Multi-sensor data fusion of the robotics sensitive skin

For the structure of sensitive skin and the characteristic of real-timely providing environmental information of intelligent robot, an on-line adaptive weighted fusion algorithm based on technology of fault tolerance is presented. The measuring data of sensitive skin board is preprocessed and virtual sensor value of fault-tolerance trait is gained. According to the changes in virtual sensor's variance, the algorithm can adjust the fused virtual sensor's optimal weight by using the adaptive way, and the estimation error is kept as of least mean square. Experimental result shows that the algorithm can deal with the conflict in information from sensors and transact the information from a faulty sensor to ensure the reliability and accuracy of final result.