Trajectory Planning Algorithm for Humanoid Welding Robots Based on Visual 3D Reconstruction

doi:10.3901/JME.260167

Abstract

Abstract: Humanoid welding robots are a promising solution for non-standard, small-scale, and narrow-space welding applications. A trajectory planning algorithm is presented for humanoid welding robots based on visual 3D reconstruction to address challenges in scene reconstruction and autonomous welding. The algorithm extracts ORB features from stereo images of the robot's head to estimate depth and generate a 3D point cloud. Using line and plane features, an improved 2D RRT* (Rapidly-exploring random tree star) algorithm is applied for path planning within the navigable domain. During welding, multi-view RGB-D images of the left arm and an enhanced NDT (normal distributions transform) method construct the 3D point cloud of the weld area. High-precision point clouds and an improved 3D RRT* algorithm are then used for planning the right-arm welding trajectory. Experimental results with a humanoid welding robot prototype demonstrate that the proposed method achieves autonomous 3D reconstruction, path planning, and welding trajectory planning with high real-time performance, short path lengths, and precise torch positioning, meeting welding accuracy requirements.

Key words: humanoid welding robot, 3D reconstruction, path planning, welding trajectory planning

CLC Number:

TP242

CHI Peng, LIU Yuan, LIAO Haipeng, WU Xiangmiao, WU Jianwen, ZHANG Qin, WANG Zhenmin. Trajectory Planning Algorithm for Humanoid Welding Robots Based on Visual 3D Reconstruction[J]. Journal of Mechanical Engineering, 2026, 62(13): 55-65.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.cjmenet.com.cn/EN/10.3901/JME.260167

http://www.cjmenet.com.cn/EN/Y2026/V62/I13/55

References

[1] SUN G，WANG Z，LU Y，et al. Underwater laser welding/cladding for high-performance repair of marine metal materials：A review[J]. Chinese Journal of Mechanical Engineering，2022，35(1)：5.
[2] 王斐，梁宸，韩晓光，等. 基于焊件识别与位姿估计的焊接机器人视觉引导[J]. 控制与决策，2020，35(8)：1873-1878. WANG Fei，LIANG Chen，HAN Xiaoguang，et al. Visual guidance of welding robot based on weldment recognition and pose estimation[J]. Control and Decision，2020，35(8)：1873-1878.
[3] 陈华斌，陈善本. 复杂场景下的焊接智能制造中的信息感知与控制方法[J]. 金属学报，2022，58(4)：541-550. CHEN Huabin，CHEN Shanben. Key information perception and control strategy of intellignet welding under complex scene[J]. Acta Metall Sin，2022，58(4)：541-550.
[4] 王耀南，谢核，邓晶丹，等. 智能制造测量机器人关键技术研究综述[J]. 机械工程学报，2024，60(16)：1-18. WANG Yaonan，XIE He，DENG Jingdan，et al. Overview of key technologies for measurement robots in intelligent manufacturing[J]. Journal of Mechanical Engineering，2024，60(16)：1-18.
[5] 王耀南，江一鸣，姜娇，等. 机器人感知与控制关键技术及其智能制造应用[J]. 自动化学报，2023，49(3)：494-513. WANG Yaonan，JIANG Yiming，JIANG Jiao，et al. Key technologies of robot perception and control and its intelligent manu-facturing applications[J]. Acta Automatic Sinica，2023，49：494-513.
[6] 刘今越，李文秀，贾晓辉，等. 基于场景点云重建的移动焊接机器人作业轨迹提取方法[J]. 计算机集成制造系统，2024，30(7)：2381. LIU Jinxiu，LI Wenxiu，JIA Xiaohui，et al. Operation trajectory extraction method of mobile welding robot based on point cloud reconstruction[J]. Computer Integrated Manufacturing System，2024，30(7)：2381.
[7] TRAN C C，LIN C Y. An intelligent path planning of welding robot based on multisensor interaction[J]. IEEE Sensors Journal，2023，23(8)：8591-8604.
[8] GENG Y，ZHANG Y，TIAN X，et al. A method of welding path planning of steel mesh based on point cloud for welding robot[J]. The International Journal of Advanced Manufacturing Technology，2021，116：2943-2957.
[9] ZHANG Y，JIANG Y，TIAN X，et al. A point cloud-based welding trajectory planning method for plane welds[J]. The International Journal of Advanced Manufacturing Technology，2023，125(3)：1645-1659.
[10] CHI P，WANG Z，LIAO H，et al. Low-latency visual-based high-quality 3D reconstruction using point cloud optimization[J]. IEEE Sensors Journal，2023，23(17)：20055-20065.
[11] HE Y，YU Z，LI J，et al. Discerning weld seam profiles from strong arc background for the robotic automated welding process via visual attention features[J]. Chinese Journal of Mechanical Engineering，2020，33(1)：21.
[12] GAO X，LIU Y，YOU D. Detection of micro-weld joint by magneto-optical imaging[J]. Optics & Laser Technology，2014，62：141-151.
[13] GAO X，MO L，YOU D，et al. Tight butt joint weld detection based on optical flow and particle filtering of magneto-optical imaging[J]. Mechanical Systems and Signal Processing，2017，96：16-30.
[14] 郭亮，张华. 狭小空间不连续折线焊缝识别移动机器人跟踪系统[J]. 机械工程学报，2019，55(17)：8-13. GUO Liang，ZHANG Hua. Discontinuous fold line welding seam recognition and mobile robot tracking system in narrow space[J]. Journal of Mechanical Engineering，2019，55(17)：8-13.
[15] 何银水，余卓骅，李健，等. 基于视觉特征的厚板机器人焊接焊缝轮廓的有效提取[J]. 机械工程学报，2019，55(17)：56-60. HE Yinshui，YU Zhuohua，LI Jian，et al. Effective weld seam profile extraction via visual features for robotic welding with thick steel plates[J]. Journal of Mechanical Engineering，2019，55(17)：56-60.
[16] KARAMAN S，FRAZZOLI E. Sampling-based algorithms for optimal motion planning[J]. The International Journal of Robotics Research，2011，30(7)：846-894.
[17] WANG X，WEI J，ZHOU X，et al. Dual-objective collision-free path optimization of arc welding robot[J]. IEEE Robotics and Automation Letters，2021，6(4)：6353-6360.
[18] WANG X，GAO J，ZHOU X，et al. Path planning for the gantry welding robot system based on improved RRT*[J]. Robotics and Computer-Integrated Manufacturing，2024，85：102643.
[19] CHI P，WANG Z，LIAO H，et al. Application of artificial intelligence in the new generation of underwater humanoid welding robots：A review[J]. Artificial Intelligence Review，2024，57(11)：306.
[20] CHI P，WANG Z，LIAO H，et al. Towards new-generation of intelligent welding manufacturing：A systematic review on 3D vision measurement and path planning of humanoid welding robots[J]. Measurement：Journal of the International Measurement Confederation，2024：116065.
[21] WANG G，LI W，JIANG C，et al. Simultaneous calibration of multicoordinates for a dual-robot system by solving the AXB= YCZ problem[J]. IEEE Transactions on Robotics，2021，37(4)：1172-1185.
[22] PEDROSA E，OLIVEIRA M，LAU N，et al. A general approach to hand-eye calibration through the optimization of atomic transformations[J]. IEEE Transactions on Robotics，2021，37(5)：1619-1633.
[23] GAO Z，LI Y，LUO Y，et al. Tool center point calibration via posture-sequence particle swarm optimization[J]. IEEE Sensors Journal，2023，24(3)：3513-3522.
[24] RUBLEE E，RABAUD V，KONOLIGE K，et al. ORB：An efficient alternative to SIFT or SURF[C]// 2011 International Conference on Computer Vision，IEEE，2011：2564-2571.
[25] BIBER P，STRAßER W. The normal distributions transform：A new approach to laser scan matching[C]// Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE，2003：2743-2748.
[26] WANG A，CHEN H，LIU L，et al. Yolov10：Real-time end-to-end object detection[J]. Advances in Neural Information Processing Systems，2025，37：107984-108011.
[27] GAMMELL J D，SRINIVASA S S，BARFOOT T D. Informed RRT*：Optimal sampling-based path planning focused via direct sampling of an admissible ellipsoidal heuristic[C]// 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE，2014：2997-3004.
[28] MA G，DUAN Y，LI M，et al. A probability smoothing Bi-RRT path planning algorithm for indoor robot[J]. Future Generation Computer Systems，2023，143：349-360.
[29] JEOBNG I B，LEE S J，KIM J H. Quick-RRT*：Triangular inequality-based implementation of RRT* with improved initial solution and convergence rate[J]. Expert Systems with Applications，2019，123：82-90.
[30] FAN J，CHEN X，LIANG X. UAV trajectory planning based on bi-directional APF-RRT* algorithm with goal-biased[J]. Expert systems with applications，2023，213：119137.
[31] WANG J，LI B，MENG M Q H. Kinematic constrained bi-directional RRT with efficient branch pruning for robot path planning[J]. Expert Systems with Applications，2021，170：114541.