In this work, a wireless communication system based on magnetic coils for underwater vehicles is presented. Firstly, the mathematical model of magnetic field induction using magnetic coils is discussed. Then, a description of the proposed communication system is presented, including the main components of the transmitter and receiver module. The experimental results show that due to the properties of the magnetic field, the proposed communication system can work properly in different environments such as air or water with the same efficiency. Underwater tests were carried out in different water circumstances: varying the temperature in a range from 10 °C to 35 °C, varying concentrations of clay in a range from 0% to 10%, and varying the salinity concentration in a range from 1000 ppm ( parts per million) to 35,000 ppm. It was observed that these conditions do not affect the information transfer. Finally, the advantages of using the proposed system compared to existing submarine communication systems are discussed.

Artificial neural networks (ANNs) are artificial intelligence techniques that have made autonomous driving more efficient and accurate; however, autonomous driving faces ongoing challenges in the accuracy of decision making based on the analysis of the vehicle environment. A critical task of ANNs is steering angle prediction, which is essential for safe and effective navigation of mobile robots and autonomous vehicles. In this study, to optimize steering angle prediction, NVIDIA’s architecture was adapted and modified along with the implementation of the Swish activation function to train convolutional neural networks (CNNs) by behavioral cloning. The CNN used human driving data obtained from the UDACITY beta simulator and tests in real scenarios, achieving a significant improvement in the loss function during training, indicating a higher efficiency in replicating human driving behavior. The proposed neural network was validated through implementation on a differential drive mobile robot prototype, by means of a comparative analysis of trajectories in autonomous and manual driving modes. This work not only advances the accuracy of steering angle predictions but also provides valuable information for future research and applications in mobile robotics and autonomous driving. The performance results of the model trained with the proposed CNN show improved accuracy in various operational contexts.

In this article, the model of a family of underwater vehicle multi-manipulator systems (UVMMS) is obtained by considering all its elements as parts of a unique system, the model includes the forces produced on the manipulators by the movement of the vehicle, as well as the reaction forces on the vehicle produced by the movement of the manipulators. The modeling process is completed using the Newton–Euler approach through the mobile arborescent kinematic chain. This work also presents different approaches to the use of numerical implementations of the proposed model, and simulation results are included to demonstrate that the model is capable to represent the interaction between the vehicle and the manipulators. The proposed model and simulations are important because they allow the design of control strategies that consider all the elements of the system instead of neglecting the interaction forces or considering the vehicle and the arms as uncoupled elements.

This paper presents an application of the active disturbance rejection control approach for humanoid robot stable walking, which is a control strategy based on the extended state observer and cascade integrator canonical form features from modern control theory to deal with disturbances, nonlinearities and unmodeled dynamics. The proposed controller is based on the 3D linear inverted pendulum walking pattern generation, and is designed to be triggered only if disturbance signals are detected. This control technique was tested on the model of a humanoid robot using numerical simulation software, showing successful results that motivate to implement it in a real humanoid robot platform.

In the present work, a path planning generation method is proposed, it is based on the learning and query phases of the original probabilistic roadmap (PRM) method, but a more efficient approach is presented, also an additional simplification and optimization phases are added to minimize the length of the resulting trajectory. The proposed method produces safe paths for navigation in a known static map without increasing execution time. The proposed method is compared to the existing implementation of the PRM method, available in Matlab. Finally a simple kinematic controller is presented to show realistic simulations of the trajectory realization, for this test real maps are used, which are obtained by means of the SLAM algorithm.