Optical active perception with 3D Gaussian splatting enables autonomous instrument insertion in robotic vitreoretinal surgery

We present an optical active perception framework that enables autonomous instrument insertion through a trocar using robot-guided multi-view imaging. A low-cost RGB-D camera provides depth-guided viewpoint planning, while 3D Gaussian Splatting (3DGS) reconstructs a high-resolution trocar model from sparse multi-view RGB images with submillimeter fidelity, overcoming the precision limits of traditional 3D optical sensing systems, such as stereo and structured-light cameras. Integrated with a 6-DOF robotic arm, the system estimates trocar pose and aligns the instrument for safe insertion. Experiments on 10 ex vivo porcine eyes achieve approximately 0.6\,mm positional and 3.4$^\circ$ angular accuracy, demonstrating the promise of 3DGS-based optical active perception for robotic microsurgical navigation.