Research on Path Planning Strategy of Driverless Cars Based on SLAM Data

Unmanned vehicles have great development potential. Path planning is the key, and the continuous progress of SLAM technology can provide accurate environmental perception and map construction. However, existing research has deficiencies in aspects such as adaptability to complex environments, multi-objective optimization, and the effectiveness of data fusion, which prompts the research on path-planning strategies for unmanned vehicles based on SLAM data. The study found that the fusion of SLAM technology can better handle the uncertainties and noise in map data in unmanned vehicles, ensuring that the A* algorithm can still plan a reliable path under imprecise environmental information. Simulation results show that in unmanned vehicle path planning, different scenes demand distinct search neighborhoods. For simple scenes, a smaller search neighborhood reduces the computational burden and enables quick path generation. In complex scenes, expanding the search neighborhood can increase the success rate of finding an optimal path. However, it is necessary to carefully control the computational load to guarantee efficient path planning.