Abstract: For the kidnapped robot problem in which most current SLAM(simultaneous localization and map building) approaches are invalid,a new solution based on the matching of local sub-graphs is proposed.The presented approach improves the architecture of current SLAM problems,provides a new feature association algorithm based on optimized vertex matching,and introduces a singular value decomposition method into robot localization.In the end,the presented approach and the EKF(extended Kalman filtering) approach are compared in structured environment,and the discussion are made in the term of the feasibility and the effectiveness of this approach based on local sub-graph matching method for the kidnapped robot problem in structured environment.