Autonomous Robotic Bone Micro-Milling System with Automatic Calibration and 3D Surface Fitting

2025-03-06

AI Summary

Automating bone micro-milling in murine cranial window surgery remains challenging due to the irregular surface topography and variable thickness of living skull bone, which impede accurate positioning and depth control. To address this, we propose a closed-loop control framework integrating automated calibration with online 3D surface reconstruction. The system combines a high-precision force-feedback robotic arm, structured-light 3D scanning, and an adaptive micro-milling strategy to enable real-time intraoperative perception, dynamic path planning, and precise bone ablation. Its key innovation lies in embedding surface fitting directly into the closed-loop control architecture—thereby overcoming the coupled morphological–thickness uncertainty inherent in irregular osseous tissue. Ex vivo validation demonstrates an 85.7% success rate, an average processing time of 2.1 minutes per specimen, and superior accuracy, repeatability, and stability compared to manual operation.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: 3D Computer Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Automating bone micro-milling using a robotic system presents challenges due to the uncertainties in both the external and internal features of bone tissue. For example, during a mouse cranial window creation, a circular path with a radius of 2 to 4 mm needs to be milled on the mouse skull using a microdrill. The uneven surface and non-uniform thickness of the mouse skull make it difficult to fully automate this process, requiring the system to possess advanced perceptual and adaptive capabilities. In this study, we propose an automatic calibration and 3D surface fitting method and integrate it into an autonomous robotic bone micro-milling system, enabling it to quickly, in real-time, and accurately perceive and adapt to the uneven surface and non-uniform thickness of the target without human assistance. Validation experiments on euthanized mice demonstrate that the improved system achieves a success rate of 85.7 % and an average milling time of 2.1 minutes, showing not only significant performance improvements over the previous system but also exceptional accuracy, speed, and stability compared to human operators.

Problem

• Automates bone micro-milling with robotic precision.
• Addresses uneven bone surfaces and thickness variations.
• Enhances accuracy and speed without human intervention.

Innovation

• Automatic calibration for robotic bone milling
• 3D surface fitting for uneven bone surfaces
• Real-time adaptation to non-uniform bone thickness