Continuous shape estimation of continuum robots using X-ray images

摘要: We present a new method for continuously and accurately estimating the shape of continuum robot during medical procedure using small number X-ray projection images (e.g., radiographs or fluoroscopy images). Continuum robots have curvilinear structure, enabling them to maneuver through constrained spaces by bending around obstacles. Accurately robot's over time is crucial success procedures that require avoidance anatomical obstacles sensitive tissues. Online estimation complicated uncertainty in its kinematic model, movement procedure, noise images, clinical need minimize acquired. Our integrates kinematics models with data extracted from an optimally selected set images. represents as deformable surface which can be described linear combination space basis functions. take advantage probabilistic priors numeric optimization select optimal camera configurations, thus minimizing expected error. evaluate our simulated concentric tube demonstrate obtaining between 3 10 viewpoints enables online errors significantly lower than model alone randomly spaced viewpoints.