Monitoring Robotic Swarm Systems Under Noisy Conditions Using an Effective Fault Detection Strategy

Abstract

Fault detection in robotic swarm systems is imperative to guarantee their reliability, safety, and to maximize operating efficiency and avoid expensive maintenance. However, data from these systems are generally contaminated with noise, which masks important features in the data and degrades the fault detection capability. This paper introduces an effective fault detection approach against noise and uncertainties in data, which integrates the multiresolution representation of data using wavelets with the sensitivity to small changes of an exponentially weighted moving average scheme. Specifically, to monitor swarm robotics systems performing a virtual viscoelastic control model for circle formation task, the proposed scheme has been applied to the uncorrelated residuals form principal component analysis model. A simulated data from ARGoS simulator is used to evaluate the effectiveness of the proposed method. Also, we compared the performance of the proposed approach to that of the conventional principal component-based approach and found improved sensitivity to faults and robustness to noises. For all the fault types tested-abrupt faults, random walks, and complete stop faults-our approach resulted in a significant enhancement in fault detection compared with the conventional approach.

Toward Emerging Cubic-Spline Patterns With a Mobile Robotics Swarm System

“…A robust control model should be tolerant to a certain level to such occurring faults. Here we are dealing with a certain type of faults called partial faults which has been specifically reported to have more impact in perturbing the overall performance of robotics swarm systems while compared to complete faults type [41]. Note that a partial fault type occurs when a robot' component doesn't stop completely to perform, but one of its sub-components is damaged or doesn't function properly.…”

A Data-Driven Soft Sensor for Swarm Motion Speed Prediction Using Ensemble Learning Methods

“…The physical law used in this study was applied in a number of our previous studies [? ], [29], [49]- [51] is based on a virtual viscoelastic force, which can be represented as a spring and damping elements connected in parallel. More formally, given a circle of a desired radius r, to be formed by N foot-bots distributed randomly inside an indoor area surrounded by four walls.…”

Sensor Selection for High-dimensional Swarm Systems Based on Observability Analysis

“…Although the concept of swarm system has several potential advantages, its large-scale and distributed communication network make faults more likely and threaten the system security [8]. To ensure the safe and effective operation of the system, it is necessary to develop monitoring mechanisms for the overall system [9], [10]. As a tool for information acquisition, it is critical to install enough sensors to the design of the monitoring mechanisms.…”