In this study, we introduce "SARDiM," a modular semi-autonomous platform enhanced with mixed reality for industrial disassembly tasks. Through a case study focused on EV battery disassembly, SARDiM integrates Mixed Reality, object segmentation, teleoperation, force feedback, and variable autonomy. Utilising the ROS, Unity, and MATLAB platforms, alongside a joint impedance controller, SARDiM facilitates teleoperated disassembly. The approach combines FastSAM for real-time object segmentation, generating data which is subsequently processed through a cluster analysis algorithm to determine the centroid and orientation of the components, categorizing them by size and disassembly priority. This data guides the MoveIt platform in trajectory planning for the Franka Robot arm. SARDiM provides the capability to switch between two teleoperation modes: manual and semi-autonomous with variable autonomy. Each was evaluated using four different Interface Methods (IM): direct view, monitor feed, mixed reality with monitor feed, and point cloud mixed reality. Evaluations across the eight IMs demonstrated a 40.61% decrease in joint limit violations using Mode 2. Moreover, Mode 2-IM4 outperformed Mode 1-IM1 by achieving a 2.33%-time reduction while considerably increasing safety, making it optimal for operating in hazardous environments at a safe distance, with the same ease of use as teleoperation with a direct view of the environment.

翻译：本研究提出"SARDiM"——一种面向工业拆解任务的模块化半自主平台，该平台通过混合现实技术增强功能。以电动汽车电池拆解为案例，SARDiM集成了混合现实、目标分割、远程操控、力反馈及可变自主性等核心技术。基于ROS、Unity和MATLAB平台，结合关节阻抗控制器，SARDiM实现了远程操控拆解流程。该方法采用FastSAM进行实时目标分割，通过聚类分析算法处理生成数据，确定组件质心与姿态，并根据尺寸和拆解优先级对组件进行分类。该数据引导MoveIt平台为Franka机械臂规划运动轨迹。SARDiM支持两种远程操控模式切换：手动模式与可变自主性半自主模式。每种模式通过四种界面方法（IM）进行评估：直接视觉、监控画面、混合现实结合监控画面、点云混合现实。八组IM测试结果表明，模式2的关节限位违规率下降40.61%。此外，模式2-IM4相比模式1-IM1减少2.33%操作时间，同时大幅提升安全性，使其成为在危险环境中实现安全距离操作的最优方案，并具备与直接视野远程操控同等的易用性。