From topological map to local cognitive map: a new opportunity of local path planning

To solve the consistency problem in local path planning, the traditional definition of topological maps is extended in this paper, by introducing a new concept of local cognitive maps (LCMs). Principal structures of a local environment including all possible routes, key obstacles, and mutual relationships among them are incorporated. Based on the LCMs, the consistency of local path planning can be guaranteed, by keeping the relationship between the chosen route and key obstacles in sequential planning cycles as consistent as possible. To generate the LCMs, an iterative decomposition method is designed . Furthermore, to evaluate candidate routes in the LCMs, the model predictive control (MPC) based on a vehicle-road evaluation method and vehicle dynamics is incorporated. The optimal route is chosen based on the MPC simulation results with criterions, such as the spending time and route width. The final path for vehicles to follow is also achieved with the simulation results. To verify the performance of the proposed method, experiments in various kinds of environments were carried out. Experimental results illustrate the effectiveness and advantages of the proposed method.