Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Learning-Based Shape Estimation for Rigid Segment Based Continuum Robots
The Multi-Scale Robotics Lab develops novel actuation methods for endoscopic devices utilizing magnetic navigation systems (MNS). In MNS, an external magnetic field applies forces and torques on magnets attached to the endoscopes. To control these endoscopes, precise shape estimation techniques are required. Current methods try to estimate the endoscope’s shape by measuring the external field along the endoscope using hall-sensors. This method requires precise knowledge about the applied external field and often lacks in localization precision in certain directions.
The scope of this thesis is to design, evaluate and test a novel micro-sized shape estimation system for endoscopic applications. A local alternating magnetic field created at some points along the endoscope can be sensed with hall-sensors which are placed along the endoscope. The direction of the magnetic flux of the alternating magnetic field is therefore an indicator of endoscopes bending behavior. Learning-based methods shall be leveraged and compared to classical estimation methods. To enable easy integration of the developed code in the existing MSRL magnetic steering system, the estimator shall be integrated in the ROS framework. To enhance shape estimation, a powerful sensor fusion of the existing and the new localization system can be optionally implemented.
The scope of this thesis is to design, evaluate and test a novel micro-sized shape estimation system for endoscopic applications. A local alternating magnetic field created at some points along the endoscope can be sensed with hall-sensors which are placed along the endoscope. The direction of the magnetic flux of the alternating magnetic field is therefore an indicator of endoscopes bending behavior. Learning-based methods shall be leveraged and compared to classical estimation methods. To enable easy integration of the developed code in the existing MSRL magnetic steering system, the estimator shall be integrated in the ROS framework. To enhance shape estimation, a powerful sensor fusion of the existing and the new localization system can be optionally implemented.
Claas Ehmke (cehmke@ethz.ch),
Dr. Quentin Boehler (qboehler@ethz.ch),
Alexandre Mesot (amesot@ethz.ch)
Claas Ehmke (cehmke@ethz.ch), Dr. Quentin Boehler (qboehler@ethz.ch), Alexandre Mesot (amesot@ethz.ch)
MT_Proposal_Shape_Estimation.pdf
