No abstract

Motivation-The use of a Home Care Robot combined with a sensor network could possibly improve or replace current home Tele-healthcare systems that monitor elderly people or other people with health problems. Using robot for this is a new and we want to find out what the advantages or disadvantages could be. Research approach-By using non-invasive wireless sensors the health of the person can be monitored. In case of a possible problem, like when the person has fallen, a robot can autonomously go to the person and ask or check whether help from care-providers would be needed. This check could avoid many false alarms. The robot can call a care-provider by itself. The control of the robot can also be taken over by a care-provider to enable telepresence. By communicating with the person though the robot and seeing through the camera of the robot, the care-provider can then better evaluate the situation and help remotely or send help directly. Findings/Design-The sensors, the robot and the interaction will be designed and evaluated by doing user-tests. Privacy-issues will be investigated too. Take away message-The use of such a Home Care Robot can be very cost-effective because it enables people to live longer in their own home, it can prevent many false alarms for the care-provider and compared to systems that need cameras everywhere it can offer more privacy.

Relative entropy and the principle of minimum relative entropy are proposed as fundamental concepts that can be used as a foundation for designing and building adaptive, generally intelligent agents that build a model of the world. An equation is derived that describes how such an agent can build a model of the world by minimizing relative entropies. With this equation we prove that the agent then continually improves its model of the world. A main advantage of this equation and the derivation is that it clarifies and shows the relation between different uses and interpretations of relative entropy, such as measures of dissimilarity, learning progress or surprise, minimization and maximization of relative entropies for minimal belief updates and how it can select actions that lead to exploratory and curious behavior. As an example we applied our equation and approach to play the game of Mastermind.