Deformable State Estimation for Autonomous Surgical Tissue Retraction Under Partial Observability
For autonomous surgical systems, this work provides a practical state estimation method that enables effective deformable manipulation under realistic perception constraints.
The paper tackles state estimation for deformable tissue retraction under partial observability, where only sparse noisy observations are available. The proposed learned estimator reconstructs the full deformable mesh from 40 noisy vertex observations and achieves 98.1% of oracle performance in multi-step retraction.
Surgical tissue retraction requires effective manipulation planning under partial and noisy perception. We study state estimation for deformable tissue retraction, where only sparse observations of the tissue surface are available at decision time. We propose a learned state estimator that reconstructs the full deformable mesh state from 40 noisy vertex observations. The estimator combines a multilayer perceptron with a low-dimensional PCA latent representation and is trained using geometry-aware regularization that encourages smooth and physically plausible deformations. We evaluate the approach in a 2D deformable sheet simulation using single-step and multi-step retraction planning. Results show that the learned estimator achieves 98.1% of oracle performance in multi-step retraction while supporting efficient inference. These results demonstrate that learned, geometry-regularized state estimation can support effective deformable manipulation under realistic perception constraints.