To tackle the complexity of robotic multiple sensor fusion asuitable system structure is urgently required. Most structures atpresent have a fusion center to deal with information from varioussensors located at different points, but unfortunately have no necessaryconnections between low-level sensors. Consequently the fusion centerhas more responsibility for communication and signal interpretation,which causes bottle-neck problem. Moreover sensors cannot help eachother to improve the task environment recognition efficiency. Toovercome the above drawbacks we define the concept of smart sensor atfirst. Each smart sensor should have five abilities, that is prediction,planning, updating, communication and assimilation. Then we discuss thealgorithm of a perception system which consists of several smartsensors. At last we take two application case study as examples toillustrate our new idea
展开▼