Towards vision-based deep reinforcement learning for robotic motion control

This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real hardware and real observation in a naive approach failed, but experiments show that the network works when replacing camera images with synthetic images.

Open source computer-vision based guidance system for UAVs on-board decision making

The use of UAVs for remote sensing tasks; e.g. agriculture, search and rescue is increasing. The ability for UAVs to autonomously find a target and perform on-board decision making, such as descending to a new altitude or landing next to a target is a desired capability. Computer-vision functionality allows the Unmanned Aerial Vehicle (UAV) to follow a designated flight plan, detect an object of interest, and change its planned path. In this paper we describe a low cost and an open source system where all image processing is achieved on-board the UAV using a Raspberry Pi 2 microprocessor interfaced with a camera. The Raspberry Pi and the autopilot are physically connected through serial and communicate via MAVProxy. The Raspberry Pi continuously monitors the flight path in real time through USB camera module. The algorithm checks whether the target is captured or not. If the target is detected, the position of the object in frame is represented in Cartesian coordinates and converted into estimate GPS coordinates. In parallel, the autopilot receives the target location approximate GPS and makes a decision to guide the UAV to a new location. This system also has potential uses in the field of Precision Agriculture, plant pest detection and disease outbreaks which cause detrimental financial damage to crop yields if not detected early on. Results show the algorithm is accurate to detect 99% of object of interest and the UAV is capable of navigation and doing on-board decision making.

A deadline-constrained 802.11 MAC Protocol with QoS differentiation for soft real-time control

As one of the most widely used wireless network technologies, IEEE 802.11 wireless local area networks (WLANs) have found a dramatically increasing number of applications in soft real-time networked control systems (NCSs). To fulfill the real-time requirements in such NCSs, most of the bandwidth of the wireless networks need to be allocated to high-priority data for periodic measurements and control with deadline requirements. However, existing QoS-enabled 802.11 medium access control (MAC) protocols do not consider the deadline requirements explicitly, leading to unpredictable deadline performance of NCS networks. Consequentially, the soft real-time requirements of the periodic traffic may not be satisfied, particularly under congested network conditions. This paper makes two main contributions to address this problem in wireless NCSs. Firstly, a deadline-constrained MAC protocol with QoS differentiation is presented for IEEE 802.11 soft real-time NCSs. It handles periodic traffic by developing two specific mechanisms: a contention-sensitive backoff mechanism, and an intra-traffic-class QoS differentiation mechanism. Secondly, a theoretical model is established to describe the deadline-constrained MAC protocol and evaluate its performance of throughput, delay and packet-loss ratio in wireless NCSs. Numerical studies are conducted to validate the accuracy of the theoretical model and to demonstrate the effectiveness of the new MAC protocol.

Development of a robust framework for an outdoor mobile manipulation UAV

There is a growing interest to autonomously collect or manipulate objects in remote or unknown environments, such as mountains, gullies, bush-land, or rough terrain. There are several limitations of conventional methods using manned or remotely controlled aircraft. The capability of small Unmanned Aerial Vehicles (UAV) used in parallel with robotic manipulators could overcome some of these limitations. By enabling the autonomous exploration of both naturally hazardous environments, or areas which are biologically, chemically, or radioactively contaminated, it is possible to collect samples and data from such environments without directly exposing personnel to such risks. This paper covers the design, integration, and initial testing of a framework for outdoor mobile manipulation UAV. The framework is designed to allow further integration and testing of complex control theories, with the capability to operate outdoors in unknown environments. The results obtained act as a reference for the effectiveness of the integrated sensors and low-level control methods used for the preliminary testing, as well as identifying the key technologies needed for the development of an outdoor capable system.

Uncertainty based online planning for UAV target finding in cluttered and GPS-denied environments

There are some scenarios in which Unmmaned Aerial Vehicle (UAV) navigation becomes a challenge due to the occlusion of GPS systems signal, the presence of obstacles and constraints in the space in which a UAV operates. An additional challenge is presented when a target whose location is unknown must be found within a confined space. In this paper we present a UAV navigation and target finding mission, modelled as a Partially Observable Markov Decision Process (POMDP) using a state-of-the-art online solver in a real scenario using a low cost commercial multi rotor UAV and a modular system architecture running under the Robotic Operative System (ROS). Using POMDP has several advantages to conventional approaches as they take into account uncertainties in sensor information. We present a framework for testing the mission with simulation tests and real flight tests in which we model the system dynamics and motion and perception uncertainties. The system uses a quad-copter aircraft with an board downwards looking camera without the need of GPS systems while avoiding obstacles within a confined area. Results indicate that the system has 100% success rate in simulation and 80% rate during flight test for finding targets located at different locations.

Modelado y control de estaci��n de c��lula de manipulaci��n

[ES]El objetivo de este proyecto es el dise��o e implementaci��n del modelo de la estaci��n FMS 201 (alimentaci��n de la base) y el dise��o e implementaci��n del control de la estaci��n. Esta estaci��n pertenece a la serie FMS 200 (sistema did��ctico modular de ensamblaje flexible) distribuido por la empresa SMC. Se dispone uno en el laboratorio de investigaci��n del departamento de Ingenier��a de Sistemas y Autom��tica de la Escuela Superior de Ingenier��a de Bilbao (EHU/UPV). Para el desarrollo e implementaci��n del modelo se usar�� la herramienta inform��tica Automation Studio. Para el control del modelo se usar�� el PLC. Para el intercambio de informaci��n entre modelo y controlador se utilizar�� la comunicaci��n OPC Para el control de la estaci��n se usa un PLC S7-300 de la marca SIEMENS. Se finaliza el documento realizando las pruebas de validaci��n del modelo desarrollado, ejecut��ndose el programa de control en el PLC y corriendo el modelo desarrollado en el PC.

������������������������������������

������������������������������������������������������������������������������������������������������������ .��������������������������������������������������������������������������� ,��������������������������������������������������������������� .������������������������������������������������������ ,��������������������������������������������������������������������������� ,���������������������������������������������������������

An evidential fusion approach for gender profiling

CCTV (Closed-Circuit TeleVision) systems are broadly deployed in the present world. To ensure in-time reaction for intelligent surveillance, it is a fundamental task for real-world applications to determine the gender of people of interest. However, normal video algorithms for gender profiling (usually face profiling) have three drawbacks. First, the profiling result is always uncertain. Second, the profiling result is not stable. The degree of certainty usually varies over time, sometimes even to the extent that a male is classified as a female, and vice versa. Third, for a robust profiling result in cases that a person���s face is not visible, other features, such as body shape, are required. These algorithms may provide different recognition results - at the very least, they will provide different degrees of certainties. To overcome these problems, in this paper, we introduce an Dempster-Shafer (DS) evidential approach that makes use of profiling results from multiple algorithms over a period of time, in particular, Denoeux���s cautious rule is applied for fusing mass functions through time lines. Experiments show that this approach does provide better results than single profiling results and classic fusion results. Furthermore, it is found that if severe mis-classification has occurred at the beginning of the time line, the combination can yield undesirable results. To remedy this weakness, we further propose three extensions to the evidential approach proposed above incorporating notions of time-window, time-attenuation, and time-discounting, respectively. These extensions also applies Denoeux���s rule along with time lines and take the DS approach as a special case. Experiments show that these three extensions do provide better results than their predecessor when mis-classifications occur.

Sistema de gesti�� integral d��� un restaurant amb TPV i Pocket PC

Aquest projecte fi de carrera es centra en un restaurant fictici i gen��ric anomenat "El Restaurant al Punt". Es tractar�� d' una empresa que s' inicia en el sector hostaler amb tot un seguit de coneixements previs per part dels propietaris. L' objectiu principal que es preten assolir en aquest projecte ��s: desenvolupar l' an��lisi, dissenyar i implementar una aplicaci�� inform��tica que permeti gestionar el funcionament d' un restaurant

Exploiting CAFS-ISP

In the summer of 1982, the ICLCUA CAFS Special Interest Group defined three subject areas for working party activity. These were: 1) interfaces with compilers and databases, 2) end-user language facilities and display methods, and 3) text-handling and office automation. The CAFS SIG convened one working party to address the first subject with the following terms of reference: 1) review facilities and map requirements onto them, 2) "Database or CAFS" or "Database on CAFS", 3) training needs for users to bridge to new techniques, and 4) repair specifications to cover gaps in software. The working party interpreted the topic broadly as the data processing professional's, rather than the end-user's, view of and relationship with CAFS. This report is the result of the working party's activities. The report content for good reasons exceeds the terms of reference in their strictest sense. For example, we examine QUERYMASTER, which is deemed to be an end-user tool by ICL, from both the DP and end-user perspectives. First, this is the only interface to CAFS in the current SV201. Secondly, it is necessary for the DP department to understand the end-user's interface to CAFS. Thirdly, the other subjects have not yet been addressed by other active working parties.

Productivity and the knowledge worker

The industrial age of Taylor and Ford transformed the landscape of office buildings. Office spaces were very uniform and highly supervised. People were units of production. Their work activities were routine. Work study, or &quot;time and motion&quot; studies measured outputs.<br /><br />The current &quot;information age&quot; way of working, combined with major demographic shifts in the workforce (Gen-Xers, career-shifting Baby Boomers and a greater number of women and minority ethnic groups in the workforce), requires major changes in how to support service industry productivity. The motivations of knowledge workers are very different from those of the industrial age worker. Commitment to the organisation has gone as a result of business re-engineering processes that increased productivity but at the expense of job security. Workers are more likely to be &quot;goal-focussed&quot; rather than &quot;prevention focussed&quot; (Meyer et al 2004 2 ) meaning that instead of doing only what is necessary to retain their job, workers actively seek more meaningful work that matches their personal value systems. They even want to have fun at work!<br /><br />What contribution can the workplace make to support this work and increase productivity? Surveys have indicated that workers spend more than 75% of their time in their own office space with more than half of that time spent in concentrated work. Concentrated work requires quiet with few distractions, yet workers report that distractions are probably the biggest problem hampering their productivity. What are the current workplace solutions to office space usage? Probably the worst option for distractions is frequently used &ndash; open-plan offices, which are a more cost-effective use of space, but at the potential expense of productivity. Visioning architects such as Duffy (1999)3 advocate quiet spaces (&quot;dens&quot;) where workers can decamp to carry out their concentrated work. But is this workspace as efficient for the worker &ndash; who may have to transport materials back and forth?<br /><br />Workers know what they need to support their productivity best. On the rare occasions when the staff have been given the opportunity to configure their work-settings, high productivity increases result. Besides noise, environmental quality is perceived as a key factor influencing productivity. Stuffy workplaces generate lethargy. Greater worker satisfaction with their workplace is reported when they have more individual control over the environment.<br /><br />We need to seriously question the &quot;one-size-fits-all&quot; office building with cellular layouts. Workers need to be involved in the design and fit-out. They need personal control over their environment and an organisation that can support their individual aspirations and values. A number of interventions that could generate significant improvements in knowledge work productivity are proposed.<br />

The implementation of mobile technology in organizations : expanding individual use contexts

Mobile computing devices such as personal digital assistants, smart mobile phones, and other handheld computing devices hold much promise in terms of their organizational application. Many existing models of the individual acceptance and implementation of information technology in organizational contexts have been developed in the era of &ldquo;at the office&rdquo; computing such as MIS, office automation, groupware, and so forth. We conducted two in-depth case studies of the implementation of mobile technology in healthcare organizations. The studies highlight interrelated individual use contexts due to the mobility of the technology: the individual as employee, as professional, as private user, and as member of society. The cases show that influences emanating from these use contexts impacted on the individual adoption of the technology within the organization. While broad extra-organizational influences are incorporated in some existing individual technology adoption models, we show that it becomes relevant to accommodate these influences more specifically in research models of mobile computing in organizations. Based on the extant literature and the case study data we pave the way toward more comprehensive models of the adoption and implementation of mobile technologies in organizations.

M��tricas de desempenho para sistema de alarmes de processos industriais

The evolution of automation in recent years made possible the continuous monitoring of the processes of industrial plants. With this advance, the amount of information that automation systems are subjected to increased significantly. The alarms generated by the monitoring equipment are a major contributor to this increase, and the equipments are usually deployed in industrial plants without a formal methodology, which entails an increase in the number of alarms generated, thus overloading the alarm system and therefore the operators of such plants. In this context, the works of alarm management comes up with the objective of defining a formal methodology for installation of new equipment and detect problems in existing settings. This thesis aims to propose a set of metrics for the evaluation of alarm systems already deployed, so that you can identify the health of this system by analyzing the proposed indices and comparing them with parameters defined in the technical norms of alarm management. In addition, the metrics will track the work of alarm management, verifying if it is improving the quality of the alarm system. To validate the proposed metrics, data from actual process plants of the petrochemical industry were used

Redes neurais artificiais no ambiente de redes industriais foundation fieldbus usando blocos funcionais padr��es

Industrial automation networks is in focus and is gradually replacing older architectures of systems used in automation world. Among existing automation networks, most prominent standard is the Foundation Fieldbus (FF). This particular standard was chosen for the development of this work thanks to its complete application layer specification and its user interface, organized as function blocks and that allows interoperability among different vendors' devices. Nowadays, one of most seeked solutions on industrial automation are the indirect measurements, that consist in infering a value from measures of other sensors. This can be made through implementation of the so-called software sensors. One of the most used tools in this project and in sensor implementation are artificial neural networks. The absence of a standard solution to implement neural networks in FF environment makes impossible the development of a field-indirect-measurement project, besides other projects involving neural networks, unless a closed proprietary solution is used, which dos not guarantee interoperability among network devices, specially if those are from different vendors. In order to keep the interoperability, this work's goal is develop a solution that implements artificial neural networks in Foundation Fieldbus industrial network environment, based on standard function blocks. Along the work, some results of the solution's implementation are also presented