CASPER: Context-Aware Anomaly Detection System for Industrial Robotic Arms

Industrial cyber-physical systems (ICPS), which is the backbone of Industry 4.0, are the result of adapting emerging information communication technologies (ICT) to the industrial control systems (ICS). ICPS utilize autonomous robotic arms to accomplish manufacturing tasks. These arms follow a certain predetermined trajectory during the task. In this dataset, we present four files generated from a setup that contains two Universal Robot UR3e collaborative robotic arms:A .csv file that consists of accelerometer, gyroscope, and magnetometer data of an arm that accomplishes a repetitive task, captured via Nicla Sense ME.Two .csv files (one per industrial arm) that consist of built-in arm parameters such as joint current, and velocity values etc.A .pcap file that contains the TCP/IP traffic between the arms and the controller PC.We modified the joint velocity of the right arm during the experiment to simulate a cyberattack that causes physical deviations while the left arm runs normal. The whole experiment is 24 hours.

工业级 cyber-physical systems（工业物联网系统，简称 ICPS），作为工业4.0的骨架，是新兴的信息通信技术（ICT）在工业控制系统（ICS）中的应用结果。ICPS 利用自主式机械臂来完成制造任务，这些机械臂在执行任务过程中遵循预设的轨迹。在本数据集中，我们展示了由包含两台 Universal Robot UR3e 协作机械臂的配置产生的四个文件：一份包含加速度计、陀螺仪和磁力计数据的 .csv 文件，这些数据由 Nicla Sense ME 捕获，机械臂执行的是重复性任务；两份各自对应工业机械臂的 .csv 文件，这些文件包含了内置的机械臂参数，如关节电流、速度值等；一份 .pcap 文件，其中包含了机械臂与控制器 PC 之间的 TCP/IP 流量。在实验过程中，我们调整了右机械臂的关节速度，以模拟在左机械臂正常运行的同时，由网络攻击引起的物理偏差。整个实验持续了 24 小时。