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.
快速扩展随机树(Rapidly-exploring Random Trees, RRT)算法是一种基于采样的方法,旨在快速的找到一条从起点到终点的拟合路线;RRT*算法是对RRT算法的改进,伪代码如算法1所示。该算法首先选择无人驾驶车辆的初始位置为,将其作为根节点构建一棵搜索树,然后在空间进行采样获得,并利用欧氏距离在随机树上寻找距离最近的节点,以扩展得到新节点,该过程是RRT*算法中最为重要的部分,具体如算法第三行所示,该过程得到的结果将作为后续操作的基础,另外如果在这个过程中没有发生碰撞,则重新规划直到找到使得代价值最小的点,并添加到随机树上;将上述过程不断进行迭代运行,进而优化路径。RRT*算法主要解决了RRT算法在求解最优路径上随着搜索空间维数增加而导致的计算复杂度急剧增加的问题。
LOWED G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110. DOI: 10.1023/B: VISI.0000029664.99615.94 .
[2]
RENS Q, HEK M, GIRSHICKR, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. DOI: 10.1109/TPAMI.2016.2577031 .
SHAOY H, ZHANGD, CHUH Y, et al. A review of YOLO object detection based on deep learning[J]. Journal of Electronics & Information Technology, 2022, 44(10): 3697-3708. DOI: 10.11999/JEIT210790(Ch ).
[5]
ZHENGW, TANGW L, CHENS J, et al. CIA-SSD: Confident IoU-aware single-stage object detector from point cloud[EB/OL]. [2021-05-18]. DOI: 10.48550/arXiv.2012.03015 .
[6]
WANGC Y, BOCHKOVSKIYA, LIAOH Y M. Scaled-YOLOv4: Scaling cross stage partial network[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE Press, 2021: 13024-13033. DOI: 10.1109/CVPR46437.2021.01283 .
[7]
RAOJ, QIANT, QIS H, et al. Student can also be a good teacher: Extracting knowledge from vision-and-language model for cross-modal retrieval[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management. New York: ACM, 2021: 3383-3387. DOI: 10.1145/3459637.3482194 .
[8]
HANK, WANGY H, CHENH T, et al. A survey on vision transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 87-110. DOI: 10.1109/TPAMI.2022.3152247 .
[9]
LIUZ, LINY T, CAOY, et al. Swin transformer: Hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). New York: IEEE Press, 2022: 9992-10002. DOI: 10.1109/ICCV48922.2021.00986 .
[10]
ZHANGZ B, AIC S, LIS, et al. Path planning and tracking control method based on Bessel curve[C]//2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM). New York: IEEE Press, 2023: 511-514. DOI: 10.1109/WCMEIM56910.2022.10021359 .
[11]
CHENX, ZHAOM Y, YINL Y. Dynamic path planning of the UAV avoiding static and moving obstacles[J]. Journal of Intelligent & Robotic Systems, 2020, 99(3): 909-931. DOI: 10.1007/s10846-020-01151-x .
[12]
GEQ Y, LIA J, LIS H, et al. Improved bidirectional RRT* path planning method for smart vehicle[J]. Mathematical Problems in Engineering, 2021: 1-14. DOI: 10.1155/2021/6669728 .
[13]
WUY, WUS B, HUX T. Cooperative path planning of UAVs & UGVs for a persistent surveillance task in urban environments[J]. IEEE Internet of Things Journal, 2021, 8(6): 4906-4919. DOI: 10.1109/JIOT.2020.3030240 .
[14]
CHIW Z, DINGZ Y, WANGJ K, et al. A generalized voronoi diagram-based efficient heuristic path planning method for RRTs in mobile robots[J]. IEEE Transactions on Industrial Electronics, 2022, 69(5): 4926-4937. DOI: 10.1109/TIE.2021.3078390 .
[15]
YANGH X, XUX M, HONGJ C. Automatic parking path planning of tracked vehicle based on improved A* and DWA algorithms[J]. IEEE Transactions on Transportation Electrification, 2023, 9(1): 283-292. DOI: 10.1109/TTE.2022.3199255 .