Decentralized Mesh-Based Model Predictive Control for Swarms of UAVs

Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach

This work has two objectives. Firstly, it describes a novel physics-informed hybrid neural network (PIHNN) model based on the long short-term memory (LSTM) neural network. The presented model structure combines the first-principle process description and data-driven neural sub-models using a specialized data fusion block that relies on fuzzy logic. The second objective of this work is to detail a computationally efficient model predictive control (MPC) algorithm that employs the PIHNN model. The validity of the presented modeling and MPC approaches is demonstrated for a simulated polymerization reactor. It is shown that the PIHNN structure gives very good modeling results, while the MPC controller results in excellent control quality.

Forgery Cyber-Attack Supported by LSTM Neural Network: An Experimental Case Study

This work is concerned with the vulnerability of a network industrial control system to cyber-attacks, which is a critical issue nowadays. This is because an attack on a controlled process can damage or destroy it. These attacks use long short-term memory (LSTM) neural networks, which model dynamical processes. This means that the attacker may not know the physical nature of the process; an LSTM network is sufficient to mislead the process operator. Our experimental studies were conducted in an industrial control network containing a magnetic levitation process. The model training, evaluation, and structure selection are described. The chosen LSTM network very well mimicked the considered process. Finally, based on the obtained results, we formulated possible protection methods against the considered types of cyber-attack.

Decentralized Triangular Guidance Algorithms for Formations of UAVs

This paper deals with the design of a guidance control system for a swarm of unmanned aerial systems flying at a given altitude, addressing flight formation requirements that can be formulated constraining the swarm to be on the nodes of a triangular mesh. Three decentralized guidance algorithms are presented. A classical fixed leader–follower scheme is compared with two alternative schemes: the former is based on the self-identification of one or more time-varying leaders; the latter is an algorithm without leaders. Several operational scenarios have been simulated involving swarms with obstacles and an increasing number of aircraft in order to prove the effectiveness of the proposed guidance schemes.

Computationally Efficient Nonlinear Model Predictive Control Using the L1 Cost-Function

Model Predictive Control (MPC) algorithms typically use the classical L2 cost function, which minimises squared differences of predicted control errors. Such an approach has good numerical properties, but the L1 norm that measures absolute values of the control errors gives better control quality. If a nonlinear model is used for prediction, the L1 norm leads to a difficult, nonlinear, possibly non-differentiable cost function. A computationally efficient alternative is discussed in this work. The solution used consists of two concepts: (a) a neural approximator is used in place of the non-differentiable absolute value function; (b) an advanced trajectory linearisation is performed on-line. As a result, an easy-to-solve quadratic optimisation task is obtained in place of the nonlinear one. Advantages of the presented solution are discussed for a simulated neutralisation benchmark. It is shown that the obtained trajectories are very similar, practically the same, as those possible in the reference scheme with nonlinear optimisation. Furthermore, the L1 norm even gives better performance than the classical L2 one in terms of the classical control performance indicator that measures squared control errors.

Path Planning and Collision Risk Management Strategy for Multi-UAV Systems in 3D Environments

Multi-UAV systems are attracting, especially in the last decade, the attention of researchers and companies of very different fields due to the great interest in developing systems capable of operating in a coordinated manner in complex scenarios and to cover and speed up applications that can be dangerous or tedious for people: search and rescue tasks, inspection of facilities, delivery of goods, surveillance, etc. Inspired by these needs, this work aims to design, implement and analyze a trajectory planning and collision avoidance strategy for multi-UAV systems in 3D environments. For this purpose, a study of the existing techniques for both problems is carried out and an innovative strategy based on Fast Marching Square—for the planning phase—and a simple priority-based speed control—as the method for conflict resolution—is proposed, together with prevention measures designed to try to limit and reduce the greatest number of conflicting situations that may occur between vehicles while they carry out their missions in a simulated 3D urban environment. The performance of the algorithm is evaluated successfully on the basis of certain conveniently chosen statistical measures that are collected throughout the simulation runs.

Fast Real-Time Model Predictive Control for a Ball-on-Plate Process

This work is concerned with an original ball-on-plate laboratory process. First, a simplified process model based on state–space process description is derived. Next, a fast state–space MPC algorithm is discussed. Its main advantage is computational simplicity: the manipulated variables are found on-line using explicit formulas with parameters calculated off-line; no real-time optimization is necessary. Software and hardware implementation details of the considered MPC algorithm using the STM32 microcontroller are presented. Tuning of the fast MPC algorithm is discussed. To show the efficacy of the MPC algorithm, it is compared with the classical PID and LQR controllers.