A Study on Path Planning for Curved Surface UV Printing Robots Based on Reinforcement Learning
In robotic surface UV printing, the irregular shape of the workpiece and frequent curvature changes require the printing robot to maintain the nozzle’s perpendicular orientation to the surface during path planning, which imposes high demands on trajectory accuracy and path smoothness. To address thi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/4/648 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850231508240957440 |
|---|---|
| author | Jie Liu Xianxin Lin Chengqiang Huang Zelong Cai Zhenyong Liu Minsheng Chen Zhicong Li |
| author_facet | Jie Liu Xianxin Lin Chengqiang Huang Zelong Cai Zhenyong Liu Minsheng Chen Zhicong Li |
| author_sort | Jie Liu |
| collection | DOAJ |
| description | In robotic surface UV printing, the irregular shape of the workpiece and frequent curvature changes require the printing robot to maintain the nozzle’s perpendicular orientation to the surface during path planning, which imposes high demands on trajectory accuracy and path smoothness. To address this challenge, this paper proposes a reinforcement-learning-based path planning method. First, an ideal main path is defined based on the nozzle characteristics, and then a robot motion accuracy model is established and transformed into a Markov Decision Process (MDP) to improve path accuracy and smoothness. Next, a framework combining Generative Adversarial Imitation Learning (GAIL) and Soft Actor–Critic (SAC) methods is proposed to solve the MDP problem and accelerate the convergence of SAC training. Experimental results show that the proposed method outperforms traditional path planning methods, as well as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Specifically, the maximum Cartesian space error in path accuracy is reduced from 1.89 mm with PSO and 2.29 mm with GA to 0.63 mm. In terms of joint space smoothness, the reinforcement learning method achieves the smallest standard deviation, especially with a standard deviation of 0.00795 for joint 2, significantly lower than 0.58 with PSO and 0.729 with GA. Moreover, the proposed method also demonstrates superior training speed compared to the baseline SAC algorithm. The experimental results validate the application potential of this method in intelligent manufacturing, particularly in industries such as automotive manufacturing, aerospace, and medical devices, with significant practical value. |
| format | Article |
| id | doaj-art-9beaa84ca7674c468c2da5d88f8d0bf3 |
| institution | OA Journals |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-9beaa84ca7674c468c2da5d88f8d0bf32025-08-20T02:03:31ZengMDPI AGMathematics2227-73902025-02-0113464810.3390/math13040648A Study on Path Planning for Curved Surface UV Printing Robots Based on Reinforcement LearningJie Liu0Xianxin Lin1Chengqiang Huang2Zelong Cai3Zhenyong Liu4Minsheng Chen5Zhicong Li6Guangdong Provincial Key Laboratory of Industrial Intelligent Inspection Technology, School of Mechatronic Engineering and Automation, Foshan University, Foshan 528225, ChinaGuangdong Provincial Key Laboratory of Industrial Intelligent Inspection Technology, School of Mechatronic Engineering and Automation, Foshan University, Foshan 528225, ChinaGuangdong Provincial Key Laboratory of Industrial Intelligent Inspection Technology, School of Mechatronic Engineering and Automation, Foshan University, Foshan 528225, ChinaGuangdong Provincial Key Laboratory of Industrial Intelligent Inspection Technology, School of Mechatronic Engineering and Automation, Foshan University, Foshan 528225, ChinaGuangdong Provincial Key Laboratory of Industrial Intelligent Inspection Technology, School of Mechatronic Engineering and Automation, Foshan University, Foshan 528225, ChinaGuangdong Provincial Key Laboratory of Industrial Intelligent Inspection Technology, School of Mechatronic Engineering and Automation, Foshan University, Foshan 528225, ChinaGuangdong Provincial Key Laboratory of Industrial Intelligent Inspection Technology, School of Mechatronic Engineering and Automation, Foshan University, Foshan 528225, ChinaIn robotic surface UV printing, the irregular shape of the workpiece and frequent curvature changes require the printing robot to maintain the nozzle’s perpendicular orientation to the surface during path planning, which imposes high demands on trajectory accuracy and path smoothness. To address this challenge, this paper proposes a reinforcement-learning-based path planning method. First, an ideal main path is defined based on the nozzle characteristics, and then a robot motion accuracy model is established and transformed into a Markov Decision Process (MDP) to improve path accuracy and smoothness. Next, a framework combining Generative Adversarial Imitation Learning (GAIL) and Soft Actor–Critic (SAC) methods is proposed to solve the MDP problem and accelerate the convergence of SAC training. Experimental results show that the proposed method outperforms traditional path planning methods, as well as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Specifically, the maximum Cartesian space error in path accuracy is reduced from 1.89 mm with PSO and 2.29 mm with GA to 0.63 mm. In terms of joint space smoothness, the reinforcement learning method achieves the smallest standard deviation, especially with a standard deviation of 0.00795 for joint 2, significantly lower than 0.58 with PSO and 0.729 with GA. Moreover, the proposed method also demonstrates superior training speed compared to the baseline SAC algorithm. The experimental results validate the application potential of this method in intelligent manufacturing, particularly in industries such as automotive manufacturing, aerospace, and medical devices, with significant practical value.https://www.mdpi.com/2227-7390/13/4/648UV printingcomplex surfacepath planningreinforcement learningSACrobot |
| spellingShingle | Jie Liu Xianxin Lin Chengqiang Huang Zelong Cai Zhenyong Liu Minsheng Chen Zhicong Li A Study on Path Planning for Curved Surface UV Printing Robots Based on Reinforcement Learning Mathematics UV printing complex surface path planning reinforcement learning SAC robot |
| title | A Study on Path Planning for Curved Surface UV Printing Robots Based on Reinforcement Learning |
| title_full | A Study on Path Planning for Curved Surface UV Printing Robots Based on Reinforcement Learning |
| title_fullStr | A Study on Path Planning for Curved Surface UV Printing Robots Based on Reinforcement Learning |
| title_full_unstemmed | A Study on Path Planning for Curved Surface UV Printing Robots Based on Reinforcement Learning |
| title_short | A Study on Path Planning for Curved Surface UV Printing Robots Based on Reinforcement Learning |
| title_sort | study on path planning for curved surface uv printing robots based on reinforcement learning |
| topic | UV printing complex surface path planning reinforcement learning SAC robot |
| url | https://www.mdpi.com/2227-7390/13/4/648 |
| work_keys_str_mv | AT jieliu astudyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT xianxinlin astudyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT chengqianghuang astudyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT zelongcai astudyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT zhenyongliu astudyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT minshengchen astudyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT zhicongli astudyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT jieliu studyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT xianxinlin studyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT chengqianghuang studyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT zelongcai studyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT zhenyongliu studyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT minshengchen studyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning AT zhicongli studyonpathplanningforcurvedsurfaceuvprintingrobotsbasedonreinforcementlearning |