Usually, programmingrobot systems is expensive and complex and only profitable for companies with big lot sizes. Hence these systems do currently not play a big role in small or medium sized enterprises. This work ex...
详细信息
ISBN:
(纸本)9783319612768;9783319612751
Usually, programmingrobot systems is expensive and complex and only profitable for companies with big lot sizes. Hence these systems do currently not play a big role in small or medium sized enterprises. This work extends the programming paradigm published in [1] that is based on the playback programming method, so that also sensor information can be used to generate more complex robot programs by means of playback programming in addition to the already existing functionality. This is achieved by developing a concept for sensor-based loops and branches that fits well to the programming paradigm. Finally, the enhanced programming system is evaluated in a user study with experts and non-experts with respect to its intuitiveness. The user study is divided into a part that tests the user interface and a part that evaluates the system as a whole, so that possible weak spots of the system or the user interface can be detected and can be taken into account in further work with this programming system.
programming by Demonstration (PbD) is used to transfer a task from a human teacher to a robot, where it is of high interest to understand the underlying structure of what has been demonstrated. Such a demonstrated tas...
详细信息
programming by Demonstration (PbD) is used to transfer a task from a human teacher to a robot, where it is of high interest to understand the underlying structure of what has been demonstrated. Such a demonstrated task can be represented as a sequence of so-called actions or skills. This work focuses on the recognition part of the task transfer. We propose a framework that recognizes skills online during a kinesthetic demonstration by means of position and force-torque (wrench) sensing. Therefore, our framework works independently of visual perception. The recognized skill sequence constitutes a task representation that lets the user intuitively understand what the robot has learned. The skill recognition algorithm combines symbolic skill segmentation, which makes use of pre- and post-conditions, and data-driven prediction, which uses support vector machines for skill classification. This combines the advantages of both techniques, which is inexpensive evaluation of symbols and usage of data-driven classification of complex observations. The framework is thus able to detect a larger variety of skills, such as manipulation and force-based skills that can be used in assembly tasks. The applicability of our framework is proven in a user study that achieves a 96% accuracy in the online skill recognition capabilities and highlights the benefits of the generated task representation in comparison to a baseline representation. The results show that the task load could be reduced, trust and explainability could be increased, and, that the users were able to debug the robot program using the generated task representation. (c) 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).
The rapid evolution of industrial robot hardware has created a technological gap with software, limiting its adoption. The software solutions proposed in recent years have yet to meet the industrial sector's requi...
详细信息
The rapid evolution of industrial robot hardware has created a technological gap with software, limiting its adoption. The software solutions proposed in recent years have yet to meet the industrial sector's requirements, as they focus more on the definition of task structure than the definition and tuning of its execution parameters. A framework for task parameter optimization was developed to address this gap. It breaks down the task using a modular structure, allowing the task optimization piece by piece. The optimization is performed with a dedicated hill-climbing algorithm. This paper revisits the framework by proposing an alternative approach that replaces the algorithmic component with reinforcement learning (RL) models. Five RL models are proposed with increasing complexity and efficiency. A comparative analysis of the traditional algorithm and RL models is presented, highlighting efficiency, flexibility, and usability. The results demonstrate that although RL models improve task optimization efficiency by 95%, they still need more flexibility. However, the nature of these models provides significant opportunities for future advancements.
The high dynamics of globalized markets and their increase in competition, as well as the demographic changes in western countries causing an increasing shortage of skilled personnel are resulting in major challenges ...
详细信息
The high dynamics of globalized markets and their increase in competition, as well as the demographic changes in western countries causing an increasing shortage of skilled personnel are resulting in major challenges for production companies today. These challenges relate in particular to the processes of assembly forming the last process step in the value chain due to its high share of manual labor. Collaborative assembly, which is characterized by immediate interaction of humans and robots, utilizes the strengths of both partners and is seen as an opportunity to achieve a higher level of flexibility in assembly just as well to support and relieve people of for instance non-ergonomic tasks through automation at work. Although almost every robot manufacturer already has collaborative systems in its product portfolio, these are not yet widely used in industrial production. This might have a variety of reasons, such as the fear of a risky investment or the lack of expertise within the company related to collaborative systems. This article shows a conceptual method that helps companies implementing human-robot-collaboration in their production more quickly and with less implied risk, thus addressing the forthcoming challenges. As a first step, companies must be qualified to make a suitable selection for a possible collaboration scenario. To achieve this, they need a tool to analyze and to evaluate their production processes according to their suitability for human-robot-collaboration. An important feature for an easy and effective use is that the process is formalized so that employees of companies can quickly and easily analyze different processes. The necessary criteria and procedures are developed accordingly and are integrated into the selection method. The main goal is to give the company a recommendation which of their processes are most suitable for human-robot-collaboration, so that they can be used effectively in their production.
Collaborative robots (cobots) can improve productivity by flexibly assisting production workers. Nevertheless, due to missing use cases, cobots have yet to be widely adopted in manufacturing. Democratizing robot progr...
详细信息
Collaborative robots (cobots) can improve productivity by flexibly assisting production workers. Nevertheless, due to missing use cases, cobots have yet to be widely adopted in manufacturing. Democratizing robotprogramming by introducing cobots in public fablabs (or makerspaces) could lead to new applications transferrable to industry thanks to the creativity of interested laypersons. Fablabs could also mitigate the risk of unemployment due to automation by training cobot programmers for manufacturing jobs. In support of the proposed approach this paper introduces a participatory three-layer programming model designed to enable people with little or no programming experience to become effective cobot operators. The model builds on task-oriented programming environments extending them by more versatile yet intuitiveprogramming environments. The model has been successfully evaluated on the basis of a real human-robot assembly application.
In the context of the rapid development of micro-devices and photonics, the importance of efficient automation solutions is becoming increasingly important. The automation of assembly processes in particular is a deci...
详细信息
In the context of the rapid development of micro-devices and photonics, the importance of efficient automation solutions is becoming increasingly important. The automation of assembly processes in particular is a decisive factor, as assembly is responsible for a large proportion of costs. The programming of robots, particularly in the field of micro-assembly, requires extensive specialist knowledge due to the complexity of the assembly systems and processes. Increasingly more powerful large language models (LLMs) enable their use in robotprogramming. These allow interaction through natural language, providing an intuitive user interface. In this work, we utilize a LLM to assist users in programming new micro-assembly processes. We develop an assistant that we integrate into a robot Operating System 2 (ROS2) framework. This framework enables the control and programming of a micro-assembly robot via ROS2 services. The assistant has access to these services and information about the components. Based on user requests, the assistant can parameterize these services and arrange them sequentially according to the assembly task. The assembly sequence can subsequently be modified by the user, either by using the assistant again or manually. We test the performance of the developed assistant using example tasks and demonstrate that, particularly, shorter sequences can be reliably generated. Finally, we present potential improvements and extensions of the application.
robot manipulators are widely used in industries to automate myriad operations. To address the demand shifts in industries, automated systems such as robots must flexibly adapt in response. Such dynamics often necessi...
详细信息
robot manipulators are widely used in industries to automate myriad operations. To address the demand shifts in industries, automated systems such as robots must flexibly adapt in response. Such dynamics often necessitate end-users to reprogram robots to meet the changing industry needs. This leads to a demand for experienced programmers, familiar with proprietary robot software. As one alternative, an augmented reality (AR) framework can offer a user-friendly solution that permits end-users to reprogram robots without any domain expertise. This paper presents an AR teaching (ART) methodology that allows end-users to program varied manipulators in an intuitive and effortless manner for tool-path teaching. The ART method is contrasted with an alternative kinesthetic teaching method for its performance and user experience. Results show that the ART method yields a convenient and time-efficient teaching method and it is recommended by users over the kinesthetic teaching method.
暂无评论