A proactive routing protocol called Multi-Mesh Tree (MMT) was developed for use in wireless ad hoc network to extend connectivity from an Internet gateway to around 20 mobile nodes in a city area. In the work presented here, we extend MMT to wireless ad hoc networks of around one hundred nodes through a clustering algorithm that is integrated into the MMT creation. The proposed scheme uses a hybrid approach, where the proactive MMT is used for intra cluster routing while a reactive MMT (RMMT) introduced in this article is used for inter cluster routing. We further propose a novel route discovery and route recording scheme using route request and route response messages but has low flooding overheads and exhibits high route stability under high node mobility conditions. We apply the proposed RMMT scheme to provide connectivity among moving teams of ground troops and present simulation results based on a study of this scenario.

This paper presents the application of a connectionist control-learning system to an autonomous mini-robot. The system's design is severely constrained by the computing power and memory available on board the mini-robot and the on-board training time is greatly limited by the short life of the battery. The system is capable of rapid unsupervised learning of output responses in temporal domains through the use of eligibility traces and data sharing within topologically defined neighborhoods.