposed metaDESK (Ullmer & Ishii, 1997). Pangaro et al. proposed a system called Actuated Workbench (Pangaro et al., 2002), and Noma et al. proposed one called Proactive Desk (Noma et al., 2004). Both systems convey only information to the user through movement of physical objects. They do not support the user from physical aspects. On the other hand, especially in rehabilitation robotics, several studies have been conducted on supporting humans working at desks from a physical aspect (Harwin et al., 1995; Dallaway et al., 1995). Dallaway & Jackson proposed RAID (Robot for Assisting the Integration of Disabled people) workstation (Dallaway & Jackson, 1994). In RAID, a user selects an object through a GUI, and a manipulator carries it to the user. Ishii et al. proposed a meal-assistance robot for disabled individuals (Ishii et al., 1995). The system user points a laser attached to his head to operate a manipulator. Topping proposed a system, Handy 1, 16