This research addresses the problem of achieving fault-tolerant cooperation
within small- to medium-sized teams of heterogeneous mobile robots. We des
cribe a novel behavior-based, fully distributed architecture, called ALLIAN
CE, that utilizes adaptive action selection to achieve fault tolerant coope
rative control in robot missions involving loosely coupled tasks. The robot
s in this architecture possess a variety of high-level functions that they
can perform during a mission, and must at all times select an appropriate a
ction based on the requirements of the mission, the activities of other rob
ots, the current environmental conditions, and their own internal states. S
ince such cooperative teams often work in dynamic and unpredictable environ
ments, the software architecture allows the team members to respond robustl
y and reliably to unexpected environmental changes and modifications in the
robot team that may occur due to mechanical failure, the learning of new s
kills, or the addition or removal of robots from the team by human interven
tion. After presenting ALLIANCE, we describe in detail our experimental res
ults of an implementation of this architecture on a team of physical mobile
robots performing a cooperative box pushing demonstration. These experimen
ts illustrate the ability of ALLIANCE to achieve adaptive, fault-tolerant c
ooperative control amidst dynamic changes in the capabilities of the robot
team. (C) 1999 Elsevier Science B.V. All rights reserved.