This article describes the software architecture of an autonomous, interact
ive tour-guide robot. It presents a modular and distributed software archit
ecture, which integrates localization, mapping, collision avoidance, planni
ng, and various modules concerned with user interaction and Web-based telep
resence. At its heart, the software approach relies on probabilistic comput
ation, on-line learning, and any-time algorithms. It enables robots to oper
ate safely, reliably, and at high speeds in highly dynamic environments, an
d does not require any modifications of the environment to aid the robot's
operation. Special emphasis is placed on the design of interactive capabili
ties that appeal to people's intuition. The interface provides new means fo
r human-robot interaction with crowds of people in public places, and it al
so provides people all around the world with the ability to establish a "vi
rtual telepresence" using the Web, To illustrate our approach, results are
reported obtained in mid-1997, when our robot "RHINO" was deployed for a pe
riod of six days in a densely populated museum. The empirical results demon
strate reliable operation in public environments. The robot successfully ra
ised the museum's attendance by more than 50%. In addition, thousands of pe
ople all over the world controlled the robot through the Web. We conjecture
that these innovations transcend to a much larger range of application dom
ains for service robots. (C) 1999 Elsevier Science B.V. All rights reserved
.