6.3.4 Improvement of Inertial Object Tracking for Low-cost Indoor-navigation with Advanced Algorithms

To improve the performance of INS, the Competence Center for Applied Sensor Systems (CCASS) has successfully designed a low-cost INS with 6 accelerometers and 6 gyroscopes. The accuracy of this object-tracking system has been dramatically improved by Shaping-filter and Sensor-error model. According to the application of this navigation system, a pattern recognition algorithm will be developed to improve the stability and accuracy of the INS. This recognition algorithm is based on the Bayesian decision method, because it is a parametric technique with benefits of simplicity. Our developing application has finite start and stop points. In other words, the pattern of the movement might possibly be recognized with pattern recognition algorithms. Then, the position will be estimated based on the result of the developing pattern recognition module and the navigation module compensated with the error module. Moreover, this pattern recognition module might be successfully integrated with the error module, which is based on Kalmanfiltering. It might possible to use the result from the pattern recognition as a reference signal, as well as the reset point of the INS system.