Heuristic sampling path planning algorithm based on semantic segmentation

doi:10.3785/j.issn.1008-973X.2025.10.016

Journal of ZheJiang University (Engineering Science)

2025, Vol. 59

Issue (10): 2154-2163 DOI: 10.3785/j.issn.1008-973X.2025.10.016

Heuristic sampling path planning algorithm based on semantic segmentation

Jiawei PAN(

),Chunli WANG,Xiujuan ZHENG,Haiyan TU*(

)

College of Electrical Engineering, Sichuan University, Chengdu 610065, China

Download:

HTML

PDF(2243KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

A new path planning algorithm was proposed to address the limitations of the conventional rapidly-exploring random trees (RRT) path planning algorithm, including excessive redundant sampling points, increased randomness, and lack of smooth paths. A model named the optimal path area prediction network (OPAPN) was developed to predict potential optimal path areas within the map using deep learning techniques. A global feature extraction module, a hybrid attention mechanism, and switchable atrous convolution techniques were incorporated in the model. The network’s understanding of the map’s overall layout and start/goal information was enhanced by the components to reduce unnecessary computational burdens. The number of sampling points was reduced significantly through heuristic sampling in the optimal path regions predicted by OPAPN, and the algorithm’s convergence speed was accelerated via a dual-tree expansion strategy. Both simulation experiments and real-world tests showed that the proposed algorithm performed well in convergence time, node count, and path length, confirming its practical application value.

Key words： mobile robot path planning rapidly-exploring random trees (RRT) deep learning semantic segmentation attention mechanism

Received: 09 October 2024 Published: 27 October 2025

CLC:

TP 242

Fund: 四川省科技计划资助项目（2022YFS0032）.

Corresponding Authors: Haiyan TU E-mail: panjiawei@stu.scu.edu.cn;haiyantu@scu.edu.cn

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Jiawei PAN
	Chunli WANG
	Xiujuan ZHENG
	Haiyan TU

Cite this article:

Jiawei PAN,Chunli WANG,Xiujuan ZHENG,Haiyan TU. Heuristic sampling path planning algorithm based on semantic segmentation. Journal of ZheJiang University (Engineering Science), 2025, 59(10): 2154-2163.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2025.10.016 OR https://www.zjujournals.com/eng/Y2025/V59/I10/2154

基于语义分割的启发式采样路径规划算法

经典快速探索随机树（RRT）路径规划算法存在冗余采样点多、随机性强、路径不平滑等不足，为此提出新的路径规划算法. 设计最优路径区域预测网络模型（OPAPN），利用深度学习方法预测地图中的潜在最优路径区域. 整合全局特征提取模块、融合注意力机制以及可切换空洞卷积技术，提升网络对整体地图布局和起点/终点信息的理解，有效降低计算开销. 通过在OPAPN预测出的最优路径区域实施启发式采样来大幅减少采样点数量，采用双树扩展策略来加速算法的收敛速度. 仿真实验及真实环境测试表明，所提算法在收敛时间、节点数量和路径长度方面的性能表现良好，具有实际应用价值.

关键词： 移动机器人, 路径规划, 快速探索随机树(RRT), 深度学习, 语义分割, 注意力机制

Fig.1 Architecture of optimal path area prediction network model

Fig.2 Structure of global feature extraction module

Fig.3 Structure of coordinate attention

Fig.4 Structure of criss-cross attention

Fig.5 Structure of hybrid attention mechanism

Fig.6 Structure of switchable atrous convolution techniques

Fig.7 Node generation process of rapidly-exploring random tree path planning algorithm

Fig.8 Discretization process for optimal path region map

Fig.9 Illustration of path optimization process

Fig.10 Images from dataset used for training optimal path area prediction network model

Fig.11 Illustration of predicted region connectivity evaluation

Fig.12 Test set prediction results of optimal path area prediction network model

Tab.1 Results of module ablation experiments for optimal path area prediction network model

Fig.13 Path planning results comparison of different algorithms on four map

Tab.2 Comparison of path planning porformance parameters of different algorithms (simulation environment testing)

Fig.14 Test environment for mobile robot

Fig.15 Path planning results comparison of different algorithms in real-world environment testing

Tab.3 Comparison of path planning performance parameters of different algorithms (real-world environment testing)


[1]	DONG L, HE Z, SONG C, et al A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures[J]. Journal of Systems Engineering and Electronics, 2023, 34 (2): 439- 459 doi: 10.23919/JSEE.2023.000051

[2]	赵学健, 叶昊, 贾伟, 等 AGV路径规划及避障算法研究综述[J]. 小型微型计算机系统, 2024, 45 (3): 529- 541 ZHAO Xuejian, YE Hao, JIA Wei, et al Survey on AGV path planning and obstacle avoidance algorithms[J]. Journal of Chinese Computer Systems, 2024, 45 (3): 529- 541

[3]	SUNDARRAJ S, REDDY R V K, BASAM M B, et al Route planning for an autonomous robotic vehicle employing a weight-controlled particle swarm-optimized dijkstra algorithm[J]. IEEE Access, 2023, 11: 92433- 92442 doi: 10.1109/ACCESS.2023.3302698

[4]	LIN Z, WU K, SHEN R, et al An efficient and accurate A-star algorithm for autonomous vehicle path planning[J]. IEEE Transactions on Vehicular Technology, 2024, 73 (6): 9003- 9008 doi: 10.1109/TVT.2023.3348140

[5]	SHAO S, ZHANG J, WANG T, et al Dynamic obstacle-avoidance algorithm for multi-robot flocking based on improved artificial potential field[J]. IEEE Transactions on Consumer Electronics, 2024, 70 (1): 4388- 4399

[6]	WANG L, WANG Z, YING Z, et al A path planning framework based on an improved weighted heuristic RRT and optimization strategy[J]. IEEE Transactions on Intelligent Vehicles, 2023, 9 (1): 1941- 1952

[7]	刘文倩, 单梁, 张伟龙, 等复杂环境下基于改进Informed RRT的无人机路径规划算法[J]. 上海交通大学学报, 2024, 58 (4): 511- 524 LIU Wenqian, SHAN Liang, ZHANG Weilong, et al Unmanned aerial vehicle path planning algorithm based on improved informed RRT in complex environment[J]. Journal of Shanghai Jiao Tong University, 2024, 58 (4): 511- 524

[8]	MENG F, CHEN L, MA H, et al NR-RRT: neural risk-aware near-optimal path planning in uncertain nonconvex environments[J]. IEEE Transactions on Automation Science and Engineering, 2024, 21 (1): 135- 146 doi: 10.1109/TASE.2022.3215562

[9]	ZHANG W, SHAN L, CHANG L, et al SVF-RRT: a stream-based VF-RRT for USVs path planning considering ocean currents[J]. IEEE Robotics and Automation Letters, 2023, 8 (4): 2413- 2420

[10]	巩浩, 谭向全, 李佳欣, 等基于改进RRT算法的移动机器人路径规划研究[J]. 组合机床与自动化加工技术, 2024, (1): 19- 24 GONG Hao, TAN Xiangquan, LI Jiaxin, et al Research on path planning of mobile robot based on improved RRT algorithm[J]. Modular Machine Tool and Automatic Manufacturing Technique, 2024, (1): 19- 24

[11]	KARAMAN S, FRAZZOLI E Sampling-based algorithms for optimal motion planning[J]. International Journal of Robotics Research, 2011, 30 (7): 846- 894 doi: 10.1177/0278364911406761

[12]	龚立雄, 陈佳霖, 黄霄, 等基于改进Informed-RRT算法的舰载机甲板平面路径规划[J]. 科学技术与工程, 2024, 24 (17): 7429- 7437 GONG Lixiong, CHEN Jialin, HUANG Xiao, et al Aircraft deck flat path planning based on improved informed-RRT algorithm[J]. Science Technology and Engineering, 2024, 24 (17): 7429- 7437

[13]	SUN Z, LEI B, XIE P, et al Multi-risk-RRT: an efficient motion planning algorithm for robotic autonomous luggage trolley collection at airports[J]. IEEE Transactions on Intelligent Vehicles, 2024, 9 (2): 3450- 3463 doi: 10.1109/TIV.2023.3349171

[14]	李昭莹, 欧一鸣, 石若凌基于深度Q网络的改进RRT路径规划算法[J]. 空天防御, 2021, 4 (3): 17- 23 LI Zhaoying, OU Yiming, SHI Ruoling Improved RRT path planning algorithm based on deep Q-network[J]. Air and Space Defense, 2021, 4 (3): 17- 23

[15]	ZHAO C, ZHU Y, DU Y, et al A novel direct trajectory planning approach based on generative adversarial networks and rapidly-exploring random tree[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23 (10): 17910- 17921 doi: 10.1109/TITS.2022.3164391

[16]	ZHANG T, WANG J, MENG M Q H Generative adversarial network based heuristics for sampling-based path planning[J]. IEEE/CAA Journal of Automatica Sinica, 2022, 9 (1): 64- 74 doi: 10.1109/JAS.2021.1004275

[17]	QIAO S, CHEN L C, YUILLE A. DetectoRS: detecting objects with recursive feature pyramid and switchable atrous convolution [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 10208–10219.

[18]	SANDLER M, HOWARD A, ZHU M, et al. MobileNetV2: inverted residuals and linear bottlenecks [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4510–4520.

[19]	CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation [EB/OL]. (2017−12−05)[2024−11−11]. https://arxiv.org/pdf/1706.05587.

[20]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// 31st Conference on Neural Information Processing Systems. Long Beach: [s.n.], 2017: 1–11.

[21]	HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13708–13717.

[22]	HUANG Z, WANG X, WEI Y, et al CCNet: criss-cross attention for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (6): 6896- 6908 doi: 10.1109/TPAMI.2020.3007032

[23]	LI M, PENG P, SUN H, et al An order-invariant and interpretable dilated convolution neural network for chemical process fault detection and diagnosis[J]. IEEE Transactions on Automation Science and Engineering, 2023, 21 (3): 3933- 3943

[24]	TU H, DENG Y, LI Q, et al Improved RRT global path planning algorithm based on Bridge Test[J]. Robotics and Autonomous Systems, 2024, 171: 104570 doi: 10.1016/j.robot.2023.104570

[25]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770–778.

[26]	RADOSAVOVIC I, KOSARAJU R P, GIRSHICK R, et al. Designing network design spaces [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 10425–10433.

[27]	李金良, 舒翰儒, 刘德建, 等基于改进RRT路径规划算法[J]. 组合机床与自动化加工技术, 2021, (2): 22- 24 LI Jinliang, SHU Hanru, LIU Dejian, et al Path planning algorithm based on improved RRT[J]. Modular Machine Tool and Automatic Manufacturing Technique, 2021, (2): 22- 24

[1]	Pengzhi LIN,Ming’en ZHONG,Kang FAN,Jiawei TAN,Zhiqiang LIN. Traffic scene perception algorithm based on cross-task bidirectional feature interaction[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(9): 1784-1792.

[2]	Jizhong DUAN,Haiyuan LI. Multi-scale parallel magnetic resonance imaging reconstruction based on variational model and Transformer[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(9): 1826-1837.

[3]	Fujian WANG,Zetian ZHANG,Xiqun CHEN,Dianhai WANG. Usage prediction of shared bike based on multi-channel graph aggregation attention mechanism[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(9): 1986-1995.

[4]	Hong ZHANG,Xuecheng ZHANG,Guoqiang WANG,Panlong GU,Nan JIANG. Real-time positioning and control of soft robot based on three-dimensional vision[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1574-1582.

[5]	Xuejun ZHANG,Shubin LIANG,Wanrong BAI,Fenghe ZHANG,Haiyan HUANG,Meifeng GUO,Zhuo CHEN. Source code vulnerability detection method based on heterogeneous graph representation[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1644-1652.

[6]	Yishan LIN,Jing ZUO,Shuhua LU. Multimodal sentiment analysis based on multi-head self-attention mechanism and MLP-Interactor[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1653-1661.

[7]	Yahong ZHAI,Yaling CHEN,Longyan XU,Yu GONG. Improved YOLOv8s lightweight small target detection algorithm of UAV aerial image[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1708-1717.

[8]	Jiarui FU,Zhaofei LI,Hao ZHOU,Wei HUANG. Camouflaged object detection based on Convnextv2 and texture-edge guidance[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1718-1726.

[9]	Hui XIONG,Banglu GE,Jinzhen LIU,Jiaxing WANG. Improved slime mould bee colony algorithm for multi-UAVs cooperative path planning[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(8): 1698-1707.

[10]	Rongtai YANG,Yubin SHAO,Qingzhi DU. Structure-aware model for few-shot knowledge completion[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(7): 1394-1402.

[11]	Jun YE,Zhibin XIAO,Xiaoyang LIN,Guan QUAN,Zhen WANG,Yueda WANG,Jiangfei HE,Yang ZHAO. Optimization methods of 3D self-supporting truss structure based on muti-axis 3D printing[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(7): 1333-1343.

[12]	Xinyu WEI,Lei RAO,Guangyu FAN,Niansheng CHEN,Songlin CHENG,Dingyu YANG. High-precision real-time semantic segmentation network for UAV remote sensing images[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(7): 1411-1420.

[13]	Kun HAO,Xuan MENG,Xiaofang ZHAO,Zhisheng LI. 3D underwater AUV path planning method integrating adaptive potential field method and deep reinforcement learning[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(7): 1451-1461.

[14]	Shengju WANG,Zan ZHANG. Missing value imputation algorithm based on accelerated diffusion model[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(7): 1471-1480.

[15]	Yuxin LIAO,Wei WANG,Weiming TENG,Haiyan HE,Zhan WANG,Jin WANG. Multi-objective constraint-based smooth path generation for UAVs global optimization method[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(7): 1481-1491.

Viewed

Full text

Abstract

Cited

Shared

Discussed