About this Research Topic
In recent years, robot-assistive surgery has attracted extensive attention because of its delicate operation, extended motion range and augmented visualization. It has been widely used in various surgeries, such as diagnostic biology, deep brain stimulation and tumor resection. However, some complex tasks, such as acupuncture, suturing, and knotting, still need surgeons to achieve. In order to release the complexity of surgical operations and enhance the interaction between surgical robots and surgeons, skill learning is proposed to improve the practicability of robots. It enables the robot to perform these complex operations autonomously after the surgeon's skill demonstration. Therefore, how to control the robot learning from the surgical skills of experts and accurately reproduce these operations is an effective way to enhance the autonomy of the surgical robot. It is becoming an inspiring and promising topic that can improve the performance of robot-assistive surgery.
In general, skill learning is divided into three stages, including demonstration, learning, and reproduction. After completing the human demonstration, the processing and modeling of the motion data will directly affect the reproduction ability of the robot. The traditional standard modeling methods include dynamical movement primitives, the Gaussian mixture model, and the Hidden Markov model. In order to improve the autonomous learning and imitation ability of robots, popular Artificial Intelligence approaches (e.g., reinforcement learning and deep learning) should be proposed to track human motion. It also needs to design some preprocessing algorithms for eliminating noise in the collected raw data. Furthermore, considering the high flexibility of the human arm, some control strategies (such as the human-robot variable stiffness control) should be applied to realize the flexible movement of the surgical manipulator. Finally, the tactile feedback mechanism can be used to increase the immersion of human-robot interaction, and the robustness and safety of robotic surgical systems need to be optimized in robot-assisted surgery.
This Research Topic will present the advanced skill learning in robot-assistive surgical systems and provide a comprehensive overview of future solutions from both theoretical and engineering aspects. Authors are encouraged to submit papers that discuss new directions in the way of original research in the field of complex robot-assistive surgical systems with a high level of autonomy. Review articles are also encouraged.
Potential topics include but are not limited to the following:
• Artificial intelligence in skill learning for surgical robotics
• Skill learning in robotics and its application in surgery
• Adaptive and robustness control for complex surgical robot systems
• Application of multimodal data fusion in robot-assisted surgery
• Skill-based human-robot cooperation in minimally invasive surgery
• Smart interaction in skill learning: Human, information, and robot
• Progress and prospects of learning ability in surgical robots
Keywords: Skill Learning, Robot Assistive Surgery, Surgical Robots, Machine Learning
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.