Hybrid Adaptive Control Strategy for Continuum Surgical Robot Under External Load

Natural orifice transluminal endoscopic surgery (NOTES) has received significant attentions due to its minimal incision trauma compared with traditional multi-port robot assisted surgery. Continuum robot can be used in NOTES due to its high flexibility which can adapt to circuitous paths. However, the modeling of continuum robot is complex due to its nonlinear dynamics, especially with uncertain external disturbance. In this letter a hybrid adaptive control framework is proposed, combining offline trained robot inverse kinematics with neural network and online adaptive adjustment of PID controller parameters with another neural network, providing additional driving amount to the robot system to compensate the positioning error caused by external disturbance. Path tracking and point tracking experiments with external load are conducted and the results validate that the proposed hybrid adaptive control framework can compensate uncertain factors such as friction, driving tendon relaxation and external load during robot movement, and obtain relatively high positioning accuracy (maximum absolute error less than 2 mm) with quickresponse.