No abstract

No abstract

No abstract

Computer vision, together with bayesian estimation algorithms, sensors and actuators are used in robotics to solve a variety of critical tasks such as localization, obstacle avoidance, and navigation. Visual servoing uses computer vision algorithms to guide robot movements. Classical approaches in visual servoing systems relied on extracting features from images to control robot movements. Now, state of the art computer vision systems use deep neural networks for object recognition, detection, segmentation, and tracking. These networks and specialized controllers play a predominant role in the design and implementation of modern visual servoing systems due to their accuracy, flexibility, and adaptability. Recent research in direct systems for visual servoing has created robotic systems that rely only on the information extracted from images. Furthermore, end-to-end systems eliminate entirely the controller by learning the control laws during training.This paper presents a comprehensive survey on the state of the art in visual servoing systems, discussing the latest classical methods not included in other surveys but emphasizing the new approaches based on deep neural networks and their applications within robotics.

Due to the harsh weather conditions, severe spatial limitations and extreme high safety requirements, the indoor climate control for offshore oil & gas production platforms is much more challenging than any on-shore situations. For instance, the indoor pressure of man-board quarters should be kept all the way above the ambient pressure according to safety regulations. Meanwhile, the indoor air needs to be regularly changed in order to guarantee the indoor air quality. Both requirements could be possibly achieved by automatically manipulating either the throttle valve located at the terminal of the inlet channel in the considered Heating Ventilation and AirCondition (HVAC) system, or the pressurization system located inside the inlet channel, or both of them in a coordinated way. A Model-Predictive Control (MPC) solution to control the inlet throttle has been proposed in our previous work. This paper proposes a set of control solutions to regulate the variablespeed pressurization fan system such that the energy efficiency of the considered HVAC system can be explicitly considered. A combined feed-forward with a PI-based feedback control solution, and a MPC solution are proposed based on derived simple system models. Some preliminary simulation results exhibit that both control solutions can keep the indoor pressure and the air circulation in a very satisfactory and robust manner, even subject to the presence of severe disturbances.