Jüri Vain

Scrub nurse robot system-intraoperative motion analysis of a scrub nurse and timed-automata-based model for surgery

The goal of the project described in this paper is to develop a human-adaptive Scrub Nurse Robot (SNR) that can adapt to surgeons with various levels of skill and experience in order to compensate for the present severe shortage of scrub nurses. To determine the specifications of the SNR, we analyzed real intraoperative behavior of a scrub nurse, and then modeled the entire surgical procedure with key participants by a multilevel modeling approach using the extended timed-automata-based formalism of Uppaal. Specifically, first, we videotaped the intraoperative motions of a scrub nurse and a surgeon in a thoracoscopic surgery performed on an infant pig, and analyzed their motions during the skin incision. Second, the motions of the nurses right wrist, elbow, and shoulder were modeled with the timed automata. Third, the entire surgical procedure as well as actions and statuses of key participants was also modeled. Finally, it is shown that the proposed multilevel modeling approach also facilitates the model checking that is considered efficient in the SNR motion analysis and its adaptive motion planning.

Recognition of the Surgeon's Motions During Endoscopic Operation by Statistics Based Algorithm and Neural Networks Based ANARX Models

Abstract The problem of recognition and short time prediction of the surgeons hand motions during surgical endoscopic operation are approached in the present contribution using neural network based nonlinear modeling techniques and statistics based segmentation of the operating room. It is shown that proposed technique provide precise recognition of surgeons motions.

Synthesis of test purpose directed reactive planning tester for nondeterministic systems

We describe a model-based construction of an online tester for black-box testing of the implementation under test(IUT). The external behaviour of the IUT is modelled as an output observable nondeterministic EFSM with the assumption that all transition paths are feasible. A test purpose is attributed to the IUT model by a set of Boolean variables called traps that are used to measure the progress of the test run. These variables are associated with the transitions of the IUT model. The situation where all traps have been reached means that the test purpose has been achieved. We present a way to construct a tester that at runtime selects a suboptimal test path from trap to trap by finding the shortest path to the next unvisited trap. The principles of reactive planning are implemented in the form of the decision rules of selecting the shortest paths at runtime. The decision rules are constructed in advance from the IUT model and the test purpose. Preliminary experimental results confirm that this method clearly out performs random choice and is better than the anti-ant algorithm in terms of resultant test sequence length to achieve the test purpose

Generating tests from EFSM models using guided model checking and iterated search refinement

We present a way to generate test sequences from EFSM models using a guided model checker: Uppaal Cora. The approach allows to specify various structural test coverage criteria of EFSMs, for example, selected states/transitions, all transitions, all transition pairs, etc. We describe a method to construct Uppaal models to achieve test sequences satisfying these criteria and experiment with the search options of Uppaal to achieve test sequences that are suboptimal in terms of length. We apply a bitstate hashing space reduction based iterated search refinement method to shorten the length of test sequences with respect to the length gained using depth first search. The test generation method and different search strategies are compared by applying them on a stopwatch and INRES protocol based case study. The outcome shows the feasibility of applying guided model checking in conjunction with iterated search refinement for generating suboptimal test sequences.

RFID-based Communications for a Self-Organising Robot Swarm

We investigate the practical questions of building a self-organizing robot swarm, using the iRobot Roomba cleaning robot as an experimental platform. Our goal is to employ self-organization for enhancing the cleaning efficiency of a Roomba swarm. The implementation uses RFID tags both for object and location-based task recognition as well as graffiti- or stigmata-style communication between robots.Easily modifiable rule systems are used for object ontologies and automatic task generation. Long-term planning and central coordination are avoided.

Application of self organizing Kohonen map to detection of surgeon motions during endoscopic surgery

Segmentation of the surgeonpsilas hand movements during the surgery into more primitive parts and recognition of those parts using Kohonen map is discussed in present paper. Main advantages of the proposed approach are that it allows to take into account dynamical characteristics of the hand movements and exclude probability of human error in building etalon segmentation. Ability to recognize current action of the surgeon has a crucial importance in developing a robot able to assist surgeon during the endoscopic surgical operation. One of the possible ways is to predefine a set of possible surgeonpsilas actions and provide a recognition algorithm explored in the framework of present contribution.

Timed-automata-based model for laparoscopic surgery and intraoperative motion recognition of a surgeon as the interface connecting the surgical scenario and the real operating room

Most computer-assisted surgery systems are an isolated standalone system in the operation room with obtrusive and cumbersome wired connections. Surgery data preparation, registration, segmentation, planning, etc. have to be running at one place. Dynamic data acquisition and cooperation during the surgical procedure is not currently possible. We develop the M-CASEngine system which provides a distributed collaborative environment for computer-assisted surgery. It enables the doctors to access and plan the surgery, and actively participate in remote surgeries, share patient information and exchange opinions in real time from anywhere at any time. By utilizing cutting-edge network technologies, the system greatly improves the overall performance of computer-assisted surgery.Linking top-level ontologies and surgical workflows O. Burgert Æ T. Neumuth Æ F. Lempp Æ R. Mudunuri Æ J. Meixensberger Æ G. Strauß Æ A. Dietz Æ P. Jannin Æ H.U. Lemke Innovation Center Computer Assisted Surgery (ICCAS), Leipzig, Germany University Hospital Leipzig, Department of Neurosurgery, Germany University Hospital Leipzig, ENT-Department/Plastic Surgery, Germany University of Rennes, Visages-U746 INSERM, INRIA, France Abstract Surgical Workflows describe the course of surgical interventions Since they are an abstraction from reality one needs unambiguous description of the single items and actions – concepts and relationships – involved in the surgical intervention. Furthermore, for computer aided analysis of surgical workflows, abstractions and relations are needed. These should be comparable between different workflows and surgical disciplines. An ontology can provide an abstract view of the world one wants to represent by using an explicit and formal description. This paper introduces an upper-levelontology based on GOL (General Ontological Language) for representing surgical interventions.

Refinement-Based development of timed systems

Refinement-based development supported by Event-B has been extensively used in the domain of embedded and distributed systems design. For these domains timing analysis is of great importance. However, in its present form, Event-B does not have a built-in notion of time. The theory of refinement of timed transition systems has been studied, but a refinement-based design flow of these systems is weakly supported by industrial strength tools. In this paper, we focus on the refinement relation in the class of Uppaal Timed Automata and show how this relation is interrelated with the data refinement relation in Event-B. Using this interrelation we present a way how the Event-B and Uppaal tools can complement each other in a refinement-based design flow. The approach is demonstrated on a fragment of an industrial case study.

Verifying Response Times in Networked Automation Systems Using Jitter Bounds

Networked Automation Systems (NAS) have to meet stringent response time during operation. Verifying response time of automation is an important step during design phase before deployment. Timing discrepancies due to hardware, software and communication components of NAS affect the response time. This investigation uses model templates for verifying the response time in NAS. First, jitter bounds model the timing fluctuations of NAS components. These jitter bounds are the inputs to model templates that are formal models of timing fluctuations. The model templates are atomic action patterns composed of three composition operators-sequential, alternative, and parallel and embedded in time wrapper that specifies clock driven activation conditions. Model templates in conjunction with formal model of technical process offer an easier way to verify the response time. The investigation demonstrates the proposed verification method using an industrial steam boiler with typical NAS components in plant floor.

Hybrid approach to detection of the surgeon's hand motions during endoscope surgery

Present paper explores possibilities to apply hybrid recognition technique to detect different types of surgeonss write hand motions during endoscope surgery. Proposed technique uses finite time automata which switches between three different detection techniques; neural networks based detection, statistical based method and Kohonen-map based technique. Such approach allows to avoid errors peculiar to certain technique.