Perceptual Docking for Robotic Control (Equipment Rich Proposal)

点击翻译按钮获取中文摘要

The quest for protecting humans from direct exposure to hazardous or safety critical environments has been the driving force behind technological developments in robotics. Whilst robotics and other related technologies continue to grow, researchers across the globe are turning their attention to what is perhaps the most challenging safety critical environment of all / the human body. Deploying robots around and within the human body, particularly for robotic surgery presents a number of unique and challenging problems that arise from the complex and often unpredictable environments that characterise the human anatomy. Master-slave based robots such as the daVinci system, which embodies the movements of trained minimal access surgeons through motion scaling and compensation, are gaining clinical significance. Micro-machines possessing sensors and actuators based on the MEMS technology are also rapidly emerging. Under the dichotomy of autonomous and manipulator technologies in robotics, intelligence of the robot is typically pre-acquired through high-level abstraction and environment modelling. For procedures that involve complex anatomy and large tissue deformation, however, this is known to create major difficulties. The regulatory, ethical and legal barriers imposed on interventional surgical robots also give rise to the need of a tightly integrated control between the operator and the robot when autonomy is being pursued. The aim of this project is to research into a new concept of perceptual docking for robotic control. The word docking is different in meaning to the conventional term used in mobile robots. It represents a fundamental paradigm shift of perceptual learning and knowledge acquisition for robotic systems in that operator specific motor and perceptual/cognitive behaviour is assimilated in situ through a gaze contingent framework. We hypothesise that saccadic eye movements and ocular vergence can be used for attention selection and recovering 3D motion and deformation of the soft tissue during MIS procedures. It is expected that the method will also open up a range of completely new opportunities for effective human-machine interaction. This proposal seeks equipment and research funding for establishing an integrated core experimental facility at Imperial College for investigating key challenges related to perceptual docking in robotics and allied research issues related to human-machine interaction, visual perception and machine learning, ergonomics, kinematics and actuation design, intra-operative image guidance, motion and biomechanical modelling, tissue-instrument interaction, and robotic control. Matching funding from the Institute of Biomedical Engineering at Imperial has already been secured, and the facility is expected to greatly enhance the multidisciplinary research capacity and facilitate the interaction and initiation of new research programmes across a number of different disciplines.