Sensors in Intelligent Space
By intelligent space (IS) we understand environments with embedded systems, information and communication technologies that create an interactive environment. The purpose of intelligent space is to combine computational technologies to ease or enhance the activities that take place in them.
by Jakub
This requires a combination of sensors and actuators. In the context of robotics actuators are provided by a robot or robots while the space itself provides them with additional information from the sensors embedded in the environment that would otherwise be difficult or impossible to obtain.
Cameras
Since vision is one of our primary senses, understanding and working with visual data is very intuitive for us. Therefore even intelligent spaces that do not rely primarily on vision tend to use it to some degree. In the case that an intelligent space does primarily utilize vision a wide variety of information can be collected from vision alone.
One such example is the intelligent space described in Intelligent Space for Human Centered Robotics.
Intelligent devices are distributed throughout the whole of the space. These intelligent devices have sensing, processing and networking functions, and are referred to as distributed intelligent networked devices (DINDs). One DIND consists of a CCD camera for acquiring space information, and a processing computer which has the functions of data processing and network interfacing. These devices observe the positions and behavior of both humans and robots coexisting in the intelligent space forming a multiple camera multiple object tracking system.
Spatial sensors
By spatial sensors we generally understand active sensors such as laser range-finder or Kinect sensors. Their advantage over cameras is that they automatically acquire spatial depth information without having to use complicated image processing algorithms.
Such example is described in Acting in Intelligent Space. Here distributed laser range finders were used to map the environment.
The acquired information was then processed clustering and data association algorithms and further with Kalman filter to track objects and people in the intelligent space. This way a robot was able to path its way between the obstacles towards a human user.
RFID
Radio-frequency identification (RFID) uses electromagnetic fields to automatically identify and track special tags. Such system consists of an active sensor (reader) and a passive chip (tag).
In Building an Intelligent Home Space for Service Robot RFID tags were distributed across the intelligent space. By reading these tags a robot was able to determine its position in intelligent space.
Other sensors
Although previously mentioned sensors tend to be more common, there are no restrictions on what kinds of sensors an intelligent space can use.
For example chapter five of Human Robot Interaction in Social Robotics describes the use of floor sensors to track multiple people in a crowd. Combined with the aforementioned RFID technology, movements of specific people could be tracked.
Conclusion
There are no set when deciding what sort of sensors should an intelligent space utilize. Specific technologies should be chosen based on the location and intended function of the intelligent space.
Jakub Hvizdoš
