D–S Evidence Theory and its Application in Robot Information Fusion
Multisensor information fusion is wildly treasured and used in the mobile robot field.This thesis describes D–S evidence theory about photoelectric encoder,laser sensors and CCD camera.Because D-S evidence theory allows the existence of uncertainty, we may obtain the event probability according to experience.As a result,it is easier to promote the application.Therefore robot can do autonomous navigation and obstacle aviodance in unknown non-structure environment safely. If the system increased other sensors in the future perfect process,we can also adopt this approach to integration. The experiment results show that the improved D–S evidence theory can eliminate the noise interference,handle signals smoothly and improve the system control precision.