Leader-Following Consensus and Formation Control of VTOL-UAVs with Event-Triggered Communications †

A Robust Deep Feature Extraction Method for Human Activity Recognition Using a Wavelet Based Spectral Visualisation Technique

Human Activity Recognition (HAR), alongside Ambient Assisted Living (AAL), are integral components of smart homes, sports, surveillance, and investigation activities. To recognize daily activities, researchers are focusing on lightweight, cost-effective, wearable sensor-based technologies as traditional vision-based technologies lack elderly privacy, a fundamental right of every human. However, it is challenging to extract potential features from 1D multi-sensor data. Thus, this research focuses on extracting distinguishable patterns and deep features from spectral images by time-frequency-domain analysis of 1D multi-sensor data. Wearable sensor data, particularly accelerator and gyroscope data, act as input signals of different daily activities, and provide potential information using time-frequency analysis. This potential time series information is mapped into spectral images through a process called use of 'scalograms', derived from the continuous wavelet transform. The deep activity features are extracted from the activity image using deep learning models such as CNN, MobileNetV3, ResNet, and GoogleNet and subsequently classified using a conventional classifier. To validate the proposed model, SisFall and PAMAP2 benchmark datasets are used. Based on the experimental results, this proposed model shows the optimal performance for activity recognition obtaining an accuracy of 98.4% for SisFall and 98.1% for PAMAP2, using Morlet as the mother wavelet with ResNet-101 and a softmax classifier, and outperforms state-of-the-art algorithms.

A Cooperative ADRC-Based Approach for Angular Velocity Synchronization and Load-Sharing in Servomechanisms

This paper is concerned with designing a dynamical synchronization (via a robust cooperative control) of an electromechanical system network (EMSN), consisting of nonidentical brushed DC motors, where only the motors’ angular velocity measurements are available. The challenge of the proposed approach is that the actuation provided by the motor needs to handle external disturbances to achieve the velocity tracking task and handle the interaction between both motors cooperatively to share the load and the disturbance rejection. The control’s basis involves differential flatness and an active disturbance rejection control (ADRC) framework augmented using ideas from the graph theory analysis and multi-agent networks. Experimental results verify the theoretical developments and show the effectiveness of the proposed control strategy despite unexpectedly changing load disturbance and parameters uncertainties. The proposed algorithm is suitable for embedded use due to its simplicity. It can be applied to a broad spectrum of mechatronic systems where dual-motor drive arrangements are necessary.

Devising a Distributed Co-Simulator for a Multi-UAV Network

Practical evaluation of the Unmanned Aerial Vehicle (UAV) network requires a lot of money to build experiment environments, which includes UAVs, network devices, flight controllers, and so on. To investigate the time-sensitivity of the multi-UAV network, the influence of the UAVs' mobility should be precisely evaluated in the long term. Although there are some simulators for UAVs' physical flight, there is no explicit scheme for simulating both the network environment and the flight environments simultaneously. In this paper, we propose a novel co-simulation scheme for the multiple UAVs network, which performs the flight simulation and the network simulation simultaneously. By considering the dependency between the flight status and networking situations of UAV, our work focuses on the consistency of simulation state through synchronization among simulation components. Furthermore, we extend our simulator to perform multiple scenarios by exploiting distributed manner. We verify our system with respect to the robustness of time management and propose some use cases which can be solely simulated by this.

Research on the Multiagent Joint Proximal Policy Optimization Algorithm Controlling Cooperative Fixed-Wing UAV Obstacle Avoidance

Multiple unmanned aerial vehicle (UAV) collaboration has great potential. To increase the intelligence and environmental adaptability of multi-UAV control, we study the application of deep reinforcement learning algorithms in the field of multi-UAV cooperative control. Aiming at the problem of a non-stationary environment caused by the change of learning agent strategy in reinforcement learning in a multi-agent environment, the paper presents an improved multiagent reinforcement learning algorithm-the multiagent joint proximal policy optimization (MAJPPO) algorithm with the centralized learning and decentralized execution. This algorithm uses the moving window averaging method to make each agent obtain a centralized state value function, so that the agents can achieve better collaboration. The improved algorithm enhances the collaboration and increases the sum of reward values obtained by the multiagent system. To evaluate the performance of the algorithm, we use the MAJPPO algorithm to complete the task of multi-UAV formation and the crossing of multiple-obstacle environments. To simplify the control complexity of the UAV, we use the six-degree of freedom and 12-state equations of the dynamics model of the UAV with an attitude control loop. The experimental results show that the MAJPPO algorithm has better performance and better environmental adaptability.