Robot mills biological tissue accurately using generic anatomy and active sensing
Autonomous Precision Milling of Biological Structures via Generic Anatomical Priors and Active Boundary Perception
Robotics
Summary
Milling biological tissues precisely is hard because it’s difficult to know the exact shape and material thickness beforehand. The authors present a method where a robot uses general knowledge about anatomy combined with active probing to understand boundaries during the milling process. This lets the robot adjust its actions in real time for safer and more accurate work. They tested this approach on biological models and live mice with promising results.
What this means in practice
- •For medical robotics teams: Automate precise milling of patient-specific biological tissues using generic anatomical models and active sensing for boundary detection.
- •For robotics developers: Develop adaptive milling robots that use hybrid vision and force feedback to safely operate near uncertain tissue boundaries.
Authors
Enduo Zhao, Xiaofeng Lin, Yifan Wang, Yuhan Song, Weihan Li, Saul Alexis Heredia Perez, Kanako Harada
Abstract
Autonomous precision milling of biological structures is challenged by incomplete knowledge of target geometry, local material thickness, and critical internal boundaries. Subject-specific preoperative models can address geometric and thickness variations, but static models cannot determine boundary status encountered during execution, while repeated target-specific imaging limits scalability. This article presents an uncertainty-aware autonomous milling framework that assigns complementary roles to generic anatomical priors and active boundary perception. A generic anatomical prior provides conservative global guidance and is transformed through semantic-guided registration and hybrid vision-force calibration into robot-executable guidance for individual targets. As milling approaches uncertain boundaries, the robot actively probes the remaining structure and uses relative stiffness changes to estimate boundary status and structural detachability. A state-adaptive controller governs transitions between active perception and spatially selective incremental refinement, repeating this cycle until the termination criterion is satisfied. Hierarchical experiments on biological surrogates and in vivo mouse cranial window creation demonstrate accurate anatomical prior transfer, reliable boundary adaptation, and autonomous precision milling of biological structures.