Autonomous aero-visual and sensor based inspection network for asset monitoring

Abstract

This article introduces a theoretical and experimental program to develop the inspection and fault detection technology needed to integrate MAVs for persistent intelligence, reconnaissance, maintenance and surveillance for obscured or logistically challenging assets in non-urban environments. The design is explained using a context of heterogeneous deployment of wireless sensors for real-time asset monitoring by anticipating exceptional conditions and building the system to cope with them. The system converges towards an error-free state with self-stabilization, the ability to fall back to a safe mode in a financially feasible manner. This sophisticated mechanism requires a real-time capacity estimation capability to sustain the quality-of-service, which can be achieved by a distributed sensor network. We discuss issues in design and information propagation in such sensor clustered topology, optimization for power-aware networking, and link and node capacity assignment to achieve the desired goals.