2^nd International Conference on Advanced Robotics, Mechatronics and Artificial Intelligence December 03-04, 2018 Valencia, Spain

Deep learning allows the computer to build complex concepts out of simpler concepts. Deep learning system can represent the concept of an image of a person by combining simpler concepts, such as corners and contours, which are in turn defined in terms of edges. The idea of learning the right representation for the data provides one perspective on deep learning. Another perspective on deep learning is that depth allows the computer to learn a multi-step computer program. Each layer of the representation can be thought of as the state of the computer’s memory after executing another set of instructions in parallel. Networks with greater depth can execute more instructions in sequence. Deep learning is a specific kind of machine learning.

Genetic Algorithms are heuristic search approaches that are applicable to a wide range of optimization problems. This flexibility makes them attractive for many optimization problems in practice. Evolution is the basis of Genetic Algorithms. It follows 3 rules and they are Selection rule, Cross over rule and Mutation Rule. Genetic operators change the solutions. Crossover operators combine the genomes of two or more solutions. Mutation adds randomness to solutions and should be scalable, drift-less, and reach each location in solution space. Genetic Algorithms are search based algorithms based on the concepts of natural selection and genetics. Genetic Algorithms are a subset of a much larger branch of computation known as Evolutionary Computation. Genetic algorithms optimize a given function by means of a random search. They are best suited for optimization and tuning problems in the cases where no prior information is available. As an optimization method genetic algorithm are much more effective than a random search. Genetic Algorithms are adaptive heuristic search algorithms that belong to the larger part of evolutionary algorithms. Genetic Algorithms have demonstrated to be effective procedures for solving multicriterial optimization problems. It is a very popular meta-heuristic technique for solving optimization problems. These algorithms mimic models of natural evolution and can adaptively search large spaces in near-optimal ways. They are commonly used to generate high-quality solutions for optimisation problems and search problems.

The concept of biomimetic control, i.e., control systems that mimic biological animals in the way they exercise control, rather than just humans, has led to the definition of a new class of biologically inspired robots that exhibit much greater robustness in performance in unstructured environments than the robots that are currently being built. A key feature of biomimetic robots is their capacity to adapt to the environment and ability to learn and react fast. However, a biomimetic robot is not just about learning and adaptation but also involves novel mechanisms and manipulator structures capable of meeting the enhanced performance requirements. Thus, biomimetic robots are being designed to be substantially more compliant and stable than conventionally controlled robots and will take advantage of new developments in materials, microsystems technology, as well as developments that have led to a deeper understanding of biological behaviour. 

Usually, the procedure of the planning and development of a process of an assembly, inspection and measurement equipment using machine vision is split into precise determination of tasks and goals like detection, recognition, grasping, handling, measurement, fault detection, etc. and into machine vision component selection and working conditions determination like camera, computer, lenses and optics, illumination, position determination, etc. 

A design-centric contribution to human-robot interaction. This includes the design of new robot morphologies and appearances, behaviour paradigms, interaction techniques and scenarios, and telepresence interfaces. The design research should support unique or improved interaction experiences or abilities for robots. The understanding and study of fundamental HRI principles that span beyond individual interfaces or projects. This includes detailing underlying interaction paradigms, theoretical concepts, new interpretations of known results, or new evaluation methodologies.

A Programmable Logic Controller (or PLC) is a specialised digital controller that can control machines and processes. it monitors inputs, makes decisions, and controls outputs in order to automate machines and processes. A building automation system is a system that controls and monitors building services. These systems can be built up in several different ways. In this chapter a general building automation system for a building with complex requirements due to the activity, such as a hospital, will be described. Real systems usually have several of the features and components described here but not all of them. The Automation level includes all the advanced controllers that controls and regulates the Field level devices in real time. 

Augmented Reality (AR) is a general-purpose term used for any view of reality where elements of that view are augmented with virtual imagery. Augmented Reality (AR) is a technology where the reality is augmented, enhanced with different types of virtual information. This information can be e.g. 3D models, text and images. With AR the user sees this information as an overlay on top of the real world. Unlike virtual reality where the user it totally immersed in the virtual world and cannot see anything but the virtual environment. To be able to place the overlay in the correct position the AR software can use different types of techniques. Some of these techniques are marker tracking, image recognition and the use of embedded sensors. Augmented reality (AR) creates an environment where computer generated information is superimposed onto the user’s view of a real-world scene.

Vehicle control can be defined as the set of tasks involved in navigating, guiding, and manoeuvring a vehicle2 via control of the electrical, mechanical and other devices provided on the vehicle for these purposes. Vehicle control can in its broadest sense be either entirely manual, entirely automated, or on a point somewhere along the continuum between these two extremes. The application of telematics to Vehicle Control involves the development and deployment of Autonomous and Infrastructure linked systems whose aim is to assist drivers in controlling their vehicle. ‘Automated Highway Systems’ or ‘Automated Vehicle Guidance’ is where vehicle guidance and control inputs are derived from on-board sensors, which can be supplemented by equipment residing outside the vehicle. Vehicle control is affected without intervention by the driver although driver override is still possible.

When a traditional feedback control system is closed via a communication channel, which may be shared with other nodes outside the control system, then the control system is called a Networked control system. An NCS can also be defined as a feedback control system wherein the control loops are closed through a real-time network. The defining feature of an NCS is that information (reference input, plant output, control input, etc.) is exchanged using a network among control system components (sensors, controllers, actuators, etc.,). Network controllers allow data to be shared efficiently. It is easy to fuse the global information to take intelligent decisions over a large physical space. They eliminate unnecessary wiring. It is easy to add more sensors, actuators and controllers with very little cost and without heavy structural changes to the whole system. Most importantly, they connect cyber space to physical space making task execution from a distance easily accessible.

In open loop control, it is assumed that the dynamical model of the system is well known, that there is little or no environmental noise and that the control signal can be applied with high precision. This approach is generally utilized when there is a target value, to achieve at a particular final time, T. The disadvantage of open-loop control is that the performance of the controller is highly susceptible to any unanticipated disturbances. In feedback control, continuous or discrete time measurements of the system output, y(t), are used to adjust the control signal in real time. At each instant, the observed process, y is compared to a tracking reference, r(t), and used to generate an error signal. Feedback therefore provides the backbone of most modern control applications. In learning control, a measurement of the system, y(t), is also used to design the optimal feedback signal; however, it is not done in real time. Instead, a large number of trial control signals are tested in advance, and the one that performs best is selected to be u â—¦ (t).

Autonomous systems have the capability to independently (and successfully) perform complex tasks. Consumer and governmental demands for such systems are frequently forcing engineers to push many functions normally performed by humans into machines. s a functional architecture for an intelligent autonomous controller with an interface to the process involving sensing (e.g., via conventional sensing technology, vision, touch, smell, etc.), actuation (e.g., via hydraulics, robotics, motors, etc.), and an interface to humans (e.g., a driver, pilot, crew, etc.) and other systems. The “execution level” has low-level numeric signal processing and control algorithms (e.g., PID, optimal, adaptive, or intelligent control; parameter estimators, failure detection and identification (FDI) algorithms). The “coordination level” provides for tuning, scheduling, supervision, and redesign of the execution-level algorithms, crisis management, planning and learning capabilities for the coordination of execution-level tasks, and higher-level symbolic decision making for FDI and control algorithm management. The “management level” provides for the supervision of lower-level functions and for managing the interface to the human(s) and other systems.