Robotic sensing and perception as the AI frontier of the I&M

The authors report on the perception/action hierarchy of an intelligent robot system. World models provide a common abstraction representation of multisensor information. At the perception level, the world model is analyzed to infer relationships between different objects and to assess the consequences of system's actions. Two types of sensors are employed: proprioceptors for measurement of internal robot parameters and exteroceptors for the measurement of environmental parameters. Multiple sensors provide redundant and complementary information about the behavior of the system and its environment. It is proved that the use of additional sensors can only improve perception performance.<<ETX>>