摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-调查人员发布了关于机器人的新报告。根据NewsRx Journal Ists在意大利雷吉奥·埃米利亚的新闻报道，研究表明，“过去十年，协作机器人（cobot）在工业应用中得到了广泛的应用。cobot可以被放置在保护笼子之外，通常被认为比大型经典工业机器人更直观，更容易编程。”新闻记者引用了摩德纳大学和雷吉奥·爱米利娅的研究，“然而，尽管合作机器人被广泛采用，但由于缺乏车间工人的培训和理解，合作潜力和机会似乎阻碍了灵活生产过程。研究人员将重点放在技术解决方案上，使新手机器人用户更容易训练合作机器人。然而，这些工作大部分还没有离开实验室。因此，为了向车间工人传授如何编程协作机器人的技能和知识,我们确定了新手编程协作机器人所必须掌握的一般基本知识和技能,介绍了如何构建和实施基于认知学徒的协作机器人培训,并使用一个测试框架对20名参与者进行了测试。UR10e和UR3e机器人。我们考虑了自适应训练和自我调节训练两种情况。我们发现，自适应训练和自我调节训练在向新手传递知识和技能方面是有效的，但没有发现自适应训练和自我调节训练之间的决定性差异。结果表明，由于所提出的训练方法，两组都能显著减少任务时间，达到减少40%的效果。虽然在位置误差方面保持相同水平的表现。但对从业人员来说没有TE-本文的动机是，SM Aller的采用，所谓的协作机器人在制造业中正在增加，但单个机器人在企业的多个地方灵活使用的潜力似乎没有实现。如果更多的非熟练工人了解协作机器人并接受结构化培训，他们将能够独立地为机器人编程。这将改变目前固定的协作机器人的格局，转向更灵活的机器人使用，从而提高公司内部整体设备效率和能力。为此，我们将培养协作机器人编程的一般技能和知识。这有助于提高新手需要知道的知识的透明度。我们展示了如何在结构化的培训框架中促进这些知识和技能，该框架有效地将必要的编程知识和技能传授给新手。随着学习者的进步，这个框架可以应用于更广泛的知识和技能。然而，我们确定的技能和知识在机器人平台上是通用的。协作机器人界面各不相同。因此，该方法的一个实际限制包括需要一个关于特定协作机器人的知识渊博的人，以便在该模型的特定领域创建培训材料。然而，根据我们确定的技能列表，它提供了一个更容易的起点。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ro botics. According to news reporting from Reggio Emilia, Italy, by NewsRx journal ists, research stated, "Collaborative robots (cobots) have seen widespread adopt ion in industrial applications over the last decade. Cobots can be placed outsid e protective cages and are generally regarded as much more intuitive and easy to program compared to larger classical industrial robots." The news correspondents obtained a quote from the research from the University o f Modena and Reggio Emilia, "However, despite the cobots' widespread adoption, t heir collaborative potential and opportunity to aid flexible production processe s seem hindered by a lack of training and understanding from shop floor workers. Researchers have focused on technical solutions, which allow novice robot users to more easily train collaborative robots. However, most of this work has yet t o leave research labs. Therefore, training methods are needed with the goal of t ransferring skills and knowledge to shop floor workers about how to program coll aborative robots. We identify general basic knowledge and skills that a novice m ust master to program a collaborative robot. We present how to structure and fac ilitate cobot training based on cognitive apprenticeship and test the training f ramework on a total of 20 participants using a UR10e and UR3e robot. We consider ed two conditions: adaptive and self-regulated training. We found that the facil itation was effective in transferring knowledge and skills to novices, however, found no conclusive difference between the adaptive or self-regulated approach. The results demonstrate that, thanks to the proposed training method, both group s are able to significantly reduce task time, achieving a reduction of 40% , while maintaining the same level of performance in terms of position error. No te to Practitioners-This paper was motivated by the fact that the adoption of sm aller, so-called collaborative robots is increasing within manufacturing but the potential for a single robot to be used flexibly in multiple places of a produc tion seems unfulfilled. If more unskilled workers understood the collaborative r obots and received structured training, they would be capable of programming the robots independently. This could change the current landscape of stationary col laborative robots towards more flexible robot use and thereby increase companies ' internal overall equipment efficiency and competencies. To this end, we identi fy general skills and knowledge for programming a collaborative robot, which hel ps increase the transparency of what novices need to know. We show how such know ledge and skills may be facilitated in a structured training framework, which ef fectively transfers necessary programming knowledge and skills to novices. This framework may be applied to a wider scope of knowledge and skills as the learner progresses. The skills and knowledge that we identify are general across robot platforms, however, collaborative robot interfaces differ. Therefore, a practica l limitation to the approach includes the need for a knowledgeable person on the specific collaborative robot in question in order to create training material i n areas specific to that model. However, with our list of identified skills, it provides an easier starting point."
NETL
NSTL