Melvin Isken

Criteria for Quality and Safety while Performing Unobtrusive Domestic Mobility Assessments Using Mobile Service Robots

A new concept for safely performing and qualitatively evaluating assessments in domestic unsupervised environments, especially when utilizing mobile service robots, is presented. The presented approach is based on the idea that classical geriatric assessments, especially from the domain of mobility, may be divided in components which happen naturally throughout the day in domestic environments. Those components are measured separately and are recombined to com-plete assessment tests later on. In order for physicians to decide how reliable assessment results from the domestic do-main are, we define technical quality criteria for the components of the Timed Up&Go assessment test. The approach is evaluated within an experiment in a living lab utilizing sensors, especially a laser range scanner, equipped with a mobile robot. Results show that the presented approach may be used to separate sensor measurements promising good assess-ment results from those containing insufficient data. Additionally, using mobile robots to perform assessments in domestic environments holds the potential danger for the inhabitant to stumble over the robot. Therefore, the paper also evaluates the aspect of inhabitants’ safety during domestic assessments based on the experiment’s data. A novel approach to navigate safely using the previously presented approach of optimal observation lots (OOL) is presented.

Towards Pervasive Mobility Assessments in Clinical and Domestic Environments

This paper provides an overview of current research and open problems in sensor-based mobility analysis. It is focused on geriatric assessment tests and the idea to provide easier and more objective results by using sensor technologies. A lot of research has been done in the field of measuring personal movement/mobility by technical approaches but there are few developments to measure a complete geriatric assessment test. Such automated tests can very likely offer more accurate, reliable and objective results than currently used methods. Additionally, those tests may reduce costs in public health systems as well as set standards for comparability of the tests. New sensor technologies and initiatives for data standardization in health processes offer increased possibilities in system development. This paper will highlight some open problems that still exist to bring automated mobility assessment tests into pervasive clinical and domestic use.

Working with a domestic assessment system to estimate the need of support and care of elderly and disabled persons: results from field studies

This article describes the results of field studies performed over a period between five months and 24 months. The objectives of these studies were to collect long-term real-life data to evaluate how these data can be mapped to items on standardized assessment tests and which presentation method is most suitable to inform caregivers about critical situations and changes in health or care needs. A Home-monitoring system which uses modern sensor technologies was developed for and used in these field studies. It was installed in living environments of seven people (three who were not in need of care, two in need of care, and two with mental disabilities). The data were generated by sensor data acquisition and questionnaire reporting. Four types of data analysis and representation were evaluated to support caregivers. Results show that sensor data can be used to determine information directly or indirectly, which can be mapped to relevant assessment items and presented with different degrees of granularity. It is also feasible to determine and present additional information of potential interest which cannot be directly mapped to any assessment item. Sensor data can also be displayed in a live view. This live data representation led to a decrease in the caregivers’ workload when assessed according to the German version of the Perceived Stress Questionnaire.

Enhancing Mobile Robots’ Navigation through Mobility Assessments in Domestic Environments

A new concept to enhance mobile robot navigation in domestic environments by the use of mobility assessment data is presented. The concept is part of our overall approach to enabling more precise and reliable mobility assessment by the use of a mobile monitoring platform i.e. a mobile service robot equipped with a laser range scanner. We are basing our new approach on our previous work on the application of the potential field method to mobility trend analysis and the precise measurements of human movement trajectories by a laser range scanner. The enhancements to the robot’s navigation enable more precise assessment results while ensuring to not hinder or endanger the human. While navigating the robot moves from one to another observation location and tries to avoid the user’s movement paths whenever possible. Additionally, it adapts its own driving speed to the human’s. We call these secure observation locations which provide better assessment results Optimal Observation Lots (OOL). The concept’s algorithm, which was only implemented partially yet, contributes to our ultimate goal to develop an ’‘off the shelf” robot that is placed in the user’s home and is able to find its own observation spots and movement paths without further pre-programmed knowledge of the environment.

Mobile Robot Platform to track User Movement and Behaviour

This document describes a currently developed robotic system that tracks and analyses human gait parameters. This system is used to conduct mobility assessments to track the user’s health status. Mobility assessments conducted by a mobile robot provide significant advantages over current methodologies. Additionally, the robot navigation capabilities can be enhanced by the use of mobility assessment data. Parts of the overall concept are evaluated by the evAAL competition 2013, Track 1, Indoor Localization and Tracking.

Gesture Controlled Hospital Beds for Home Care

This article introduces a gesture-based user interface for hospital beds. This interface enables caregivers to focus on their patients and have both hands available for mobilizing and transferring them. Gestures are detected either via static (96% sensitivity) or dynamic gestures (67.5% sensitivity) and might be corrected by an extra repetition. Once gestures are correctly detected, caregivers can trigger bed movements via a foot switch as a hands-free operation, which as well functions as a dead man button. The evaluation of the usability through interviews with caregivers highlighted the system’s general applicability, but as well some future challenges that have to be solved in order to achieve a system for every-day use.

Continuous Geriatric Assessments Supported by a Mobile Service Robot: Movement Analysis

This document describes a method to measure geriatric assessment data by using a mobile robotic platform that is able to track and analyze human motion parameters. The information gathered by this system can be used to assess the user’s health status. Geriatric mobility assessments conducted by a mobile robot provide significant advantages over current methodologies. For example, sensor data can be used to track multiple assessments at once. Additionally, the robot navigation capabilities can be enhanced by the use of geriatric assessment data. This paper concentrates on the movement analysis aspect of the whole system due to the limited space.

Housing Enabling: Detection of Imminent Risk Areas in Domestic Environments Using Mobile Service Robots

Because of the greying society the need of user centred care concepts are raising. One big wish of older persons is to stay as long as possible in their own flat. Depending on the demographic change it won’t be possible to realize complete care by formal or informal caregivers especially for people living alone. One possible way to cope this problem is to use ICT based solutions e.g. mobile service robots. The personal in-house mobility and its preservation it is one goal to enable staying as long as possible in her/his own flat. The concept of an automated housing enabling assessment which is presented here is an advanced solution for this problem. It is based on three main components: (1) Measurement and analysis of the cognitive and physical capabilities of the user, (2) Measurement and validation of the flat and (3) Computation of areas with a higher risk to fall and advice to remove such issues, e.g. restructuring of the furniture. The great benefit of a mobile robot platform is that all needed sensors are mounted on the robot and it can follow the user to make measurements at different places in the home. This will reduce the cost and installation effort in the flat to a minimum. Another benefit is the continuous assessment which helps to restructure the flat in a continuous way. This helps to reduce the probability of a fall event and raise the feeling of safety. All measurements could also be used by other assessment tools to preserve the indoor mobility not only by preventing a fall event but also by reacting on changes in the mobility level over time.

Multisensor Soft Tissue Navigation for the Controlled Guidance in Intra-Cardiac Microsurgery

This paper describes the concept of a new kind of soft-tissue navigation system for minimally invasive intracardiac micro surgery like valve resection. Via a specialized trocar all instruments and a valve isolation chamber system [1] are inserted to generate a separate operation space around the valve. The instruments are at least a novel shape memory alloy actuated laser fibre and two endoscopic optic fibres. Via the endoscopic optic fibres a stereoscopic view on the operation field is provided while the laser is used for resection of a calcified valve. The guidance of the laser is controlled by the navigation system on basis of a three dimensional virtual model. The model is build out of preoperative taken static CT images merged with intra-operative taken ultrasonic images and the stereoscopic images generated from the endoscopic optic fibres. With the virtual model the intervention will be supported by visualization of the operation field on the one hand and control of the guidance of the laser actor on the other hand. Thus the system provides an undisturbed view to the operating field without limiting factors like bodily fluids and the small aditus of minimally invasive surgery. The guidance of the surgical instruments is easier and the intervention faster and safer for the patient.