Background

The COVID-19 pandemic and the measures it entails such as social distancing exacerbate the situation of people living alone. Emergency situations may go unnoticed (e.g., falls) and this can have life-threatening consequences. As people are less often in personal contact with their beloved ones, they are more concerned about whether everything is all right with their relatives and friends. Emergency call systems for home use could be helpful in such cases, but they have their drawbacks. For instance, people usually need to actively make contact (not possible when passing out); in addition, the use of such systems is associated with a social stigma.

Project Content

The previous project Smart Companion 1 (SC2) was aimed at overcoming the drawbacks of conventional emergency call systems and alleviating the concerns that are associated with their usage. The main idea was not to build a stand-alone device but to integrate features such as bidirectional voice assistance into devices already in use (in particular vacuum cleaning robots). SC2 builds on this and focuses on user acceptance/user experience, on technical solutions for fall prevention and on other safety features. Overall, the system shall be able to trigger an emergency call chain for relatives and emergency call centres. This strengthens (and does not undermine) autonomy and gives relatives and friends reassurance that help is at hand in cases of emergency. Project results will also lay the foundation for a new generation of personal emergency response systems (PERS), which are urgently needed by emergency call centre providers (e.g.,project partner ASB).

Goals

Based on the insights gain in the previous project, we create a prototype and test whether it meets our expectations in a controlled home lab environment. The main focus of the current project is on key components of fall detection and systems that autonomously can call for help. This includes  

• an active emergency call (i.e., user calls for help),
• appropriate reactions to unusual events (i.e., user does not react and the device autonomously detects the emergency), and
• fall prevention (i.e., the device warns users of potential obstacles).

We place the needs of the future users at the centre of our investigations, implement voice interaction systems as they are the most inclusive way of communicating, use machine learning for emergency detection and attach great importance to privacy, usability and convenience.

Methods

We pursue a “Human Centered Design” (HCD) process, where the users’ needs and experiences are of pivotal importance. “Care ethics” is a second defining concept of the SC2 project. It emphasizes the necessity to design inventions and applications in a way that “promotes the well-being and flourishing of all, based on the knowledge and responses of the one cared for”. The novel "Ethics by Design" process is an additional pillar of the project, meaning that users actively participate in all development steps, starting from the first mock- ups to definition of user interfaces. Questions such as what data needs to be recorded and analysed and how privacy and security can be guaranteed are answered during this process.

The technological part of the project includes intelligent personal assistants (IPAs), machine learning and modern sensor technology. IPAs  combine automatic speech recognition and speech analysis with the synthesis of natural-language answers through deep learning. They are easy to use and well accepted by the elderly because they allow to control complex systems via a humanlike way of communication. We also make use of ambient sensors and camera based system and apply advanced machine learning algorithms for image processing. Because vacuum cleaning robots are highly available at reasonable prices and equipped with advanced sensors like cameras or laser systems (LIDAR) for distance measuring they are a perfect choice for equipping them with an emergency call system.

Results

The technological leap of Smart Companion lies in the combination of several intelligent services. Integrating data from different sources (i.e., sensors and actuators) breaks new grounds in human-machine interaction and paves the way for a new generation of personal assistance systems. The partners involved in the project benefit from its outcomes in many ways. St. Pölten UAS leads the European University Initiative E³UDRES² with several partner universities and sees Smart Companion as an important milestone for further international research on this topic. The Bosch AG strengthens its position as a European manufacturer of robot vacuum cleaners and smart home systems. The Akademie für Altersforschung am Haus der Barmherzigkeit is receives first-hand experience with assistance systems and provides valuable support in achieving high user-acceptance and high ethical standards. Arbeiter-Samariter-Bund Group Linz as a provider of Personal Emergency Response Systems urgently needs devices for passive fall detection, because such systems are currently not available on the market.

Funded by the „ICT of the future“ programme initiated by the  Federal Ministry for Climate Action, Environment, Energy, Mobility, Innovation and Technology (BMK)