Germano Veiga

Programming‐by‐demonstration in the coworker scenario for SMEs

– The purpose of this paper is to report a collection of developments that enable users to program industrial robots using speech, several device interfaces, force control and code generation techniques., – The reported system is explained in detail and a few practical examples are given that demonstrate its usefulness for small to medium‐sized enterprises (SMEs), where robots and humans need to cooperate to achieve a common goal (coworker scenario). The paper also explores the user interface software adapted for use by non‐experts., – The programming‐by‐demonstration (PbD) system presented proved to be very efficient with the task of programming entirely new features to an industrial robotic system. The system uses a speech interface for user command, and a force‐controlled guiding system for teaching the robot the details about the task being programmed. With only a small set of implemented robot instructions it was fairly easy to teach the robot system a new task, generate the robot code and execute it immediately., – Although a particular robot controller was used, the system is in many aspects general, since the options adopted are mainly based on standards. It can obviously be implemented with other robot controllers without significant changes. In fact, most of the features were ported to run with Motoman robots with success., – It is important to stress that the robot program built in this section was obtained without writing a single line of code, but instead just by moving the robot to the desired positions and adding the required robot instructions using speech. Even the upload task of the obtained module to the robot controller is commanded by speech, along with its execution/termination. Consequently, teaching the robotic system a new feature is accessible for any type of user with only minor training., – This type of PbD systems will constitute a major advantage for SMEs, since most of those companies do not have the necessary engineering resources to make changes or add new functionalities to their robotic manufacturing systems. Even at the system integrator level these systems are very useful for avoiding the need for specific knowledge about all the controllers with which they work: complexity is hidden beyond the speech interfaces and portable interface devices, with specific and user‐friendly APIs making the connection between the programmer and the system.

A Vertical and Cyber–Physical Integration of Cognitive Robots in Manufacturing

Cognitive robots, able to adapt their actions based on sensory information and the management of uncertainty, have begun to find their way into manufacturing settings. However, the full potential of these robots has not been fully exploited, largely due to the lack of vertical integration with existing IT infrastructures, such as the manufacturing execution system (MES), as part of a large-scale cyber-physical entity. This paper reports on considerations and findings from the research project STAMINA that is developing such a cognitive cyber-physical system and applying it to a concrete and well-known use case from the automotive industry. Our approach allows manufacturing tasks to be performed without human intervention, even if the available description of the environment-the world model-suffers from large uncertainties. Thus, the robot becomes an integral part of the MES, resulting in a highly flexible overall system.

ON THE USE OF SERVICE ORIENTED SOFTWARE PLATFORMS FOR INDUSTRIAL ROBOTIC CELLS

Abstract The integration of different robot automation technologies, with the aim for reusing available production solutions, is a major obstacle for deployment of low-cost components into productive (high-performance) systems. Technologies demanding high processing power, like machine vision or voice recognition systems, are normally easy to program but require proprietary languages and platforms, which constitutes an important problem during communications and setup. Instead of the current need for trained specialist, in particular flexible manufacturing in SMEs call for solutions that are easy easy to use and (re)configure. One attempt in that direction is the service-oriented architecture (SOA) approach, which here is accomplished by the use of Universal Plug-and-Play (UPnP) technologies and confronted with real robot application demand represented by an experimental manufacturing cell. Contributions include the way of building software applications to program manufacturing cells whose building blocks are represented by UPnP devices. Such devices encapsulate both manufacturing equipment and interaction methods. The latter is exemplified by a speech recognition system, for which a tool for automatic generation of UPnP devices based on the information contained in speech recognition XML grammars is presented. Experiences form experiments confirms the desired efficiency and simplicity when setting up advanced manufacturing equipment.

The SPIDERobot: A Cable-Robot System for On-site Construction in Architecture

The use of robots in architectural construction has been a research field since the 1980s. Driven by both productive and creative concerns, different systems have been devised based on large-scale robotic structures, mobile robotic units or flying robotic vehicles. By analyzing these approaches and discussing their advantages and limitations, this paper presents an alternative strategy to automate the building construction processes in on-site scenarios. The SPIDERobot is a cable-robot system developed to perform assembly operations, which is driven by a specific Feedback Dynamic Control System (FDCS) based on a vision system. By describing and illustrating this research work, the authors argue about the advantages of this cable robot system to deal with the complexity and the scale of building construction in architecture.

Evaluation of Depth Sensors for Robotic Applications

The sensors that acquire 3D data play an important role in many applications. In addition, they have been used in the robotic field for several purposes, for instance, enhancing the navigation of mobile robots, object detection, scene reconstruction, 3D inspection of parts and others. Moreover, a significant amount of devices with distinct cost, accuracy and features have been released in the recent years which increases the difficulty of comparing each sensor in a proper manner or choosing the most suitable device for a specific task and operation field. This paper compares the Kinect v1, Kinect v2, Structure Sensor and Mesa Imaging SR4000. The noise of each sensor is characterized for different distances and considering objects with different colors. Therefore, this paper proposes a simple but quantitative benchmark for evaluating 3D devices that characterizes the most relevant features for the robotic field and in accordance with different type of operations.

The ECHORD Project: A General Perspective

The European funded ECHORD project European Clearing House for Open Robotics Development began in January 2009 with the ambitious goal of bringing together European robotics manufacturers with the excellent European research institutions. Europe has a very strong robot industry and there is significant research potential as well as technological knowledge. There has been a long history of outstanding research and development in both robot manufacturers and research institutes. However, finding common ground between manufacturers and the research community, especially when it comes to defining the future direction of robotics research, has proven difficult in the past. This is one of the recurring themes on both sides, and a new level of cooperation is long overdue. Thus, ECHORD acted as a clearing house to streamline successful know-how transfers.

Separation of concerns on the orchestration of operations in flexible manufacturing

Purpose – The growing complexity of industrial robot work‐cells calls for the use of advanced orchestration techniques to promote flexibility and reusability. This paper aims to present a solution based on service‐oriented platforms that endorses the separation of concerns, coordination and execution.Design/methodology/approach – This paper starts with the evaluation of available tools for the orchestration and service generation. Endorsing the missing features depicted in that evaluation, the paper describes developments of concepts and software and the evaluation made.Findings – From the early evaluations made in this paper, the SCXML‐based purposed language is more adapted to the industrial robotic cell scenario than existing alternatives. The generation of services allow the integration without knowledge from any programming language.Practical implications – This approachs main drawback, as described by some users, was the lack of some programming features: simple math operations and conditional stat...

Robust 3/6 DoF self-localization system with selective map update for mobile robot platforms

Mobile robot platforms capable of operating safely and accurately in dynamic environments can have a multitude of applications, ranging from simple delivery tasks to advanced assembly operations. These abilities rely heavily on a robust navigation stack, which requires stable and accurate pose estimations within the environment. To solve this problem, a modular localization system suitable for a wide range of mobile robot platforms was developed. By using LIDAR/RGB-D data, the proposed system is capable of achieving 1-2 cm in translation error and 1?-3??degrees in rotation error while requiring only 5-35?ms of processing time (in 3 and 6 DoF respectively). The system was tested in three robot platforms and in several environments with different sensor configurations. It demonstrated high accuracy while performing pose tracking with point cloud registration algorithms and high reliability when estimating the initial pose using feature matching techniques. The system can also build a map of the environment with surface reconstruction and incrementally update it with either the full field of view of the sensor data or only the unknown sections, which allows to reduce the mapping processing time and also gives the possibility to update a CAD model of the environment without degrading the detail of known static areas due to sensor noise. 3/6 DoF localization system capable to operate in cluttered/dynamic and challenging environments.Efficient C++ ROS implementation with multi-level point cloud registration and recovery.Robust initial pose estimation using geometric feature matching.2D/3D mapping with integration of full sensor data or only unknown areas.Fully configurable and modular processing pipeline, extensible to other tasks besides self-localization.

Towards an orientation enhanced astar algorithm for robotic navigation

This paper presents an algorithm capable of generating smooth, feasible paths for an any-shape non-holonomic mobile robot, taking into account orientation restrictions, with the aim of navigating close to obstacles. Our contribution consists in an extension of the A* algorithm in a cell decomposition, where besides its position, the orientation of the platform is also considered when searching for a path. This is achieved by constructing 16 layers of orientations and only visiting neighbor layers when searching for the lowest cost. To simplify collision checking, the robots footprint is used to inflate obstacles, yet, to allow the robot to find paths close to obstacles, the actual footprint of the robot must used. By discretizing the orientation space into layers and computing an oriented footprint for each layer, the actual footprint of the robot is used, increasing the configuration space without becoming computationally expensive. The path planning algorithm was developed under the EU-funded project CARLoS1 and was implemented in a stud welding robot simulated within a naval industry environment, validating our approach.

The ECHORD project proposals analysis - Research profiles, collaboration patterns and research topic trends

This paper investigates the research profiles, collaboration patterns and research topic trends which can be identified in the proposals submitted to the ECHORD (European Clearing House for Open Robotics Development) FP7 project. On a country level, clusters were identified and characterized by patterns of proposal production per inhabitant, score and international cooperation. Belgium and Sweden constitute a cluster characterized by high proposal production, with very high scores and extensive international collaboration. Belgium also excels from another cluster analysis, being as the only country where 100% of proposals involve industry-academia cooperation and obtain scores above 10. Other findings show that single partner proposals have significantly lower quality than multi-partner proposals but, on the other hand, the number of countries involved shows no influence on the quality of the proposals. Despite the high number of industrial participants present on the proposals, it is observed that they play secondary roles in the proposals, with a very low number projects leaded by companies. Also, it is observed that partnerships between research institutions (non-universities) are the most successful. Concerning topics of the proposals, the technology human-robot interface and the product vision robot for small-scale manufacturing are the most significant. Finally, the paper shows clusters of institutions extracted from the giant network of relations obtained from the ECHORD set of proposals.