摘要
一位新闻记者兼机器人与机器学习的新闻编辑每日新闻-关于人工智能的新研究结果已经发表。根据NewsRx记者从奥地利Villach发回的新闻报道，研究表明，“按照ISO/TS 15066标准的性能和力限制方法，在假设准静态冲击的危急情况下评估人-抢OT协作任务的安全性。”新闻记者从卡林西亚应用科学大学的研究中得到一句话：“为此，对撞击力和压力进行实验测量，并与ISO/TS 15066规定的限值进行比较。因此，当协作工作空间或任务发生变化时，必须重复进行这种安全评估，这严重限制了协作系统的灵活性。”本文提出了一种基于物理指南的机器学习(ML)方法,用UR10e机器人在感兴趣范围内测量的峰值冲击力,结合位置相关的线性化模型,训练了一个提升决策树(B DT)集成和一个前馈神经网络(NN).
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New study results on artificial intell igence have been published. According to news reporting originating from Villach , Austria, by NewsRx correspondents, research stated, "Following the performance and force limitation method of the ISO/TS 15066 standard, safety of a human-rob ot collaboration task is assessed for critical situations assuming quasi-static impact." The news correspondents obtained a quote from the research from Carinthia Univer sity of Applied Sciences: "To this end, impact forces and pressures are experime ntally measured and compared with limit values specified by ISO/TS 15066. Conseq uently, such a safety assessment must be repeated whenever something changes in the collaborative workspace or the task, which severely limits the flexibility o f collaborative systems. To overcome this problem, in this paper a physics guide d machine learning (ML) method for prediction of peak impact forces, within pred efined modification dimensions of collaborative applications, is proposed. Along with a pose-dependent linearized model, an ensemble of boosted decision tree (B DT) in combination with a feed-forward neural network (NN) is trained with peak impact forces measured at a UR10e robot covering the range of interest."
NETL
NSTL