Suturing is required in almost all surgeries but it is challenging to perform with surgical robots due to limited vision and/or haptic feedback. To tackle this problem, we present an autonomous suturing framework that encompasses a novel needle path planner, as well as an accurate needle pose estimator and a six degrees-of-freedom controller. A novel needle grasper is developed that enables needle pose estimation both inside and outside the tissue. The framework was evaluated experimentally using the Raven IV surgical system and important suture parameters were quantified. The experiment results confirmed a needle pose estimation accuracy of°in orientation across all directions. Moreover, the results revealed that using the proposed framework enabled following the reference needle trajectories with errors of 2.07 mm in position and 4.29°in orientation. These are drastic improvements of more than 10× in position and 5× in orientation compared to the Raven IV kinematic controller. Additionally, the results verified that our framework delivered the desired clinical suture parameters successfully across tissue phantom environments with different mechanical properties and under various needle trajectories. A supplementary video can be found at: http://bionics.seas.ucla.edu/research/surgeryproject18.htmlhttp://bionics.seas.ucla.edu/research/surgeryproject18

Tissue manipulation is a frequently used fundamental subtask of any surgical procedures, and in some cases it may require the involvement of a surgeon's assistant. The complex dynamics of soft tissue as an unstructured environment is one of the main challenges in any attempt to automate the manipulation of it via a surgical robotic system. Two AI learning based model predictive control algorithms using vision strategies are proposed and studied: (1) reinforcement learning and (2) learning from demonstration. Comparison of the performance of these AI algorithms in a simulation setting indicated that the learning from demonstration algorithm can boost the learning policy by initializing the predicted dynamics with given demonstrations. Furthermore, the learning from demonstration algorithm is implemented on a Raven IV surgical robotic system and successfully demonstrated feasibility of the proposed algorithm using an experimental approach. This study is part of a profound vision in which the role of a surgeon will be redefined as a pure decision maker whereas the vast majority of the manipulation will be conducted autonomously by a surgical robotic system. A supplementary video can be found at: http://bionics.seas.ucla.edu/research/surgeryproject17.html.