发表机构
Mærsk Mc-Kinney Møller Institute; University of Southern Denmark; Danish Institute for Advanced Study (DIAS)（马士基麦金尼姆勒研究所; 南丹麦大学; 丹麦高等研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对机器人插入任务，提出结合UMAP降维与Wilson Score置信边界的二分类自监督学习数据引擎，可随任务执行减少昂贵验证需求并控制误差水平。
AI 中文摘要
柔性制造要求解决方案能快速部署且设置时间最短，以保持竞争力，控制误差水平是关键属性，故障可能从轻微性能下降到严重设备损坏，但传统部署常涉及大量设置、数据收集、模型训练或参数调优及系统测试，导致显著延迟，阻碍商业可行性。我们提出一种数据引擎，在执行任务时收集数据并提升性能，该引擎包含两个分类器：快速模型预测与昂贵验证。首先执行模型预测，基于预测的置信度水平决定是否使用昂贵验证，通过调整置信度水平，用户可控制可容忍误差水平。我们将该方法应用于真实机器人插入任务，使用力数据进行模型预测，系统采用UMAP降维，并使用Wilson Score计算预测的置信边界。结果表明，该方法能随时间学习并减少对昂贵验证的需求，同时保持在设定的错误率范围内，凸显了置信边界在自改进模型中提升机器人分类任务可靠性的潜力。
英文摘要
Flexible manufacturing requires rapid deployment of solutions and minimal setup time to remain competitive. An essential attribute is the ability to control error levels, as failures can range from minor performance degradation to severe equipment damage. However, conventional deployment often involves extensive setup, data collection, model training or parameter tuning, and system testing, resulting in significant delays that hinder commercial feasibility. We propose a data engine which gathers data and improves its performance while executing the task. The data engine consists of two classifiers, a fast model prediction and expensive verification. First, a model prediction is performed and based on the confidence level of the prediction, the expensive verification can be used. By adjusting the confidence level, users can control the level of tolerable error. Our method is implemented on a real-world robotic insertion task, which uses force data for the model prediction. The system applies UMAP dimensionality reduction and uses Wilson-Score to compute the confidence bounds of the prediction. Results demonstrate the ability to learn and reduce the need for expensive verifications over time, while staying within the set error-rate. The results highlight the potential of confidence bounds in self-improving models to enhance reliability in robotic classification task.
Comments8 pages, 7 figures, 2 tables
