No description available.

This bachelor’s thesis has been carried through at the company Mabema AB in Linköping which offers complete vision based systems for multiple applications. With camera technology and advanced image processing, the company is working mainly in four different business areas; RobotVision, Vision, Nuclear and Wood. Mabema AB has been assigned to develop a vision system for robot guidance for the company Pipelife Sverige AB which is a big supplier of plastic pipes. The vision system is supposed to identify plastic pipes which are transported by a conveyor belt in random order. The pipes are then to be picked by two robots and placed in fixtures for further processing. Through studies of existing similar systems and analysis of suitable hardware, a system that satisfies the customer’s needs was made and alternative systems was presented. The result of the thesis ended with vision controlled system built of two robots and a 3D-scanner that accomplishes the assigned task with high robustness and an analysis of alternative systems was presented.

One of the remaining obstacles to the widespread application of industrial robots is their inability to deal with parts that are not precisely positioned. In the case of manual assembly, components are often presented in bins. Current automated systems, on the other hand, require separate feeders which present the parts with carefully controlled position and attitude. Here we show how results in machine vision provide techniques for automatically directing a mechanical manipulator to pick one object at a time out of a pile. The attitude of the object to be picked up is determined using a histogram of the orientations of visible surface patches. Surface orientation, in turn, is determined using photometric stereo applied to multiple images. These images are taken with the same camera but differing lighting. The resulting needle map, giving the orientations of surface patches, is used to create an orientation histogram which is a discrete approximation to the extended Gaussian image. This can be matched against a synthetic orientation histogram obtained from prototypical models of the objects to be manipulated. Such models may be obtained from computer aided design (CAD) databases. The method thus requires that the shape of the objects be described, but it is not restricted to particular types of objects.

This paper describes a hand-eye system we developed to perform the binpicking task. Two basic tools are employed: the photometric stereo method and the extended Gaussian image. The photometric stereo method generates the surface normal distribution of a scene. The extended Gaussian image allows us to determine the attitude of the object based on the normal distribution. Visual analysis of an image consists of two stages. The first stage segments the image into regions and determines the target region. The photometric stereo system provides the surface normal distribution of the scene. The system segments the scene into isolated regions using the surface normal distribution rather than the brightness distribution. The second stage determines object attitude and position by comparing the surface normal distribution with the extended-Gaussian-image. Fingers, with LED sensor, mounted on the PUMA arm can successfully pick an object from a pile based on the information from the vision part.

Robotic bin picking is the problem of emptying a bin of randomly distributedobjects through a robotic interface. This thesis examines an SVM approach to ex-tract grasping points for a vacuum-type gripper. The SVM is trained on syntheticdata and used to classify the points of a non-synthetic 3D-scanned point cloud aseither graspable or non-graspable. The classified points are then clustered intograspable regions from which the grasping points are extracted. The SVM models and the algorithm as a whole are trained and evaluated againstcubic and cylindrical objects. Separate SVM models are trained for each type ofobject in addition to one model being trained on a dataset containing both typesof objects. It is shown that the performance of the SVM in terms accuracy isdependent on the objects and their geometrical properties. Further, it is shownthat the algorithm is reasonably robust in terms of successfully picking objects,regardless of the scale of the objects.

This master´s thesis describes the concept of Bin-picking technology, image recognition and the posibility of grasping parts of various shapes. It deals with the interaction between industrial robot, end-effector and recognition cell system in the industrial cell in process of random collection of parts from the box. The practical part is concerned with construction of end effector for a given part of a specific shape in a random selection/collection of parts from industrial pallets. For this operation is used the KUKA KR16 industrial robot and for safety reasons senzor FTC/collision OPS. Further work is designed working cell which deals with the design and layout of the working elements including security.

Background Manufacturers have to adopt modern technologies to compete at the top of their field. However, adopting new technologies can be expensive and difficult to validate prior to implementation. One technology that has difficulties receiving a wider application is bin picking. Bin picking uses vision technology to communicate with an industrial robot. Consequently, the technology enables robots to pick randomly sorted objects. Research finds that the difficulty in assessing its performance can explain the lacklustre application of bin picking. In addition, research on bin picking is primarily focused on its technical difficulties and neglects information that can be valuable for potential adopters.  Objectives This thesis aims to aid decision-makers in assessing the implications and opportunities of bin picking. Furthermore, the thesis desire to inspire potential adopters by analysing the viability of bin picking through feasibility and the tangible and intangible benefits in a real-world setting. Methods A utility function is developed and assigned categories based on interviews with suppliers and adopters of the technology and literature review. The utility function highlights the feasibility and the intangible benefits of a bin picking solution and enables ranking among alternatives. The highest scoring article is used to conduct a feasibility study in collaboration with suppliers of bin picking technology. Based on the feasibility studies, a DES is created to highlight the implications that may arise in a real manufacturing environment. Finally, financial calculations through NPV, IRR, PP and DPP are created to evaluate the solution. Results All NPV calculations (excluding a 12.5 \% discount rate) are positive with enough years. The IRR is positive when the time span exceeds 11 years. The PP is 10-11 years while the DPP is 12-13, 14-15, 19-20, 32-33 years at a discount rate of 2.5 \%, 5 \%, 7.5 \% respectively 10 \%. However, the investment is never recoupable at a discount rate of 12.5 \%. The categories of the utility function have a clear impact on the feasibility and intangible benefits of the technology in a real-world setting. Bin picking relieves MMH tasks for operators, frees up facility space and reduces the collision risk. However, there are several risks with a bin picking solution. Conclusions Bin picking can become financially viable through automating MMH processes. However, how much capital is released depends on the man-hours spent in the previous process. The feasibility of bin picking implementation is dependent on the geometric complexity of the article, the sorting method inside the bin, the surrounding environment and the time margin. Decision-makers need to account for these factors prior to implementation. The intangible benefits can incentivise decision-makers to implement bin picking, even if the financial calculations show a net loss on the investment. / Bakgrund Tillverkare måste anta moderna tekniker för att kunna konkurrera vid toppen av sin bransch. Det kan dock vara både dyrt och svårt att validera ny teknologi före implementation. En teknologi som har haft det svårt att nå en bredare tillämpning är bin picking. Bin picking använder visionteknik för att kommunicera med industrirobotar. Teknologin gör det möjligt för robotar att plocka slumpmässigt sorterade objekt. Den låga tillämpningen av teknologin kan enligt forskare bero på svårigheterna med att bedöma dess prestanda. Forskning fokuserar dessutom främst på de tekniska problemen med bin picking och försummar information som är värdefull för potentiella användare. Syftet Syftet med denna studie är att tillhandahålla underlag för beslutsfattare att bedöma konsekvenserna och möjligheterna med bin picking. Vidare avser studien att inspirera potentiella användare genom att analysera lönsamheten av bin picking via dess genomförbarhet och dess materiella samt immateriella förmåner i en verklig miljö. Metod En nyttofunktion utvecklas och tilldelas kategorier baserat på intervjuer med leverantörer och antagare av teknologin samt från tidigare litteratur. Nyttofunktionen lyfter fram genomförbarheten samt de immateriella förmånerna i en bin  picking lösning, dessutom möjliggör den rangording mellan alternativ. Artikeln som rankas högst används för att genomföra en förstudie tillsammans med leverantörer av bin picking teknologi. En DES som baseras på förstudierna skapas för att lyfta fram de implikationer som kan uppstå i en verklig produktionsmiljö. Slutligen utvärderas lösningen genom finansiella medel, innefattande NPV, IRR, PP och DPP. Resultat Alla NPV-beräkningar (exklusive vid en diskonteringsränta på 12,5 \%) är positiva efter tillräckligt många år. IRR är positivt när tiden överstiger 11 år. PP är 10-11 år, medans DPP är 12-13, 14-15, 19-20, 32-33 år med en diskonteringsränta på 2,5 \%, 5 \%, 7,5 \% respektive 10 \%. Investeringen är dock aldrig återbetalningsbar vid en diskonteringsränta på 12,5 \%. Nyttofunktionens kategorier har en tydlig påverkan gällande teknologins genomförbarhet och immateriella fördelar i en verklig produktionsmiljö. Bin picking avlastar operatörer från MMH-uppgifter, frigör fabriksyta och minskar kollisionsrisken. Det finns dock flera risker med en bin picking lösning. Slutsats Bin picking kan vara ekonomiskt lönsamt genom att automatisera MMH processer. Hur mycket kapital som frigörs beror dock på det antal arbetstimmar som spenderas vid den manuella processen. Genomförbarheten vid implementeringen av bin picking är beroende av artikelns geometriska komplexitet, sorteringsmetod, omgivningen och tidsmarginal. Detta är faktorer som beslutsfattare måste ta hänsyn till före implementation. De immateriella fördelarna kan ge beslutsfattare incitament att införa bin picking, även om de finansiella beräkningar visar en förlust vid en investering.

This thesis focuses on robotic 3D vision for application in Bin Picking. The new method based on Conformal Geometric Algebra (CGA) is proposed and tested for identification of spheres in Pointclouds created with 3D scanner. The speed, precision and scalability of this method is compared to traditional descriptors based method. It is proved that CGA maintains the same precision as the traditional method in much shorter time. The CGA based approach seems promising for the use in the future of robotic 3D vision for identification and localization of spheres.

The master thesis deals with design of a robotic workcell for the operating of CNC lathe. The material input is realized by bin picking technology. The first part is an overview of related industries. Three variants of the workcell layout were created in the second part and the most suitable variant was selected. Selected variant is further elaborated, including 3D models of the workplace parts and drawings. The functionality of the designed workcell is checked by Siemens Process Simulate software simulation. The technical and economical evaluation is performed at the final part of the thesis.

<p>This thesis presents methods useful in a bin picking application, such as detection and representation of local features, pose estimation and multi-cue integration.</p><p>The scene tensor is a representation of multiple line or edge segments and was first introduced by Nordberg in [30]. A method for estimating scene tensors from gray-scale images is presented. The method is based on orientation tensors, where the scene tensor can be estimated by correlations of the elements in the orientation tensor with a number of 1<em>D</em> filters. Mechanisms for analyzing the scene tensor are described and an algorithm for detecting interest points and estimating feature parameters is presented. It is shown that the algorithm works on a wide spectrum of images with good result.</p><p>Representations that are invariant with respect to a set of transformations are useful in many applications, such as pose estimation, tracking and wide baseline stereo. The scene tensor itself is not invariant and three different methods for implementing an invariant representation based on the scene tensor is presented. One is based on a non-linear transformation of the scene tensor and is invariant to perspective transformations. Two versions of a tensor doublet is presented, which is based on a geometry of two interest points and is invariant to translation, rotation and scaling. The tensor doublet is used in a framework for view centered pose estimation of 3<em>D</em> objects. It is shown that the pose estimation algorithm has good performance even though the object is occluded and has a different scale compared to the training situation.</p><p>An industrial implementation of a bin picking application have to cope with several different types of objects. All pose estimation algorithms use some kind of model and there is yet no model that can cope with all kinds of situations and objects. This thesis presents a method for integrating cues from several pose estimation algorithms for increasing the system stability. It is also shown that the same framework can also be used for increasing the accuracy of the system by using cues from several views of the object. An extensive test with several different objects, lighting conditions and backgrounds shows that multi-cue integration makes the system more robust and increases the accuracy.</p><p>Finally, a system for bin picking is presented, built from the previous parts of this thesis. An eye in hand setup is used with a standard industrial robot arm. It is shown that the system works for real bin-picking situations with a positioning error below 1 mm and an orientation error below 1^o degree for most of the different situations.</p> / Report code: LiU-TEK-LIC-2005:15.