No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Automation of product packaging for industrial applications
Abstract
This work presents a robotic-based solution devised to automate the product packaging in industrial environments. Although the proposed approach is illustrated for the case of the shoe industry, it applies to many other products requiring similar packaging processes. The main advantage obtained with the automated task is that productivity could be significantly increased. The key algorithms for the developed robot system are: object detection using a computer vision system; object grasping; trajectory planning with collision avoidance; and operator interaction using a force/torque sensor. All these algorithms have been experimentally tested in the laboratory to show the effectiveness and applicability of the proposed approach.
... Many studies have been conducted and have reported on robot-based automation of the shoe manufacturing process [3][4][5][6][7][8][9][10][11][12][13][14]. Ding et al. proposed a methodology for measuring foot girths using a local radial basis function [3]. ...
... Pedrocchi et al. represented the upper roughing process in a different way by designing a fuzzy logic controller [7]. In contrast, Gracia et al. introduced shoe packaging process automation based on a robot that was implemented with the viewpoint of human-robot cooperation [8,9]. Automation for gluing and spraying processes was also proposed in [10,11]. ...
(1) Background: Conventional shoe manufacturing involves many processes that most workers avoid because of loud noises and harmful environments. Therefore, a robot-based shoe manufacturing system is needed to implement an automated process. (2) Aim: We propose a new robot-based shoe manufacturing automation system that includes an automatic robotic solution for replacing the manual manufacturing processes of the upper and sole. (3) Methods: For the upper manufacturing process, a new trajectory acquisition system with a digitizer and a shoe last turning device is proposed. A method to plan the robot’s tool path for roughing and cementing by industrial robot manipulators is also presented. For the sole manufacturing process, we adopted an industrial robot manipulator with a 3-D scanning system and a cementing tool. A trajectory generation algorithm for cementing the outer and inner sides of the sole by transforming 3-D information of the sole into a 6-D posture for the robot is proposed. (4) Results: All developed systems and proposed algorithms are applied to an automated production testbed, and their performances are experimentally verified. (5) Conclusions: The proposed system and methods can be applied for upper and sole manufacturing processes according to evaluation experiments in a demonstrative production line.
... Automation in its broadest sense aims to systematically structure all aspects to do with the process execution, whereas the use of robotic technologies only serves to be a physical means of performing physical tasks. For example, Perez-Vidal et al [2], Abujelala et al [3], and Nayak and Padhye [4] proposed the use of robotic based operations, using physical interactions between machines and products in order to improve certain aspects towards full automation. Based on their work, automation can be defined as to encompass robots, information management, data modelling, simulation, and scenario developments to meet the overall industry requirements which is to be analysed in this research paper. ...
This paper presents a real-life example of using industrial robots to automate the testing procedures of aerospace products. Three different scenarios are proposed as potential solutions to allow a Mobile Manipulator to help automate the environmental testing process. An overview of different simulation and Off Line Programming (OLP) software packages are presented and discussed as methods to test and validate the scenarios. A framework is presented consisting of a product data model to be used for the identification of the different products and a unified modelling system is introduced to allow information exchange at the operational level. The focus of this paper and future work is towards integrating all the elements of the proposed framework into a human machine interface to create a collaborative process involving human, robots, machines and products.
... Then, they used different strategies based on distance between robot and operator. Pérez-Vidal et al. (2018) introduced an algorithm that used trajectory planning with collision avoidance in order to automate the product packaging in industrial environments. Xu et al. (2003) presented a concept for dynamic obstacle avoidance. ...
Obstacle avoidance is one of the basic, but computationally, costly issues of robotic science. In this paper, a safety ring around the work piece was defined, so that since the wrist of the robot is inside the ring, it is guaranteed that no collision will occur. Considering the wrist of the robot, instead of a tooltip, reduces the computational cost due to removal of the three last robot joints from calculations. The robot wrist is able to move freely inside the safety ring volume instead of a specific curve. The rotation of the end effector around its axis in some applications like welding, cutting, etc. is not important; therefore, this functional redundancy was used in inverse kinematic solution in order to search in the null space to find the optimal joint angles for moving the robot wrist inside the safety ring. In addition, inherent redundancy of the robot base movement on the rail was used to avoid joint limits. The algorithm was applied to a common industrial application i.e. intersecting pipes welding.
... When talking about lean rules at higher levels, their application should not differ from the standard application adopted in companies involved in manual or automatic production. However, collaborative robot implementation can increase the productivity of manual work stations (Perez-Vidal et al. 2018) and should be adopted for the bottleneck process, whenever possible. ...
Industry 4.0 stresses the importance of considering production automation as an integrated and collaborative teamwork process between human workers and intelligent machines and tools. Collaborative robotics is a recent field of study for industrial automation. Although fenceless robot systems are available, the actual implementation of collaborative schemes for the conduction of assembly jobs should be supported through dedicated procedures and guidelines. These procedures have yet to be found and defined in detail. In this work, the authors claim that it may be possible to approach the problem of collaborative cell design with the methods devised for lean thinking. In the paper, the most common lean strategies are listed and analysed from the viewpoint of setting up a collaborative work cell. The most suitable strategies and tools are then recommended in a methodology that has been proposed to redesign an industrial assembly cell. The methodology has then been adopted in the presented industrial use case which is focused on the steps of HRC design process such as tasks assignment and scheduling.
... A number of footwear tasks have been studied and automated thanks to the third revolution. Examples of work done in footwear automated tasks include the application of adhesive to shoe soles (Wu, 2008), roughing or grinding of the bottom surface of the shoe so that the gluing process works correctly (Pedrocchi, Villagrossi, Cenati, & Tosatti, 2015;Jatta, Zanoni, Fassi, & Negri, 2004), last milling to create shoe lasts based on custom measurements (Xiong, Zhao, Jiang, & Dong, 2010), last marking to add information to them (Conte, Facchino, Marziali, & Mazzocchetti, 2013), lasting operation to secure the leather upper to the sole (Nemec, Lenart, & Zlajpah, 2003), polishing of the finished product (Zlajpah & Nemec, 2008) and shoe-packaging (Gracia et al., 2017;Perez-Vidal et al., 2018) at the end of the production line. Those processes require a high degree of flexibility to face continuous changes in product demand and variety, and to manage complex and variant production processes (Brusaferri, Ballarino, & Carpanzano, 2011). ...
In the footwear sector, automation is often performed by robotic arms due to the inherent adaptive requirements of some of its tasks. With the Industry 4.0 revolution, automation is even less human dependent than before. The fact that fewer people interact with machinery during the manufacturing process has led to a rising need for production monitoring. The interconnection of machines present in 4.0 environments makes monitoring possible at a low investment cost. In this paper, a common communication layer is proposed to enable homogeneous status data retrieval of robotic arms from several different robot manufacturers. This layer is then attached to a 3D simulator software as a client, responsible for the monitoring process. Experiments proved the feasibility of the proposed method in a test bench scenario applying the required constraints of time, cost, bandwidth and disk space.
In recent years, robotics emerged as a leading contender in many applications. Most of the applications employed multiple mobile robot to accomplish parallel tasks efficiently. In most of the multi-robot applications, though robots work in the same environment, but may not have the same objective. In multi-robot navigation, robots may encounter a deadlock situation, where robots faced each other and trying to find the safe path to escape and reach their target. In such situation, it can be advantageous for robots to cooperate and trust each other to finish their assignments quickly. This paper aims to develop a trust based navigation control algorithm that evaluates the trustworthiness of robots based on their service and utilize it to decide the next waypoint of robots to avoid the deadlock. The effectiveness of the proposed method is validated through simulation. The simulation outcome reveals that the proposed method is efficient for navigation planning of multi-robot to avoid the deadlock situation.
The last is the basic industrial component in footwear manufacturing, from which product development starts. Correct last grading ensures the best fit for the intended group of users of the footwear model to be produced. The size marked on the last should respect the specific intervals defined in the different international sizing systems, like the European, UK, US or Mondopoint systems, which are all described in international standards. New approaches in the field of CAD/CAM have emerged over recent years towards the automation of this process. However, these are partial approaches that neither address the grading process according to the different standards nor consider the various parts of the shoe that are not affected by size increments. This paper presents a new accurate and efficient technique for the automation of the shoe last grading process based on the conjugate gradient method. Through this method, it is possible to obtain a graded shoe last that conforms to the international standards in force relative to shoe sizing and allows for the shoe parts that are not affected by size increments. This technique is based on the target measures of length and perimeter of the last to be graded, and aims to minimise the quadratic difference between these values and those obtained from the graded last. This method has been evaluated through a battery of tests performed on a geometrically heterogeneous group of shoe lasts. The results obtained were accurate and the execution time was fast enough to be used for mass production.
The fashion footwear industry is strongly characterized by hand-crafted fabrication. Companies operating in this field are usually reluctant to employ industrial robots in their facilities, where the integration of automated solutions is often an element of disruption. It is also still difficult to perform many of the operations involved with industrial robots. The roughing of the uppers of fashion shoes is a typical example: the great inaccuracy in shoe dimensions and shape makes definition of an automated path a critical aspect, and this is reflected in the complexity of robot programming. In addition, standard industrial position-based control solutions are unsuitable in force-tracking application as roughing by the variable stiffness of the environment and by arm flexibilities. In this scenario, the paper describes an innovative robotic cell for roughing operations with a layout conceived for installation in artisan-based production. The robot controller is an admittance control loop with a fuzzy regulator designed to be integrated with standard robot controller by exploiting the so-called sensor-tracking option. The design of the robot controller is grounded on an in-depth analysis of the manual strategies used by workers skilled in roughing operations. The results of a series of experiments on different kinds of shoes demonstrate the feasibility of this approach.
This paper addresses the machine layout problem in a flexible manufacturing cell served by a robot. The objective of the proposed approach is to obtain the optimum values of the locations and orientations of machines and the corresponding feasible configurations of the robot at each input/output location. Two optimization criteria have been considered, the travel time and the total joint displacement for all possible sequences of operations required by the robot at a given period of time. Non-linear optimization models are proposed which can be applied not only to a planar robot but also to an industrial one. The optimization problems were solved by a sequential quadratic programming algorithm.
The open motion planning library (OMPL) is a new library for sampling-based motion planning, which contains implementations of many state-of-the-art planning algorithms. The library is designed in a way that it allows the user to easily solve a variety of complex motion planning problems with minimal input. OMPL facilitates the addition of new motion planning algorithms, and it can be conveniently interfaced with other software components. A simple graphical user interface (GUI) built on top of the library, a number of tutorials, demos, and programming assignments are designed to teach students about sampling-based motion planning. The library is also available for use through Robot Operating System (ROS).
The paper presents a knowledge-based system (KBS) for the conceptual design of grippers for handling fabrics. Its main purpose is the integration of the domain knowledge in a single system for the systematic design of this type of grippers. The knowledge presented, in terms of gripper, material and handling process, are classified. The reasoning strategy is based upon a combination of a depth-first search method and a heuristic method. The heuristic search method finds a final solution from a given set of feasible solutions and can synthesize new solutions to accomplish the required specifications. Details of the main features of the system are given, including its ability to take critical design decisions according to four criteria, weighted by the designer. The knowledge-based system was implemented in the Kappa P. C. 2.3.2 environment. Two examples are given to illustrate some critical aspects concerning the KBS development, to explain the operation of the proposed searching heuristic method, and to show its effectiveness in producing design concepts for grippers.
Using visual feedback to control the movement of the end-effector is a common approach for robust execution of robot movements in real-world scenarios. Over the years several visual servoing algorithms have been developed and implemented for various types of robot hardware. In this paper, we present a hybrid approach which combines visual estimations with kinematically determined orientations to control the movement of a humanoid arm. The approach has been evaluated with the humanoid robot ARMAR III using the stereo system of the active head for perception as well as the torso and arms equipped with five finger hands for actuation. We show how a robust visual perception is used to control complex robots without any hand-eye calibration. Furthermore, the robustness of the system is improved by estimating the hand position in case of failed visual hand tracking due to lightning artifacts or occlusions. The proposed control scheme is based on the fusion of the sensor channels for visual perception, force measurement and motor encoder data. The combination of these different data sources results in a reactive, visually guided control that allows the robot ARMAR-III to execute grasping tasks in a real-world scenario.
In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded
Up Robust Features). It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness,
and robustness, yet can be computed and compared much faster.
This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing
detectors and descriptors (in casu, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods
to the essential. This leads to a combination of novel detection, description, and matching steps. The paper presents experimental
results on a standard evaluation set, as well as on imagery obtained in the context of a real-life object recognition application.
Both show SURF’s strong performance.
Humans can use the Internet to share knowledge and to help each other accomplish complex tasks. Until now, robots have not taken advantage of this opportunity. Sharing knowledge between robots requires methods to effectively encode, exchange, and reuse data. In this article, we present the design and first implementation of a system for sharing knowledge between robots.
Classic registration methods for model-based tracking try to align the projected edges of a 3D model with the edges of the image. However, wrong matches at low level can make these methods fail. This paper presents a new approach allowing to retrieve multiple hypothesis on the camera pose from multiple low-level hypothesis. These hypothesis are integrated into a particle filtering framework to guide the particle set toward the peaks of the distribution. Experiments on simulated and real video sequences show the improvement in robustness of the resulting tracker.
Finishing operations in the shoe manufacturing process comprises operations such as application of polishing wax, polishing cream and spray solvents, and brushing in order to achieve high gloss. These operations require skilled workers and are generally difficult to automate owing to the complex motion trajectories. This paper describes a robotic cell for finishing operations in a custom shoe production plant. Such customization of shoe production should allow production of small batches of shoes of the same type. This requires automatic set-up and adaptation of the production line. To meet these requirements, a computer aided design (CAD) system for automatic generation, optimization and validation of motion trajectories was integrated into a robotic cell. In automatic trajectory generation some of the major problems are limitations posed by the robot joint limits, robot singularities and environment obstacles. These problems were solved using the kinematic redundancy of the robot manipulator.
Today, the footwear industry is facing many challenges. First, consumers demand for new products with better comfort and design; second, competition is becoming stronger in current global market. Due to these factors, flexibility and rapidity in developing new products are key factors for the medium and long-term survival and success of the footwear industry. This paper proposes a new software application based in simple image processing techniques for optimization of two important steps of the processes involved in footwear manufacturing: the shoe sole halogenation and lead roughing process. The application presented in this paper has a friendly interface where the sole contour points for shoe sole halogenation and lead roughing are automatically determined. The operator can easily change and set new points to improve details within the interest region where tools will be applied, when the halogenation or the roughing process is executed. Another feature of this application is the automatic transformation of the 2D coordinates of the dominant points to 3D real world coordinates. This feature simplifies further ongoing work - automatic code generation for different industrial robots to execute the halogenation and roughing processes.
Establishing safe human–robot collaboration is an essential factor for improving efficiency and flexibility in today’s manufacturing environment. Targeting safety in human–robot collaboration, this paper reports a novel approach for effective online collision avoidance in an augmented environment, where virtual three-dimensional (3D) models of robots and real images of human operators from depth cameras are used for monitoring and collision detection. A prototype system is developed and linked to industrial robot controllers for adaptive robot control, without the need of programming by the operators. The result of collision detection reveals four safety strategies: the system can alert an operator, stop a robot, move away the robot, or modify the robot’s trajectory away from an approaching operator. These strategies can be activated based on the operator’s existence and location with respect to the robot. The case study of the research further discusses the possibility of implementing the developed method in realistic applications, for example, collaboration between robots and humans in an assembly line.
This is a study of a Human-Robot Collaboration (HRC) framework for the execution of collaborative tasks in hybrid assembly cells. Robots and humans coexist in the same cell and share tasks according to their capabilities. An intelligent decision-making method that allows human-robot task allocation is proposed and is integrated within a Robot Operating System (ROS) framework. The proposed method enables the allocation of sequential tasks assigned to a robot and a human in separate workspaces. The focus is rather given to the human–robot coexistence for the execution of sequential tasks, in order for the automation level in manual or even hybrid assembly lines to be increased. Body gestures are the means of a human’s interaction with a robot for commanding and guiding reasons. The proposed framework is implemented into a case coming from the manual assembly lines of an automotive industry. A preliminary design of a hybrid assembly cell is presented, focusing on the assembly of a hydraulic pump by robots and humans.
The wide interest of research and industry in the human–robot interaction (HRI) related topics is proportional to the increased productivity and flexibility of the production lines, as it combines human and robot capabilities. This paper presents a review of recent research and progress on HRI, related to task planning/coordination and programming with emphasis on the manufacturing/production environment. Human–robot task allocation and scheduling, metrics for HRI, as well as the social aspects are reviewed. The role of digital human modelling systems for human–robot task planning related issues is also discussed. The process of learning by demonstration as well as the instructive systems is reviewed, focussing mainly on programming through visual guidance and imitation, voice commands and haptic interaction. The aspect of physical HRI as well as the safety related issues are also discussed. Additionally, a survey on multimodal communication frameworks is presented. Challenges encountered and directions for future research are discussed.
Mass-customization of wearable products are offered as a higher added value to the broad public and have to compete with ready-to-wear offer. However, people with specific requirements are not covered by the current mass-customised products. This is the case of the elderly, disabled, diabetic and obese population groups when wearing textiles, clothing, footwear and textile-based orthotic goods. Further, at present, available knowledge and flexibility of production equipment and machinery of small and medium-sized enterprises operating in these traditional industries (even those that already offer made-to-measure products to the mass public) is unable to respond to the individual needs among such heterogeneous groups. The FASHION-ABLE project has solved this problem with a comprehensive set of solutions.
The performance of virtual machine tools and virtual robot arms relies on the use of efficient and precise collision detection methods. This study proposes an octree-based collision detection method, called the ‘shared triangles extended octrees’, applied on virtual machine tools and virtual robot arms. The proposed scheme combines the high computational efficiency of the octree test and the high numerical accuracy of an analytical surface boundaries intersection test. In the proposed algorithm, the overlapping voxels between neighbouring geometries in the virtual mechanisms are identified using octrees, and the intersections of the triangles within these voxels are then checked. It works efficiently, with rapid generation of deformed geometry by shared triangles without using decomposition.
The proposed collision detection scheme is implemented on virtual machine tools and the virtual robot arms in a virtual manufacturing cell. The virtual machine tools and virtual robot arms are composed of component trees, which describe the kinematic relation between components. The necessity to check for collisions between each component is indicated by a Boolean matrix. The pairs of components selected by the Boolean matrix are checked using the proposed shared triangles extended octree method.
The proposed collision detection method is an efficient tool for verifying the manipulation of CNC machine tools and robot arms and is of great help to CAD/CAM engineers and manufacturing engineers and operators of machine tools and robot arms.
Three-dimensional models provide a volumetric representation of space which is important for a variety of robotic applications including flying robots and robots that are equipped with manipulators. In this paper, we present an open-source framework to generate volumetric 3D environment models. Our mapping approach is based on octrees and uses probabilistic occupancy estimation. It explicitly represents not only occupied space, but also free and unknown areas. Furthermore, we propose an octree map compression method that keeps the 3D models compact. Our framework is available as an open-source C++ library and has already been successfully applied in several robotics projects. We present a series of experimental results carried out with real robots and on publicly available real-world datasets. The results demonstrate that our approach is able to update the representation efficiently and models the data consistently while keeping the memory requirement at a minimum.
The use of redundant manipulators in assembly stations, where a number of pick-and-place tasks needs to be performed, is examined in this paper. The aim is to obtain optimum values for the location of the robot in the workstation, the sequence of tasks and the configuration of the robot at each task location, such that the total travel time is minimized. The location of the robot and the optimal configurations, for a given sequence of tasks, is obtained by formulating and solving a constrained nonlinear optimization problem using the sequential quadratic programming method. A near-optimum sequence of travel is then obtained using simulated annealing. The proposed techniques are illustrated using three numerical examples.
This paper describes the design of a new hand for the robot iCub. Developed as part of the European project RobotCub the iCub is a robot baby based on an 18 month to 2.5 year old child. The current iCub hands are under-actuated which means they are not as dexterous as a true childpsilas hand. The hand designed in this work has a total of 22 degrees of freedom of which 18 are independently drivable. In order to minimise weight and cost the hand has been produced from acrylonitrile butadiene styrene (ABS) using 3D printing techniques. This removes the need for extensive machining which would add significantly to the overall cost of the hand. A prototype finger has been produced and tested and a full mechanical design is presented.
AbstractThe position of a robot within a flexible manufacturing workcell, where machine station and storage locations are predetermined, plays an important role in determining the cell's cycle time [1].In this paper. the optimum position of the robot (defined as the position of the robot in the workcell that results in the minimum cycle time) in a multi-location industrial workcell is determined through the use of a numerical optimization routine and ROBCAD. a kinematic computer graphics simulation program.
The classical travelling salesperson problem (TSP) models the movements of a salesperson travelling through a number of cities. The optimization problem is to choose the sequence in which to visit the cities in order to minimize the total distance travelled. This paper presents a generalized point-to-point motion-planning technique for multi-robot assemblysystems modelled as TSP-type optimization problems. However, in these augmented TSPs (TSP+), both the 'salesperson' (a robot with a tool) as well as the 'cities' (another robot with a workpiece) move. In addition to the sequencing of tasks, further planning is required to choose where the 'salesperson' (i.e., the tool) should rendezvous with each 'city' (i.e. the workpiece). The use of a genetic algorithm (GA) is chosen as the search engine for the solution of this TSP+ optimization problem. As an example area, the optimization of the electronic-component placement process is addressed. The simulation tools developed have been tested on five different component-placement system configurations. In the most generalized configuration, the placement robot meets the component delivery system at an optimal rendezvous location for the pick-up of the component and subsequently meets the printed-cirucit-board (on a mobile XY-table) at an optimal rendezvous location. In addition to the solution of the component-placement sequencing problem and the rendezvous-point planning problem, the collision-avoidance issue is addressed.
In the shoe manufacturing process, in order to attach the upper with the corresponding sole, it is necessary to ‘scrape’ a thin layer of material off the upper surface so that glue can penetrate the leather and adhere; an operation called ‘roughing’. This paper describes the design and the implementation of an innovative robotic cell for roughing and cementing of shoe uppers, which operates at the moment in a pilot plant for custom-made shoe production. The small size of the production lots, as required by customization, and the accuracy needed to follow the complex 3D roughing paths, require a considerable degree of flexibility to minimized setup time. In order to meet these severe requirements, the robotic cell, described in this paper, integrates CAD-CAM generated tool paths with the use of a force controlled head, mounted at the manipulator wrist, which allows real-time adaptation of the trajectory in order to ensure continuous and stable contact between the tool and the shoe to be processed, regardless, to a certain extent, of the inaccuracies in the path specification. The paper describes the development details involved in the design of the cell, with a special emphasis on the active head and the overall control architecture.
This paper describes the facilities that are available at the ITIA Design and Mass Customization Laboratory of Vigevano. The history of the Laboratory and how ITIA has come, through different research projects, to the implementation of the integrated production plant (IPP) is presented. Then the main features, in terms of structures, system architectures and implemented technologies, of the IPP will be described, showing how such innovative research infrastructure will be used in the final phases of the EUROShoE project, in particular for what concerns the research related to the mass customization paradigm and its application in different industrial sectors. These phases will be described in details indicating the roles of the different elements of the system and their respective interactions, in terms of the vertical (between sale, design and manufacturing) and horizontal (between different machines and systems within the same phase of the product life cycle) integration. Aspects related to the experimental validation of such technologies in a quasi–productive environment are also presented, showing how the experimental campaigns are planned and organized. Future uses and applications of the IPP as a public research infrastructure at the European level are presented in the conclusions.
2016-Robots and Robotic Devices-Collaborative robots
- Iso Ts
Object Detection Methods for Robot Grasping: Experimental Assessment and Tuning
- F Rigual
- A Ramisa
- G Aleny
- C Torras
Customization in the Footwear Industry
- E Montiel
Project Funded by 6th FP
- Environment Custom
- Comfort Made Shoe
Distributed Databases, Information Exchange, Knowledge Transfer, Robot Kinematics, Robot Sensing Systems, Semantics, Service Robots
- M Waibel
- M Beetz
- J Civera
- R Andrea
- J Elfring
- D Galvez-Lopez
- K Haussermann
- R Janssen
- J M M Montiel
- A Perzylo
- B Schiessle
- M Tenorth
- O Zweigle
- R Van De Molengraft
Environment and Comfort Made Shoe
- Custom
URDF) documentation Website
- Ros Robot Model