Learning Dynamic Spatial Relations

Andreas Bihlmaier describes a novel method to model dynamic spatial relations by machine learning techniques. The method is applied to the task of representing the tacit knowledge of a trained camera assistant in minimally-invasive surgery. The model is then used for intraoperative control of a robot that autonomously positions the endoscope. Furthermore, a modular robotics platform is described, which forms the basis for this knowledge-based assistance system. Promising results from a complex phantom study are presented.ContentsEndoscope Robots and Automated Camera GuidanceKnowledge-based Cognitive SystemsModular Research Platform for Robot-Assisted Surgery based on ROSLearning of Surgical Know-how by Models of Spatial RelationsIntraoperative Camera AssistanceEvaluation Study: TME in the Open Source Heidelberg Laparoscopic Phantom (OpenHELP)Target GroupsScientists and students in the field of robotics, surgical assistance systems, cognitive and knowledge-based systemsPractitioners in companies selling manually controlled robots or motorized endoscope holdersAbout the AuthorAndreas Bihlmaier is leader of the Cognitive Medical Technologies group in the Institute for Anthropomatics and Robotics - Intelligent Process Control and Robotics Lab (IAR-IPR) at the Karlsruhe Institute of Technology (KIT). His research focuses on cognitive surgical robotics for minimally-invasive surgery, as part of the SFB/Transregio 125 Cognition-Guided Surgery.