Human-Machine Interaction Systems for Training Industrial Robots

摘要

Workplace robot processing speed and efficiency depend on human-machine interaction. This study investigated RLIL, ViTREX, and NLCCF, three innovative HMI approaches. The purpose is to improve workplace robot setup and use. RLIL uses copying and reinforcement learning to improve robot behaviour in real time. Workshops and assembly lines benefit from this flexible and precise solution. Computer vision lets ViTREX robots adapt to new environments. This makes moving and transport simpler. In circumstances where people need to utilize conventional language to lead robots, NLCCF makes it easier for people and robots to communicate. We assessed these methods’ F1 accuracy, precision, and high score. RLIL was accurate and precise, making it suitable for precise outcomes. ViTREX balanced precision with memory, making it ideal for users who had to choose. The NLCCF was versatile and outperformed in every way. These cutting-edge HMI technologies provide more alternatives, faster decision-making, and greater communication, making them valuable in current workplaces. Considering memory, precision, and balance, the procedure should be suited to the application. These technologies might improve robot-human collaboration in manufacturing, enabling more efficient, flexible, and natural automation.