The architecture of human-controlled arm manipulator operator training system

Nowadays Industrial robots of different kinematic structures and functionality are widely used nowadays in different areas of industry and most of them function autonomously with pre-programmed set of actions or typical trajectories. Some special purposes mobile and stationary robots are human-controlled and in most cases require qualified operator skills. For example, in nuclear industry the mechanical and electro-mechanical “master arm - slave arm” manipulators are widely used. Modern approaches of control systems and human machine interfaces designs allow to eliminate direct copy of kinematic configuration of manipulator arms, add semi-automatic and automated control modes. Key feature of such manipulator systems is a presence of human in control loop, by reason of variety and complexity of manipulations and, in some cases, non-deterministic environment. Due to these factors, it is very desirable to form operator sustainable skills to control such manipulators, including learning process using training systems. This article describes general approaches and practical aspects of the operator training and qualification system for arm-based special purpose manipulators. The set of training system functions include: general manipulator control (basic motion) and grasping actions, manipulator operations in restricted working areas, operator actions using virtual reality helms and multi-monitor visualization, etc. The hardware and software architecture of training system should allow effective training process and teamwork of trainee and instructor to reach good results. The paper proposes ROS-based software part of training system with description of inter-process communication messages, data formats, integration with database and following analysis of trainee action.