Implicit Neural Field-Based Process Planning for Multi-Axis Manufacturing: Direct Control over Collision Avoidance and Toolpath Geometry

2025-11-15

AI Summary

Existing bending-layer process planning methods address collision avoidance indirectly, and toolpaths are generated in post-processing, precluding direct geometric control during optimization. This paper proposes an end-to-end differentiable process planning framework based on implicit neural representations (INRs). For the first time, it unifies manufacturing layer generation and toolpath design within a single differentiable model: layers and toolpaths are jointly represented by sine-activated INRs, enabling arbitrary point-wise field evaluation and gradient computation. Collision constraints and topological control are explicitly embedded, and regularization ensures optimization stability. The method achieves joint, collision-free, high-fidelity toolpath optimization for both additive and subtractive manufacturing tasks, significantly enhancing automation and geometric controllability in fabricating complex freeform parts.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Existing curved-layer-based process planning methods for multi-axis manufacturing address collisions only indirectly and generate toolpaths in a post-processing step, leaving toolpath geometry uncontrolled during optimization. We present an implicit neural field-based framework for multi-axis process planning that overcomes these limitations by embedding both layer generation and toolpath design within a single differentiable pipeline. Using sinusoidally activated neural networks to represent layers and toolpaths as implicit fields, our method enables direct evaluation of field values and derivatives at any spatial point, thereby allowing explicit collision avoidance and joint optimization of manufacturing layers and toolpaths. We further investigate how network hyperparameters and objective definitions influence singularity behavior and topology transitions, offering built-in mechanisms for regularization and stability control. The proposed approach is demonstrated on examples in both additive and subtractive manufacturing, validating its generality and effectiveness.

Problem

• Direct collision avoidance control in multi-axis manufacturing
• Joint optimization of manufacturing layers and toolpaths
• Stable topology transitions through neural network regularization

Innovation

• Implicit neural fields embed layer and toolpath generation
• Direct collision avoidance via differentiable field evaluation
• Joint optimization with built-in regularization for stability