Machine learning (ML) is a branch of artificial intelligence that has been developing at a dynamic pace in recent years. ML is also linked with Big Data, which are huge datasets that need special tools and approaches to process them. ML algorithms make use of data to learn how to perform specific tasks or make appropriate decisions. This paper presents a comprehensive survey of recent ML approaches that have been applied to the task of mobile robot control, and they are divided into the following: supervised learning, unsupervised learning, and reinforcement learning. The distinction of ML methods applied to wheeled mobile robots and to walking robots is also presented in the paper. The strengths and weaknesses of the compared methods are formulated, and future prospects are proposed. The results of the carried out literature review enable one to state the ML methods that have been applied to different tasks, such as the following: position estimation, environment mapping, SLAM, terrain classification, obstacle avoidance, path following, learning to walk, and multirobot coordination. The survey allowed us to associate the most commonly used ML algorithms with mobile robotic tasks. There still exist many open questions and challenges such as the following: complex ML algorithms and limited computational resources on board a mobile robot; decision making and motion control in real time; the adaptability of the algorithms to changing environments; the acquisition of large volumes of valuable data; and the assurance of safety and reliability of a robot’s operation. The development of ML algorithms for nature-inspired walking robots also seems to be a challenging research issue as there exists a very limited amount of such solutions in the recent literature.

Today, specific convolution neural network (CNN) models assigned to specific tasks are often used. In this article, the authors explored three models: MobileNet, EfficientNetB0, and InceptionV3 combined. The authors were interested in investigating how quickly an artificial intelligence model can be taught with limited computer resources. Three types of training bases were investigated, starting with a simple base verifying five colours, then recognizing two different orthogonal elements, followed by more complex images from different families. This research aimed to demonstrate the capabilities of the models based on training base parameters such as the number of images and epoch types. Architectures proposed by the authors in these cases were chosen based on simulation studies conducted on a virtual machine with limited hardware parameters. The proposals present the advantages and disadvantages of the different models based on the TensorFlow and Keras libraries in the Jupiter environment based on the Python programming language. An artificial intelligence model with a combination of MobileNet, proposed by Siemens, and Efficient and Inception, selected by the authors, allows for further work to be conducted on image classification, but with limited computer resources for industrial implementation on a programmable logical controller (PLC). The study showed a 90% success rate, with a learning time of 180 s.

Concepts in maritime issues such as Maritime Autonomous Surface Ships (MASS) have been known for several years. At present, it is difficult to define clear rules for the cooperation of multiple systems for autonomous control, i.e., unmanned operation, which is written in the MASS requirements for the various degrees of control (four degrees). The paper proposes a multidimensional control of a ship on a certain determined trajectory, where a model of a training ship sails autonomously in restricted waters in a port. The control algorithm is based on the synthesis of a Linear Matrix Inequalities (LMI) controller and an overriding trajectory controller. The automation is divided into two parts. The master trajectory controller converts the ship’s position and course into small velocities, which, with the help of the LMI controller through an allocation system, control the operation of the ship’s propellers. The setpoints are specific twelve trajectory points given in the form of x, y coordinates and the ship’s course. The tests were carried out under real conditions and showed a silhouette of the ship performing the maneuver and a reading of the individual speeds, wind parameters and GPS mode. The solution presented is used to address MASS 3 level control.

The concept of the Marine Autonomous Surface Ship (MASS) requires new solutions in many areas: from law, through economics, social sciences, environmental issues to the technology and even ethics. It also plays a central role in the work of numerous research teams dealing with the ship motion control systems. This article presents the results of the experiments with application of the selected control methods in automatic steering of the movement of an autonomous ship in the two regimes: during the maneuvers at low speed (in a harbor confined waters) and during the lake trials in open water conditions. In the first case, multidimensional state controller synthesized with Linear Matrix Inequalities (LMI) algorithms was used, while, in the second case, Model Predictive Control (MPC) control was adopted. The object for which the experiments were carried out was 1:24 scale model of the Liquefied Natural Gas (LNG) carrier. The paper presents also the design of the measurement and control system and the user interface. The experiments were conducted in the natural conditions on the lake. The results of the experiments indicate the fundamental role of the measurement system in the process of controlling an autonomous ship.

The article described two full multidimensional controllers applied to steer a real vessel named ‘Blue Lady’ that is used by the Foundation for Safety of Navigation and Environment Protection at its training and research facility loacted at Silm lake in Poland. Both controllers were based on different approaches, but finally gave similar results. The first part describes the object to be controlled which is a training ship used for training of navigators in various conditions, areas and manoeuvres. This is followed by a short description of the theory for both controllers, Robust and Linear Matrix Inequalities (LMI). Next real time trials are described, which are 3 different manouvers for low velocities, executed by both LMI and Robust contrllers. In these trials ‘Blue Lady’ velocities, silhouete trajectory ans wind data are recorded. Finally the quality of work for both controllers is collected in two tables.

The article presents the synthesis of a multi-layer group control system for a marine autonomous surface vessel with the use of modern control theory methods. First, an evolutionary programming algorithm for determining the optimal route path was presented. Then the algorithms—dynamic programming with neural state constraints, ant colony, and neuro-phase safe control algorithms—were presented. LMI and predictive line-of-sight methods were used for optimal control. The direct control layer is implemented in multi-operations on the principle of switching. The results of the computer simulation of the algorithms were used to assess the quality control.