
Tom KollerUniversity of Bremen | Uni Bremen · Faculty 03: Mathematics/Computer Science
Tom Koller
Doctor of Engineering
About
12
Publications
1,413
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
30
Citations
Introduction
My current research is about mathematical modelling, simulation and deep learning for medical diagnosis and intervention.
Additional affiliations
July 2018 - present
Education
October 2012 - June 2018
Publications
Publications (12)
Recent studies indicate that malignant breast lesions can be predicted from structural changes in prior exams of preventive breast MRI examinations. Due to non-rigid deformation between studies, spatial correspondences between structures in two consecutive studies are lost. Thus, deformable image registration can contribute to predicting individual...
Surgical Navigation Systems have significantly enhanced surgical procedures by enabling computer-aided position tracking of medical instruments and the patient’s body. Optical Tracking Systems (OTS) have emerged as the leading technology, relying on infrared retroreflective markers for instrument recognition. However, lineof-sight issues, caused by...
State estimation can significantly benefit from prior
knowledge about a system’s dynamics and state. In this paper,
we investigate a special class of prior knowledge: Events that
correspond to a subset of the state space. This class of knowledge
was introduced in pedestrian activity classification to improve
the position estimation. We argue that t...
For some years, inertial sensors have become increasingly popular in various sports applications due to their small size and weight. However–due to the problem of sensor drift–additional sensors are usually required to obtain reliable position estimates. In this paper, we present an approach for position estimation in bouldering that relies solely...
Hybrid systems are subject to multiple dynamic models, or so-called modes. To estimate
the state, the sequence of modes has to be estimated, which results in an exponential growth of possible sequences. The most prominent solution to handle this is the interacting multiple model filter, which can be extended to smoothing. In this paper, we derive a...
The interacting multiple model filter is the standard in state estimation where different dynamic models are required to model the behavior of a system. It performs a probabilistic mixing of estimates. Up to now, it is undefined how to perform this mixing properly on manifold spaces, e.g. quaternions. We present the proper probabilistic mixing on d...
Control, tracking, and obstacle detection algorithms for mobile robots, including autonomous cars, rely on a jump-free estimate of the vehicle's pose. While one cannot completely avoid jumps in global solutions like INS/GNSS and SLAM, relative localization (i.e., odometry) does not suffer from this problem. Methods based on graph optimization are p...
Inertial navigation systems suffer from unbounded errors in the position and orientation estimates. This drift can be corrected by applying prior knowledge, instead of using exteroceptive sensors. We want to show that the use of prior knowledge can yield full observability of the position and orientation. A previous study showed that track cyclers...
Inertial Navigation Systems suffer from unbounded errors on the position and orientation estimate. This drift can be corrected by applying prior knowledge, instead of using exteroceptive sensors. Analysing the state observability induced by prior knowledge motivates us to track bikers in track cycling races. In this paper, we show that the pose of...
Inertial Navigation Systems suffer from unbounded errors on the position and orientation estimate. Extero-
ceptive sensors may not always be available to correct the error. Applications in the literature overcome this
problem by fusing IMU data with prior knowledge in an ad-hoc fashion. In different applications, various
knowledge is available, whi...
Assistive robotic manipulators have the potential to support individuals with severe motor impairments at performing activities of daily life. With the help of robotic manipulators, the individuals may eat and drink independently of caregivers. The presented research work focuses on interactive drinking with a cup without a straw. The interaction e...
Questions
Question (1)
In some estimation tasks the precision can be increased by applying different models. E.g. it is known that airplanes can be tracked more precisely when different models for different maneuvers as flying straight or curves are used. Usually, something like the interacting multiple model filter (IMM) is used.
In the case of a single model the "online" algorithm is the Extended Kalman Filter. If the data can be processed offline a bundle adjuster/batch estimator/least square optimizer as ceres can be used which yields better results since it adjusts the complete dataset at once. It can handle the nonlinearities better.
Is there any algorithm which does the same for multiple model problems ? Something like a gold standard which should almost always yield the best results ?