Meta-learning enhanced adaptive robot control strategy for automated PCB assembly

TL;DR

The paper tackles occlusion and lighting challenges in PCB assembly by proposing a vision-free, interactive meta-search method that compensates robotic positioning errors under uncertainty. It models insertion feasibility with a Gaussian distribution, iteratively updating the posterior and guiding search via gradient ascent and Monte Carlo sampling, with repulsion terms to maintain diverse search covers. Three classic search strategies (linear, spiral, hybrid) are extended into a meta-learning framework, showing that the proposed method can learn from past insertions to accelerate future placements, demonstrated on odd-form components using a UR3e-based assembly line. Experimental results indicate substantial reductions in assembly time (e.g., average times around 42–47 s for the studied tasks) and robust adaptation to irregular hole positions, highlighting potential for low-cost, flexible production in multi-variety, small-batch contexts. The work opens avenues for sequence/route optimization and broader robotic-adaptive strategies in PCB assembly and similar tasks.

Abstract

The assembly of printed circuit boards (PCBs) is one of the standard processes in chip production, directly contributing to the quality and performance of the chips. In the automated PCB assembly process, machine vision and coordinate localization methods are commonly employed to guide the positioning of assembly units. However, occlusion or poor lighting conditions can affect the effectiveness of machine vision-based methods. Additionally, the assembly of odd-form components requires highly specialized fixtures for assembly unit positioning, leading to high costs and low flexibility, especially for multi-variety and small-batch production. Drawing on these considerations, a vision-free, model-agnostic meta-method for compensating robotic position errors is proposed, which maximizes the probability of accurate robotic positioning through interactive feedback, thereby reducing the dependency on visual feedback and mitigating the impact of occlusions or lighting variations. The proposed method endows the robot with the capability to learn and adapt to various position errors, inspired by the human instinct for grasping under uncertainties. Furthermore, it is a self-adaptive method that can accelerate the robotic positioning process as more examples are incorporated and learned. Empirical studies show that the proposed method can handle a variety of odd-form components without relying on specialized fixtures, while achieving similar assembly efficiency to highly dedicated automation equipment. As of the writing of this paper, the proposed meta-method has already been implemented in a robotic-based assembly line for odd-form electronic components. Since PCB assembly involves various electronic components with different sizes, shapes, and functions, subsequent studies can focus on assembly sequence and assembly route optimization to further enhance assembly efficiency.

Figures (12)

• Figure 1: Illustration of robot gripper (in virtual environment).
• Figure 2: Examples of components clamping tolerance(left) and positioning tolerance(right) during assembly.
• Figure 3: The overview experiment process.
• Figure 4: Cases of component insertion. Blue circle: feasible; Red circle: not feasible; Green circle: on the boundary. (For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.)
• Figure 5: Gradient ascent direction for the case of two search covers. The black short arrows show the gradient descent directions. (For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.)