自主可控平台AGV设计及视觉循线算法研究

doi:10.3778/j.issn.1673-9418.2311095

摘要/Abstract

摘要： 设计并实现了一种基于自主可控平台的自动导引车（AGV）。AGV满足核心硬件国产化、软件开源可控的要求，并可兼容多种自主导航算法。对传统纯追踪算法在跟踪精度和安全性上进行了改进：一是载具在直线路段偏离参考轨迹较远的情况下使用Dubins路径进行快速回归；二是在大曲率参考轨迹处使用预瞄点偏移算法纠正跟踪轨迹，减小跟踪误差；三是应用动态预瞄距离和动态速度进一步减小大曲率路段的跟踪误差和安全风险。改进的算法在设计的AGV上进行了实现。在完成AGV设计和改进算法实现后，在实际环境中进行了视觉循线实验。改进的算法在0.1 m/s的速度下在曲率较小路段的平均偏差相较改进前的两种纯追踪算法变体分别减少了3.3%、7.3%，在大曲率路段减少了8.34%、23.06%；在0.5 m/s的速度下在曲率较小路段的平均偏差相较改进前的两种纯追踪算法变体分别减少了9.08%、11.33%，在大曲率路段减少了2.97%、24.67%。改进算法实验的整体结果优于使用改进前两种算法变体的结果，且设计并实现的AGV能够满足一般环境下的视觉循线导航需求，可应用于多种实际场合。

关键词: 自主可控, 自动导引车（AGV）, 跟踪控制, 纯追踪算法

Abstract: This paper designs and implements an AGV based on an autonomous and controllable platform. This AGV meets the requirements of domestic core hardware production and open-source software, and is compatible with multiple autonomous navigation algorithms. Moreover, the tracking accuracy and security of the traditional pure pursuit algorithm is improved and implemented on the AGV designed in this paper. Firstly, when the vehicle is far away from the reference path, Dubins path is introduced for fast convergence. Secondly, the looking-ahead point offset algorithm is used to correct the tracking path at the large curvature reference path and reduce the tracking errors. Thirdly, the application of dynamic looking-ahead distance and dynamic speed can further reduce the tracking errors and safety risk of large curvature sections. After completing the AGV design and algorithm updating, the real environment experiment is carried out. At the speed of 0.1 m/s, the average deviation of the improved algorithm on the section with small curvature is reduced by 3.3% and 7.3%, compared with two pure pursuit variants respectively, and that on the section with large curvature is reduced by 8.34% and 23.06%. At the speed of 0.5 m/s, the average deviation of the road section with small curvature is reduced by 9.08% and 11.33%, respectively, and that of the road section with large curvature is reduced by 2.97% and 24.67%. The overall experimental results of the improved algorithm are better than the results of the two variants, and the AGV designed in this paper can meet the requirements of visual line-following navigation in general environment, and can be applied to a variety of practical scenarios.

Key words: autonomous and controllable, autonomic guiding vehicle (AGV), tracking control, pure pursuit

徐诗著, 高军, 孙秋君. 自主可控平台AGV设计及视觉循线算法研究[J]. 计算机科学与探索, 2025, 19(1): 264-276.

XU Shizhu, GAO Jun, SUN Qiujun. Design of AGV Based on Autonomous Controllable Platform and Research on Visual Line-Following Algorithm[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(1): 264-276.

参考文献

[1] BOSTEL A J, SAGAR V K. Dynamic control systems for AGVs[J]. Computing & Control Engineering Journal, 1996, 7(4): 169-176.
[2] GUL F, RAHIMAN W, NAZLI A, et al. A comprehensive study for robot navigation techniques[J]. Cogent Engineering, 2019, 6: 1632046.
[3] 倪光南. 坚持信创科技自立自强建设网络强国和数字中国[J]. 信息安全研究, 2021, 7(1): 2-3.
NI G N. Adhere to information innovation technology self-reliance and self-improvement to build a strong network and digital China[J]. Journal of Information Security Research, 2021, 7(1): 2-3.
[4] LáZARO J L, GARCíA J C, MAZO M, et al. Distributed architecture for control and path planning of autonomous vehicles[J]. Microprocessors & Microsystems, 2001, 25(3): 159-166.
[5] YASUDA G. Distributed autonomous control of modular robot systems using parallel programming[J]. Journal of Materials Processing Technology, 2003, 141(3): 357-364.
[6] PADGHAM L. Developing intelligent agent systems: a practical guide[M]. John Wiley & Sons, Inc., 2004.
[7] GASCUE?A J M, FERNáNDEZ-C A. Agent-oriented modeling and development of a person-following mobile robot[J]. Expert Systems with Applications, 2011, 38(4): 4280-4290.
[8] BARBERá H M, PéREZ D H. Development of a flexible AGV for flexible manufacturing systems[J]. Industrial Robot, 2010, 37(5): 459-468.
[9] YUAN P, CHEN D, WANG T, et al. AGV system based on multi-sensor information fusion[C]//Proceedings of the 2014 International Symposium on Computer, Consumer and Control. Piscataway: IEEE, 2014.
[10] COSTLEY A, KUNZ C, SHARMA R, et al. Low cost, open-source platform to enable full-sized automated vehicle research[J]. IEEE Transactions on Intelligent Vehicles, 2020, 6(1): 3-13.
[11] TANABATA T, KODAMA K, HASHIGUCHI T, et al. Development of a plant conveyance system using an AGV and a self-designed plant-handling device: a case study of DIY plant phenotyping[J]. Breeding Science, 2022, 72(1): 85-95.
[12] SUZEN A A, DUMAN B, SEN B. Benchmark analysis of Jetson TX2, Jetson Nano and Raspberry PI using Deep-CNN[C]//Proceedings of the 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications. Piscataway: IEEE, 2020.
[13] ZHANG S, LIU J Y, DU Y F, et al. Method on automatic navigation control of tractor based on speed adaptation[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 326(23): 56-63.
[14] ZHANG W Y, GAI J Y, ZHANG Z G, et al. Double-DQN based path smoothing and tracking control method for robotic vehicle navigation[J]. Computers and Electronics in Agriculture, 2019, 166: 11.
[15] LI Z Q, CHEN L Q, ZHENG Q, et al. Control of a path following caterpillar robot based on a sliding mode variable structure algorithm[J]. Biosystems Engineering, 2019, 186: 293-306.
[16] NGUYEN P T T, YAN S W, LIAO J F, et al. Autonomous mobile robot navigation in sparse LiDAR feature environments[J]. Applied Sciences, 2021, 11(13): 16.
[17] ZHAO P, CHEN J J, SONG Y, et al. Design of a control system for an autonomous vehicle based on adaptive-PID[J]. International Journal of Advanced Robotic Systems, 2012, 9: 11.
[18] MAI T A, DANG T S, DUONG D T, et al. A combined backstepping and adaptive fuzzy PID approach for trajectory tracking of autonomous mobile robots[J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2021, 43(3): 13.
[19] YAMASHITA A S, ALEXANDRE P M, ZANIN A C, et al. Reference trajectory tuning of model predictive control[J]. Control Engineering Practice, 2016, 50: 1-11.
[20] DEAN S, MANIA H, MATNI N, et al. On the sample complexity of the linear quadratic regulator[J]. Foundations of Computational Mathematics, 2017(5).
[21] QIAO N, WANG L, ZHU W, et al. An improved path-tracking controller with mid-angle adaptive calibration for combine harvester[J]. Journal of Instrumentation, 2020, 15(1): 16.
[22] ABDELMONIEM A, OSAMA A, ABDELAZIZ M, et al. A path-tracking algorithm using predictive Stanley lateral controller[J]. International Journal of Advanced Robotic Systems, 2020, 17(6): 11.
[23] BU X, HOU Z, CHI R. Model free adaptive iterative learning control for farm vehicle path tracking[C]//Proceedings of the 3rd IFAC International Conference on Intelligent Control and Automation Science, Chengdu, Sep 2-4, 2013: 153-158.
[24] COULTER R C. Implementation of the pure pursuit path tracking algorithm[EB/OL]. [2023-09-14]. http://dx.doi.org/.
[25] SHAN Y X, YANG W, CHEN C, et al. CF-Pursuit: a pursuit method with a clothoid fitting and a fuzzy controller for autonomous vehicles[J]. International Journal of Advanced Robotic Systems, 2015, 12: 13.
[26] ANDERSEN H, CHONG Z J, ENG Y H, et al. Geometric path tracking algorithm for autonomous driving in pedestrian environment[C]//Proceedings of the 2016 IEEE International Conference on Advanced Intelligent Mechatronics.Piscataway: IEEE, 2016: 1669-1674.
[27] SUN Q P, WANG Z H, LI M, et al. Path tracking control of wheeled mobile robot based on improved pure pursuit algorithm[C]//Proceedings of the 2019 Chinese Automation Congress. Piscataway: IEEE, 2019.
[28] CHEN I M, CHAN C Y. Deep reinforcement learning based path tracking controller for autonomous vehicle[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2021, 235(2/3): 541-551.
[29] YU L L, YAN X X, KUANG Z X, et al. Driverless bus path tracking based on fuzzy pure pursuit control with a front axle reference[J]. Applied Sciences, 2020, 10(1): 19.
[30] WANG L H, CHEN Z L, ZHU W X. An improved pure pursuit path tracking control method based on heading error rate[J]. Industrial Robot, 2022, 49(5): 973-980.
[31] LI B, WANG Y Z, MA S J, et al. Adaptive pure pursuit: a real-time path planner using tracking controllers to plan safe and kinematically feasible paths[J].IEEE Transactions on Intelligent Vehicles, 2023, 8(9): 4155-4168.
[32] WU J D, REN H L, LIN T L, et al. A pure electric driverless crawler construction machinery walking method based on the fusion SLAM and improved pure pursuit algorithms[J]. Sensors, 2023, 23(18): 7784.
[33] NETTO M, BLOSSEVILLE J M, LUSETTI B, et al. A new robust control system with optimized use of the lane detection data for vehicle full lateral control under strong curvatures[C]//Proceedings of the 2006 IEEE Intelligent Transportation Systems Conference. Piscataway: IEEE, 2006: 1382-1387.
[34] ZHAO Z, ZHOU L, ZHU Q. Preview distance adaptive optimization for the path tracking control of unmanned vehicle[J]. Journal of Mechanical Engineering, 2018, 54(24): 166-173.
[35] 张华强, 王国栋, 吕云飞，等. 基于改进纯追踪模型的农机路径跟踪算法研究[J]. 农业机械学报, 2020, 51(9): 18-25.
ZHANG H Q, WANG G D, LV Y F, et al. Agricultural machinery automatic navigation control system based on improved pure tracking model[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(9): 18-25.
[36] AHN J, SHIN S, KIM M, et al. Accurate path tracking by adjusting look-ahead point in pure pursuit method[J]. International Journal of Automotive Technology, 2021, 22(1): 119-129.
[37] MACENSKI S, SINGH S, MARTíN F, et al. Regulated pure pursuit for robot path tracking[J]. Autonomous robots, 2023, 47(6): 685-694.
[38] 李魏魏, 袁森, 周小容. 基于视觉神经元PID的AGV轨迹跟踪控制器[J]. 组合机床与自动化加工技术, 2022(11): 56-61.
LI W W, YUAN S, ZHOU X X. AGV trajectory tracking controller based on visual neuron PID[J]. Combined Machine Tools and Automated Processing Technology, 2022(11): 56-61.
[39] 齐志权, 吴世南, 邹波, 等. 自动泊车路径纯跟踪算法应用研究[J]. 北京理工大学学报, 2023, 43(5): 510-516.
QI Z Q, WU S N, ZOU B, et al. Research on automatic parking path pure tracking algorithm[J]. Journal of Beijing Institute of Technology, 2023, 43(5): 510-516.
[40] OHTA H, AKAI N, TAKEUCHI E, et al. Pure pursuit revisited: field testing of autonomous vehicles in urban areas[C]//Proceedings of the 2016 IEEE 4th International Conference on Cyber-Physical Systems, Networks, and Applications. Piscataway: IEEE, 2016: 7-12.