An efficient algorithm which finds collision free paths for a manipulator with 5 or 6 revolute joints is described. It solves the problem for four degree of freedom pick and place operations. Examples are given of paths found by the algorithm in tightly cluttered workspaces. The algorithm first describes free space in two ways: as freeways for the hand and payload ensemble and as freeways for the upperarm. Freeways match volumes swept out by manipulator motions and can be "inverted" to find a class of topologically equivalent path segments. The two freeway spaces are searched concurrently under projection of constraints determined by motion of the forearm.

Bildverarbeitungssysteme bieten innovative Lösungen für den Fertigungsprozess. Kameras und zugehörige Bildverarbeitungssysteme können zur Identifizierung, Prüfung und Lokalisierung von Teilen auf einem Förderband oder in einem Behälter mit Teilen eingesetzt werden. Roboter werden dann eingesetzt,um jedes Teil aufzunehmen und im Montagebereich zu platzieren oder sogar um die Grundmontage direkt durchzuführen. Das System für dieses Projekt besteht aus einem Roboter Kuka KR6 900, der die Position (x-, y- und z-Koordinaten des Objektschwerpunkts) und die Ausrichtung eines Bauteils von einem Bildverarbeitungssystem basierend auf einem Jetson Nano erhält. Das Ziel dieses Projekts ist es, eine automatische Erkennung eines Objekts mit Hilfe einer 2D-Kamera und der Auswertung mit dem Deep Learning Algorithmus Darknet YOLO V4 durchzuführen, so dass der Roboter das Objekt greifen und platzieren kann. Dieses Projekt verwendet zwei verschiedene Objekttypen: einen Quader und einen Zylinder. Die Bilderkennung erfolgt mit Hilfe des Jetson Nano, dort erfolgt aus den Pixelkoordinaten die Berechnung der realen Koordinaten, die dann über die TCP/IP-Schnittstelle des Kuka KR6 900 zur Durchführung der Entnahme und Platzierung übermittelt werden. Die Flexibilität des Roboters, dessen Steuerung auf diese Weise von der Bildverarbeitung unterstützt wird, kann den Bedarf an präzise konstruierten Teilezuführungen verringern und so die Flexibilität in der Fertigungszelle erhöhen und kurze Produktionsläufe und Anpassungsfähigkeit ermöglichen.

Made available in DSpace on 2015-03-05T14:01:20Z (GMT). No. of bitstreams: 0 Previous issue date: 23 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Este trabalho aborda o problema da otimização relacionado ao ciclo de operação de uma insersora automática de componentes (pick-and-place) em máquinas do tipo multi-head. O objetivo consiste em desenvolver uma técnica computacional capaz de encontrar uma boa solução para o problema de otimização, associado ao processo de inserção de componentes. A otimização consiste em resolver de forma conjunta, os Problemas de Escalonamento das Ferramentas, de Escalonamento da Seqüência de Inserção de Componentes e por fim, o Problema da Alocação dos Componentes no Alimentador, visando a redução do tempo total de operação. Como resultados, a técnica computacional permite elevar a produtividade das máquinas onde a mesma é aplicada. Neste trabalho, foi desenvolvida uma aplicação híbrida das metaheurísticas Busca Tabu e Algoritmos Genéticos. Através do uso de uma abordagem diferenciada e utilizando metaheurísticas contemporâneas, bons resultados são apresentados ao longo do trabalho. / This work approaches the optimization Problem related to the operation cycle in an automatic multi-head SMT placement machine (pick-and-place). The objective of this work is developing a computational technique capable to find a good solution for the optimization problem associated with the component insertion process. The optimization process was planned to solve in a joint way the Tools Scheduling Problem, Schedule of Component Insertion Sequence Problem and finally the Component Feeder Allocation Problem. The main objective is to reduce the total operation time. As a result the computational technique can increase the productivity of the machines where it is applied. This study developed a hybrid application of Tabu Search and Genetic Algorithms. The use of a differentiated approach combined with modern metaheuristics, good results are presented in the work.

In this thesis, a strategy to accomplish pick-and-place operations using a six degree-of-freedom (DOF) robotic arm attached to a wheeled mobile robot is presented. This research work is part of a bigger project in developing a robotic-assisted nursing to be used in medical settings. The significance of this project relies on the increasing demand for elderly and disabled skilled care assistance which nowadays has become insufficient. Strong efforts have been made to incorporate technology to fulfill these needs. Several methods were implemented to make a 6-DOF manipulator capable of performing pick-and-place operations. Some of these methods were used to achieve specific tasks such as: solving the inverse kinematics problem, or planning a collision-free path. Other methods, such as forward kinematics description, workspace evaluation, and dexterity analysis, were used to describe the manipulator and its capabilities. The manipulator was accurately described by obtaining the link transformation matrices from each joint using the Denavit-Hartenberg (DH) notations. An Iterative Inverse Kinematics method (IIK) was used to find multiple configurations for the manipulator along a given path. The IIK method was based on the specific geometric characteristic of the manipulator, in which several joints share a common plane. To find admissible solutions along the path, the workspace of the manipulator was considered. Algebraic formulations to obtain the specific workspace of the 6-DOF manipulator on the Cartesian coordinate space were derived from the singular configurations of the manipulator. Local dexterity analysis was also required to identify possible orientations of the end-effector for specific Cartesian coordinate positions. The closed-form expressions for the range of such orientations were derived by adapting an existing dexterity method. Two methods were implemented to plan the free-collision path needed to move an object from one place to another without colliding with an obstacle. Via-points were added to avoid the robot mobile platform and the zones in which the manipulator presented motion difficulties. Finally, the segments located between initial, final, and via-points positions, were connected using straight lines forming a global path. To form the collision-free path, the straight-line were modified to avoid the obstacles that intersected the path. The effectiveness of the proposed analysis was verified by comparing simulation and experimental results. Three predefined paths were used to evaluate the IIK method. Ten different scenarios with different number and pattern of obstacles were used to verify the efficiency of the entire path planning algorithm. Overall results confirmed the efficiency of the implemented methods for performing pick-and-place operations with a 6-DOF manipulator.

Robotic automation has been the major driving force in modern industrial developments. High speed pick-and-place operations find their place in many manufacturing applications. The goal of this project is to develop a class of high speed robots that has a planar workspace. The presented robots are intended for pick-and-place applications that have a relatively large workspace. In order to achieve this goal, the robots must be both stiff and light. The design strategies adapted in this study were expanded from the research work by Prof Khajepour and Dr. Behzadipour. The fundamental principles are to utilize a parallel mechanism to enhance robot stiffness and cable construction to reduce moving inertia. A required condition for using cable construction is the ability to hold all cables under tension. This can only be achieved under certain conditions. The design phase of the study includes a static analysis on the robot manipulator that ensures certain mechanical components are always held under tension. This idea is extended to address dynamic situations where the manipulator velocity and acceleration are bounded. Two concept robot configurations, 2D-Deltabot, and 2D-Betabot are presented. Through a series of analyses from the robot inverse kinematic model, the dynamic properties of a robot can be computed in an effective manner. It was determined that the presented robots can achieve 4g acceleration and 4m/s maximum speed within their 700mm by 100mm workspace with a pair of 890W rotary actuators controlling two degrees of freedom. The 2D-Deltabot was chosen for prototype development. A kinematics calibration algorithm was developed to enhance the robot accuracy. Experimental test results had shown that the 2D-Deltabot was capable of running at 81 cycles per minute on a 730mm long pick-and-place path. Further experiments showed that the robot had a position accuracy of 0. 62mm and a position repeatability of 0. 15mm, despite a few manufacturing errors from the prototype fabrication.

Robotic automation has been the major driving force in modern industrial developments. High speed pick-and-place operations find their place in many manufacturing applications. The goal of this project is to develop a class of high speed robots that has a planar workspace. The presented robots are intended for pick-and-place applications that have a relatively large workspace. In order to achieve this goal, the robots must be both stiff and light. The design strategies adapted in this study were expanded from the research work by Prof Khajepour and Dr. Behzadipour. The fundamental principles are to utilize a parallel mechanism to enhance robot stiffness and cable construction to reduce moving inertia. A required condition for using cable construction is the ability to hold all cables under tension. This can only be achieved under certain conditions. The design phase of the study includes a static analysis on the robot manipulator that ensures certain mechanical components are always held under tension. This idea is extended to address dynamic situations where the manipulator velocity and acceleration are bounded. Two concept robot configurations, 2D-Deltabot, and 2D-Betabot are presented. Through a series of analyses from the robot inverse kinematic model, the dynamic properties of a robot can be computed in an effective manner. It was determined that the presented robots can achieve 4g acceleration and 4m/s maximum speed within their 700mm by 100mm workspace with a pair of 890W rotary actuators controlling two degrees of freedom. The 2D-Deltabot was chosen for prototype development. A kinematics calibration algorithm was developed to enhance the robot accuracy. Experimental test results had shown that the 2D-Deltabot was capable of running at 81 cycles per minute on a 730mm long pick-and-place path. Further experiments showed that the robot had a position accuracy of 0. 62mm and a position repeatability of 0. 15mm, despite a few manufacturing errors from the prototype fabrication.

This work analyzes human-in-the-loop robotic systems to determine where human input can be most beneficial to a collaborative task. This is accomplished by implementing a pick-and-place task using a human-in-the-loop robotic system and determining which segments of the task, when replaced by human guidance, provide the most improvement to overall task performance and require the least cognitive effort. The first experiment entails implementing a pick and place task on a commercial robotic arm. Initially, we look at a pick-and-place task that is segmented into two main areas: coarse approach towards a goal object and fine pick motion. For the fine picking phase, we look at the importance of user guidance in terms of position and orientation of the end effector. Results from this initial experiment show that the most successful strategy for our human-in-the-loop system is the one in which the human specifies a general region for grasping, and the robotic system completes the remaining elements of the task. We extend this study to include a second experiment, utilizing a more complex robotic system and pick-and-place task to further analyze human impact in a human-in-the-loop system in a more realistic setting. In this experiment, we use a robotic system that utilizes an Xbox Kinect as a vision sensor, a more cluttered environment, and a pick-and-place task that we segment in a way similar to the first experiment. Results from the second experiment indicate that allowing the user to make fine tuned adjustments to the position and orientation of the robotic hand can improve task success in high noise situations in which the autonomous robotic system might otherwise fail. The experimental setups and procedures used in this thesis can be generalized and used to guide similar analysis of human impact in other human-in-the-loop systems performing other tasks.

During the spring of 2014, Johan Kooiker and Kashira Roil Beto, students in mechanical engineering at Linnaeus University carried out a degree project together with Husqvarna construction products Sweden AB. The topic of this project was "product development" to develop an automated system for assembling cold pressed segments. The project began with studying the current situation to get a clearer picture of the problem and finding out the requirements. The main requirements were studied and implanted in behaviour descriptions of the system. Later on ideas and concepts were generated, which then through rating and screening led to the final concept. The final concept was divided into subsystems and developed in details. The detail work included 3D cad models of unique components and selection of standard component. The final step was to build simple prototypes of the subsystems to test their functions. The prototypes of the subsystems accomplished the main requirements of the company and that led to future investment in final system.

This thesis deals with the design and realization of SMD pick and place machine. Significant part of thesis was focused on computer vision and its application for SMD devices centering. Beside the mechanical construction the control software capable of use in production environment have been realized.

Printed circuit boards used in most ordinary electrical devices are usually equipped through an assembly line. Pick and place machines as part of those lines require accurate detection of incorrectly picked components, and this is commonly performed via image analysis. The goal of this project is to investigate if we can achieve state-of-the-art performance in an industrial quality assurance task through the application of artificial neural networks. Experiments regarding different network architectures and data modifications are conducted to achieve precise image classification. Although the classification rates do not surpass or equal the rates of the existing vision-based detection system, there remains great potential in the deployment of a machine-learning-based algorithm into pick and place machines. / Tryckta kretskort som används i de flesta vanliga elektroniska produkter är vanligtvis monterade i monteringslinjer. Ytmonteringsmaskinerna i dessa monteringslinjer kräver exakt detektering av felaktigt plockade komponenter, vilket ofta genomförs med hjälp av bildanalys. Målet med detta projekt är att undersöka om vi kan uppnå framstående resultat i en industriell kvalitetssäkringsuppgift genom användandet av artificiella neuronnätverk. Experiment utförs med olika nätverksarkitekturer och datamodifikationer för att uppnå exakt bildklassificering.  Även om klassificeringsgraderna inte uppnår klassificeringsgraderna hos existerande synbaserade detekteringssystem, finns en stor potential för användandet av maskininlärningsbaserade algoritmer i ytmonteringsmaskiner.