Path planning for unpiloted vehicles often encounters route-fitting errors caused by the misidentification of obstacle targets.By designing the real-time recognition of obstacle targets based on the Swin Transformer network,combined with the path fitting algorithm based on the RRT*algorithm and Bessel curves,we design an unpiloted path planning based on the Swin Transformer.Use video frames as the data source and construct an obstacle image dataset by using data enhancement.Experimental results indicate that the proposed algorithm achieves superior performance across multiple metrics compared to baseline methods,demonstrating enhanced robustness in path planning for unpiloted vehicles.
万方数据
