Loss of Distributed Coverage Using Lazy Agents Operating Under Discrete, Local, Event-Triggered Communication

TL;DR

This paper studies how asynchronous, event-driven communication among lazy robots can cause coverage loss in distributed surveillance, revealing that the number of robots critically affects coverage guarantees and scalability.

Contribution

It demonstrates that a well-known coverage algorithm can lose coverage under certain communication sequences when robot numbers exceed a threshold, highlighting scalability issues.

Findings

Coverage loss occurs with certain communication sequences and robot counts.

Coverage guarantees are sensitive to the number of robots.

Validation scenarios should match deployment robot numbers.

Abstract

Continuous surveillance of a spatial region using distributed robots and sensors is a well-studied application in the area of multi-agent systems. This paper investigates a practically-relevant scenario where robotic sensors are introduced asynchronously and inter-robot communication is discrete, event-driven, local and asynchronous. Furthermore, we work with lazy robots; i.e., the robots seek to minimize their area of responsibility by equipartitioning the domain to be covered. We adapt a well-known algorithm which is practicable and known to generally work well for coverage problems. For a specially chosen geometry of the spatial domain, we show that there exists a non-trivial sequence of inter-robot communication events which leads to an instantaneous loss of coverage when the number of robots exceeds a certain threshold. The same sequence of events preserves coverage and, further, leads to an equipartition of the domain when the number of robots is smaller than the threshold. This result demonstrates that coverage guarantees for a given algorithm might be sensitive to the number of robots and, therefore, may not scale in obvious ways. It also suggests that when such algorithms are to be verified and validated prior to field deployment, the number of robots or sensors used in test scenarios should match that deployed on the field.