A 3-DOF Neuro-Adaptive Pose Correction System For Frameless and Maskless Cancer Radiotherapy

Precise patient positioning during treatment of cancers of the head and neck region is fundamental to a successful clinical removal of malignant tumors. We propose a 3-DOF soft-robot position correcting system to correct head deviations along 3 axes. The robot consists of inflatable air bladders to move the head while ensuring patient safety and comfort. The robot is controlled with an based off an adaptive neuro-controller consisting of a state feedback regulator, a command reference tracking component, and a function approximator that compensated for parametric and non-parametric system errors in real-time. Feedback is provided by a precise 3D stereo camera for surface imaging of the head. We implement the controller on a 3D printed head-and-neck simulator and demonstrate that our control exhibits real-time learning to correct positioning deviations.