Moving Object Detecting and Tracking with Mobile Robot Based on Extended Kalman Filter in Unknown Environment

In order to solve the problem of moving object tracking in unknown environment, an algorithm based on extended Kalman filter is proposed. The states of robot, landmark and object are used to form whole system state, such that the covariance between different object state become more and more intensive in process of iteration, so improves accuracy of object state estimation. For practical application, a method of moving object detection based on occupy grid map is combined with our algorithm to obtain the measurements of moving object and environment landmarks. Moreover, the using of data verification step gives system more ability to tackle problem of disturbance sourced from false object observations. Real robot experiment and simulation results prove the effectiveness and accuracy of presented approach.