Digital-Twin-Assisted Skill Learning for 3C Assembly Tasks

The utilization of robots in computer, communication, and consumer electronics (3C) assembly has the potential to significantly reduce labor costs and enhance assembly efficiency. However, many typical scenarios in 3C assembly, such as the assembly of flexible printed circuits (FPCs), involve complex manipulations with long-horizon steps and high-precision requirements that cannot be effectively accomplished through manual programming or conventional skill-learning methods. To address this challenge, this article proposes a learning-based framework for the acquisition of complex 3C assembly skills assisted by a multimodal digital-twin environment. First, we construct a fully equivalent digital-twin environment based on the real-world counterpart, equipped with visual, tactile force, and proprioception information, and then collect multimodal demonstration data using virtual reality (VR) devices. Next, we construct a skill knowledge base through multimodal skill parsing of demonstration data, resulting in primitive policy sequences for achieving 3C assembly tasks. Finally, we train primitive policies via a combination of curriculum learning, residual reinforcement learning, and domain randomization methods and transfer the learned skill from the digital-twin environment to the real-world environment. The experiments are conducted to verify the effectiveness of our proposed method.

I. Introduction

In recent years, computer, communication, and consumer electronics (3C) products have been widely used in our daily life. However, the assembly of these products still heavily relies on manual labor. To reduce costs and improve efficiency, robots have gradually been integrated into 3C assembly processes [1], [2]. Today, 3C products are increasingly focused on miniaturization and portability, resulting in components that are diverse and flexible. Furthermore, the rapid evolution of 3C products necessitates continuously adjusting strategies to effectively assemble new products. Traditional programming methods are insufficient in addressing these complex situations, as they are time-consuming and costly [3], [4].