Rapid AI-based generation of coverage paths for dispensing applications

2025-05-06

AI Summary

Thermal interface material (TIM) dispensing path planning traditionally relies on manual expertise or computationally expensive optimization algorithms. Method: This paper proposes an end-to-end neural network that directly generates air-free, production-ready dispensing paths from geometric specifications of the target cooling region. It introduces a novel label-free training paradigm integrating geometric feature encoding with industrial robot trajectory interface adaptation, enabling high-fidelity path generation under weak supervision. Contributions/Results: The method achieves 100% air-free coverage across diverse complex geometries, is fully compatible with existing dispensing hardware, and operates with inference latency <50 ms—over 100× faster than conventional optimization. It is the first to demonstrate real-time artificial neural network (ANN)-based inversion of manufacturing parameters to precisely realize target geometric states, providing a plug-and-play, general-purpose solution for intelligent process planning.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Coverage Path Planning of Thermal Interface Materials (TIM) plays a crucial role in the design of power electronics and electronic control units. Up to now, this is done manually by experts or by using optimization approaches with a high computational effort. We propose a novel AI-based approach to generate dispense paths for TIM and similar dispensing applications. It is a drop-in replacement for optimization-based approaches. An Artificial Neural Network (ANN) receives the target cooling area as input and directly outputs the dispense path. Our proposed setup does not require labels and we show its feasibility on multiple target areas. The resulting dispense paths can be directly transferred to automated manufacturing equipment and do not exhibit air entrapments. The approach of using an ANN to predict process parameters for a desired target state in real-time could potentially be transferred to other manufacturing processes.

Problem

• Automate coverage path planning for Thermal Interface Materials dispensing
• Replace manual expert methods with AI-based real-time solutions
• Enable label-free ANN prediction for manufacturing process parameters

Innovation

• AI-based rapid coverage path generation
• ANN predicts dispense paths without labels
• Real-time transfer to manufacturing equipment