面向无先验模型的机器人喷涂工艺研究进展

Research progress on prior-model-free robot spraying technology

摘要

[目的]针对传统机器人喷涂技术高度依赖先验几何模型，导致在动态形变场景下易产生“配准误差”，且难以适应多品种、小批量的柔性生产模式等问题，系统梳理了面向无先验模型的自主喷涂技术研究进展，旨在突破复杂未知曲面场景下的工艺智能化瓶颈。[方法]围绕“感知−思考−执行”的闭环工作流程，从硬件架构、三维点云感知与预处理、涂料沉积物理模型及动态参数自适应优化、基于点云切片与数据驱动的三维空间轨迹自主生成等方面，对现有技术体系进行了系统性的综述与剖析。[结果]归纳了当前面向无先验模型的机器人喷涂关键环节的核心算法演进脉络：即轨迹规划从局部启发式切片算法，跨越至基于三维深度学习的对象级生成与端到端扩散策略；揭示了“视觉−语言−动作”大模型与代理式人工智能对底层控制域的重塑。[结论]面向无先验模型的自主喷涂技术突破了信息技术与运营技术的壁垒，克服了传统编程方法的局限性。该技术是提升柔性制造场景下喷涂智能化水平的必然方向，未来将向基于合成数据驱动的数字孪生与具备硬约束物理安全护栏的高阶认知决策能力持续演进。

Abstract

[Objective] Aiming at the problems that traditional robotic spraying technology highly depends on prior geometric models, which easily causes “registration errors” in dynamic deformation scenarios and is difficult to adapt to multi-variety and small-batch flexible production modes, this paper systematically reviews the research progress of prior-model-free autonomous spraying technologies. It aims to overcome the bottlenecks in process intelligence for complex unknown curved surface scenarios. [Method] Focusing on the “perception–reasoning–action” closed-loop workflow, this study systematically reviews and analyzes existing technical systems from the perspectives of hardware architecture, 3D point cloud perception and preprocessing, physical modeling of coating deposition and adaptive optimization of dynamic parameters, as well as point cloud slicing-based and data-driven approaches for autonomous 3D spatial trajectory generation. [Result] It summarizes the core algorithmic evolutionary trajectories in key aspects of prior-model-free robotic spraying: specifically, the transition of trajectory planning from local heuristic slicing algorithms to 3D deep learning-based object-centric generation and end-to-end diffusion policies. Furthermore, it highlights the transformative impact of unified vision–language–action models and agentic AI (artificial intelligence) on the underlying control domain. [Conclusion] Prior-model-free autonomous spraying technology breaks the barriers between information technology and operational technology, overcoming the limitations of conventional programming methods. It represents an inevitable direction for enhancing spraying intelligence in flexible manufacturing scenarios and is expected to evolve further toward synthetic data-driven digital twins and higher-order cognitive decision-making capabilities fortified by hard-constrained physical safety guardrails.

关键词

机器人喷涂 / 无先验模型 / 三维点云 / 轨迹规划 / 涂料沉积模型 / 综述

Key words

robotic spraying / prior-model-free / three-dimensional point cloud / trajectory planning / coating deposition model / review

参考文献

[1] KUMAR V, KALITA K, CHATTERJEE P, et al. A SWARA-CoCoSo-based approach for spray painting robot selection[J]. Informatica, 2022, 33(1): 35-54.

[2] 刘亚军, 訾斌, 王正雨, 等. 智能喷涂机器人关键技术研究现状及进展[J]. 机械工程学报, 2022, 58(7): 53-74.

[3] LIU Y J, ZI B, WANG Z Y, et al. Research progress and trend of key technology of intelligent spraying robot[J]. Journal of Mechanical Engineering, 2022, 58(7): 53-74.

[4] CHEN H P, FUHLBRIGGE T, LI X Z. A review of CAD‐based robot path planning for spray painting[J]. Industrial Robot, 2009, 36(1): 45-50.

[5] BHAT R, KARUPPASAMY M, MARAGATHARAJAN M, et al. Optimization of robotic spray painting trajectories using machine learning for improved surface quality[J]. Scientific Reports, 2025, 15(1): 18767.

[6] 赵嘉浩, 訾斌, 王威, 等. 刚柔复合驱动并联喷涂机器人机构设计与工作空间分析[J]. 机械工程学报, 2023, 59(15): 28-39.

[7] ZHAO J H, ZI B, WANG W, et al. Mechanical design and workspace analysis of a rigid-flexible hybrid driven parallel spray-painting robot[J]. Journal of Mechanical Engineering, 2023, 59(15): 28-39.

[8] 潘波涛, 李园园, 王锦霞, 等. 铝防护涂层制备方法的研究进展[J]. 材料保护, 2022, 55(10): 171-179.

[9] PAN B T, LI Y Y, WANG J X, et al. Research progress of preparation methods of aluminum protective coating[J]. Materials Protection, 2022, 55(10): 171-179.

[10] 宋启良, 李吉丹, 郑玉杰, 等. 航天用T9A-D弹簧表面离子液体镀Al工艺研究[J]. 电镀与精饰, 2024, 46(2): 10-16.

[11] SONG Q L, LI J D, ZHENG Y J, et al. Study on ionic liquid Al plating technology on surface of T9A-D spring for aerospace applications[J]. Plating and Finishing, 2024, 46(2): 10-16.

[12] ANDULKAR M V, CHIDDARWAR S S, MARATHE A S. Novel integrated offline trajectory generation approach for robot assisted spray painting operation[J]. Journal of Manufacturing Systems, 2015, 37: 201-216.

[13] WEBER A M, GAMBAO E, BRUNETE A. A survey on autonomous offline path generation for robot-assisted spraying applications[J]. Actuators, 2023, 12(11): 403.

[14] 訾斌, 潘敬锋, 李元, 等. 智能喷涂机器人编程方法与遥操作技术研究综述[J]. 控制与决策, 2025, 40(4): 1057-1078.

[15] ZI B, PAN J F, LI Y, et al. Programming methods and teleoperation technology for intelligent spray-painting robot: a review[J]. Control and Decision, 2025, 40(4): 1057-1078.

[16] GUO J W, DING F, JIA X H, et al. Automatic and high-quality surface mesh generation for CAD models[J]. Computer-Aided Design, 2019, 109: 49-59.

[17] CAMBA J D, CONTERO M, COMPANY P. Parametric CAD modeling: an analysis of strategies for design reusability[J]. Computer-Aided Design, 2016, 74: 18-31.

[18] CHEN W, LI X, GE H L, et al. Trajectory planning for spray painting robot based on point cloud slicing technique[J]. Electronics, 2020, 9(6): 908.

[19] YU D Y, SU C Z, WANG E G, et al. Method of 3D coating accumulation modeling based on inclined spraying[J]. Sensors, 2024, 24(4): 1212.

[20] 李文畅, 盛施展, 吴金洪, 等. 表面活性剂对Ni−W−P化学镀层沉积行为及性能的影响[J]. 电镀与精饰, 2024, 46 (1): 1-8.

[21] LI W C, SHENG S Z, WU J H, et al. Effect of surfactant on deposition behavior and properties of electroless Ni−W−P coatings[J]. Plating and Finishing, 2024, 46 (1): 1-8.

[22] 周鑫, 王晓丽, 皇磊, 等. 喷射复合电沉积技术研究进展[J]. 电镀与精饰, 2024, 46(1): 55-63.

[23] ZHOU X, WANG X L, HUANG L, et al. Research progress of jet composite electrodeposition technology[J]. Plating and Finishing, 2024, 46(1): 55-63.

[24] ARAVIND J V, GANESH K V S S, PRINCE S. Real-time appearance based mapping using visual sensor for unknown environment[J]. Journal of Physics: Conference Series, 2022, 2335(1): 012057.

[25] BI Z M, LANG S Y. A framework for CAD-and sensor-based robotic coating automation[J]. IEEE Transactions on Industrial Informatics, 2007, 3(1): 84-91.

[26] 訾斌, 王宜藩, 徐锋, 等. 冗余机械臂逆运动学分析与迷彩喷涂路径规划[J]. 电子机械工程, 2023, 39 (1): 1-11.

[27] ZI B, WANG Y F, XU F, et al. Inverse kinematics analysis of redundant manipulator and path planning for camouflage painting[J]. Electro-mechanical Engineering, 2023, 39 (1): 1-11.

[28] HUANG Y Y, LAI J T, WU H H. Real-time 3D vision-based robotic path planning for automated adhesive spraying on lasted uppers in footwear manufacturing[J]. Applied Sciences, 2025, 15(11): 6365.

[29] BERENSTEIN R, EDAN Y. Human-robot collaborative site-specific sprayer[J]. Journal of Field Robotics, 2017, 34(8): 1519-1530.

[30] CHEN H P, SHENG W H, XI N, et al. Automated robot trajectory planning for spray painting of free-form surfaces in automotive manufacturing[C] // Proceedings of 2002 IEEE International Conference on Robotics and Automation. [S.l.]: IEEE, 2002: 450-455.

[31] ZHANG T, BIAN Y. Improved adaptive PSO for spray process optimization[C] // Proceedings of 2025 6th International Conference on Energy Power and Automation Engineering. [S.l.]: IEEE, 2025: 428-432.

[32] ZHANG B B, WU J, WANG L P, et al. Accurate dynamic modeling and control parameters design of an industrial hybrid spray-painting robot[J]. Robotics and Computer-Integrated Manufacturing, 2020, 63: 101923.

[33] YAN T T, ZHU H P, SUN L, et al. Detection of 3-D objects with a 2-D laser scanning sensor for greenhouse spray applications[J]. Computers and Electronics in Agriculture, 2018, 152: 363-374.

[34] BASTIDA S N, LIN C Y. Autonomous trajectory planning for spray painting on complex surfaces based on a point cloud model[J]. Sensors, 2023, 23(24): 9634.

[35] YU X Y, CHENG Z Y, ZHANG Y K, et al. Point cloud modeling and slicing algorithm for trajectory planning of spray painting robot[J]. Robotica, 2021, 39(12): 2246-2267.

[36] LUO Y, HE X L, SHI H W, et al. Design and development of a precision spraying control system for orchards based on machine vision detection[J]. Sensors, 2025, 25(12): 3799.

[37] XIA W, YU S R, LIAO X P. Paint deposition pattern modeling and estimation for robotic air spray painting on free-form surface using the curvature circle method[J]. Industrial Robot, 2010, 37(2): 202-213.

[38] 薛迪杰, 忽晓伟. 工件浸入电镀液温度状态控制方法研究[J]. 电镀与精饰, 2025, 47(9): 1-6, 28.

[39] XUE D J, HU X W. Research on temperature state control method for workpiece immersion of plating solution[J]. Plating and Finishing, 2025, 47(9): 1-6, 28.

[40] 黄文涛, 雪生兵, 邹文兵, 等. 磷化和磷化−电泳复合处理对ZM6性能的影响研究[J]. 电镀与精饰, 2025, 47(10): 11-16, 59.

[41] HUANG W T, XUE S B, ZOU W B, et al. Effect of phosphating and phosphating−electrophoresis compound treatment on properties of ZM6[J]. Plating and Finishing, 2025, 47(10): 11-16, 59.

[42] LIU L M, LIU Y J, HE X K, et al. Precision variable-rate spraying robot by using single 3D LIDAR in orchards[J]. Agronomy, 2022, 12(10): 2509.

[43] MAHMUD M S, ZAHID A, HE L, et al. Opportunities and possibilities of developing an advanced precision spraying system for tree fruits[J]. Sensors, 2021, 21(9): 3262.

[44] MU X Y, HE L, HEINEMANN P, et al. UGV-based precision spraying system for chemical apple blossom thinning on trellis trained canopies[J]. Journal of Field Robotics, 2025, 42(4): 1000-1011.

[45] 赵东波, 李龙, 于博, 等. 机车车身表面机器人喷涂均匀性研究[J]. 电镀与涂饰, 2024, 43(11): 155-162.

[46] ZHAO D B, LI L, YU B, et al. Study on uniformity of robotic spraying on surface of locomotive body[J]. Electroplating & Finishing, 2024, 43(11): 155-162.

[47] SHEN B, YE Q Y, GUETTLER N, et al. Primary breakup of a non-Newtonian liquid using a high-speed rotary bell atomizer for spray-painting processes[J]. Journal of Coatings Technology and Research, 2019, 16(6): 1581-1596.

[48] 关珂. 基于图像处理的激光熔覆镍镀层微小裂纹识别[J]. 电镀与精饰, 2025, 47 (12): 12-18.

[49] GUAN K. Identification of micro cracks in laser cladding nickel coatings based on image processing[J]. Plating and Finishing, 2025, 47 (12): 12-18.

[50] TIBONI G, CAMORIANO R, TOMMASI T. PaintNet: Unstructured multi-path learning from 3D point clouds for robotic spray painting[C] // Proceedings of 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems. [S.l.]: IEEE, 2023: 3857-3864.

[51] HUANG Z, WANG Y C, WEN J, et al. An object detection algorithm combining semantic and geometric information of the 3D point cloud[J]. Advanced Engineering Informatics, 2023, 56: 101971.

[52] CHEN J D, CHO Y K. CrackEmbed: Point feature embedding for crack segmentation from disaster site point clouds with anomaly detection[J]. Advanced Engineering Informatics, 2022, 52: 101550.

[53] MIRZAEI K, ARASHPOUR M, ASADI E, et al. End-to-end point cloud-based segmentation of building members for automating dimensional quality control[J]. Advanced Engineering Informatics, 2023, 55: 101878.

[54] OTSUKA Y, JYOGO S, TANAKA G, et al. Simulation system for electrostatic coating and automated robotic coating strategy development for H-beams of various scales[C] // Proceedings of 2025 IEEE 21st International Conference on Automation Science and Engineering. [S.l.]: IEEE, 2025: 1444-1449.

[55] 张淑珍, 贾伦, 金炅德, 等. 基于针-环组合电极的静电空气喷涂成膜及转移率的仿真计算[J]. 电镀与涂饰, 2023, 42(8): 45-51.

[56] ZHANG S Z, JIA L, JIN J D, et al. Numerical simulation on film formation and paint transfer efficiency of electrostatic air spray painting with needle-ring electrode[J]. Electroplating & Finishing, 2023, 42(8): 45-51.

[57] 李明, 钟明强, 邓俊杰, 等. 基于仿真软件的汽车喷涂快速调试方法[J]. 电镀与涂饰, 2024, 43(3): 144-149.

[58] LI M, ZHONG M Q, DENG J J, et al. Rapid commissioning of automotive painting line by simulation software[J]. Electroplating & Finishing, 2024, 43(3): 144-149.

[59] 王海平. 基于预测性维护技术的机器人喷涂质量缺陷改善[J]. 电镀与涂饰, 2025, 44(12): 134-139.

[60] WANG H P. Improvement of robotic spraying quality defects based on predictive maintenance technology[J]. Electroplating & Finishing, 2025, 44(12): 134-139.

基金资助

黑龙江省重大科技成果产业化项目(CG 24002)