Hostname: page-component-669899f699-rg895 Total loading time: 0 Render date: 2025-04-29T11:11:11.416Z Has data issue: false hasContentIssue false
  • English
  • Français

Hybrid learning-based visual path following for an industrial robot

Published online by Cambridge University Press:  16 October 2024

Mustafa Can Bingol Open the ORCID record for Mustafa Can Bingol [Opens in a new window]  and
Omur Aydogmus Open the ORCID record for Omur Aydogmus [Opens in a new window]
Mustafa Can Bingol
Affiliation:
Department of Electrical-Electronics Engineering, Burdur Mehmet Akif Ersoy University, Burdur, Turkiye
Omur Aydogmus*
Affiliation:
Department of Mechatronics Engineering, Faculty of Technology, Fırat University, Elazig, Turkiye
*
Corresponding author: Omur Aydogmus; Email: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

This study proposes a novel hybrid learning approach for developing a visual path-following algorithm for industrial robots. The process involves three steps: data collection from a simulation environment, network training, and testing on a real robot. The actor network is trained using supervised learning for 500 epochs. A semitrained network is then obtained at the $250^{th}$ epoch. This network is further trained for another 250 epochs using reinforcement learning methods within the simulation environment. Networks trained with supervised learning (500 epochs) and the proposed hybrid learning method (250 epochs each of supervised and reinforcement learning) are compared. The hybrid learning approach achieves a significantly lower average error (30.9 mm) compared with supervised learning (39.3 mm) on real-world images. Additionally, the hybrid approach exhibits faster processing times (31.7 s) compared with supervised learning (35.0 s). The proposed method is implemented on a KUKA Agilus KR6 R900 six-axis robot, demonstrating its effectiveness. Furthermore, the hybrid approach reduces the total power consumption of the robot’s motors compared with the supervised learning method. These results suggest that the hybrid learning approach offers a more effective and efficient solution for visual path following in industrial robots compared with traditional supervised learning.

Keywords

hybrid learningindustrial robotreinforcement learningsupervised learning
Type
Research Article
Information
Robotica , Volume 42 , Issue 11 , November 2024 , pp. 3888 - 3903
Copyright
© The Author(s), 2024. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

International Federation of Robotics (IFR), Homepage, https://ifr.org, accessed October 05, 2024.Google Scholar
Lin, Y., Zhao, H. and Ding, H., “A data-driven approach for online path correction of industrial robots using modified flexible dynamics model and disturbance state observer,” IEEE/ASME Trans. Mechatron. 28(6), 3410–3421 (2023).CrossRefGoogle Scholar
Raikwar, S., Fehrmann, J. and Herlitzius, T., “Navigation and control development for a four-wheel-steered mobile orchard robot using model-based design,” Comput. Electron. Agric. 202, 107410 (2022).CrossRefGoogle Scholar
Khaled, T. A., Akhrif, O. and Bonev, I. A., “Dynamic path correction of an industrial robot using a distance sensor and an ADRC controller,” IEEE/ASME Trans. Mechatron. 26(3), 1646–1656 (2020).CrossRefGoogle Scholar
Geng, Y., Zhang, Y., Tian, X. and Zhou, L., “A novel 3D vision-based robotic welding path extraction method for complex intersection curves,” Robot. Comput.-Integr. Manuf. 87, 102702 (2024).CrossRefGoogle Scholar
Chen, Z. and Birchfield, S. T., “Qualitative vision-based path following,” IEEE Trans. Robot. 25(3), 749–754 (2009).CrossRefGoogle Scholar
Okamoto, K., Itti, L. and Tsiotras, P., “Vision-based autonomous path following using a human driver control model with reliable input-feature value estimation,” IEEE Trans. Intell. Veh. 4(3), 497–506 (2019).CrossRefGoogle Scholar
Duan, K., Suen, C. W. K. and Zou, Z., “Robot morphology evolution for automated HVAC system inspections using graph heuristic search and reinforcement learning,” Automat. Constr. 153, 104956 (2023).CrossRefGoogle Scholar
Baltes, J., Christmann, G. and Saeedvand, S., “A deep reinforcement learning algorithm to control a two-wheeled scooter with a humanoid robot,” Eng. Appl. Artif. Intell. 126, 106941 (2023).CrossRefGoogle Scholar
Chettibi, T., “Multi-objective trajectory planning for industrial robots using a hybrid optimization approach,” Robotica 42(6), 2026–2045 (2024).CrossRefGoogle Scholar
Zhang, X. and Shi, G., “Multi-objective optimal trajectory planning for manipulators in the presence of obstacles,” Robotica 40(4), 888–906 (2022).CrossRefGoogle Scholar
Yang, D., Dong, L. and Dai, J. K., “Collision avoidance trajectory planning for a dual-robot system: Using a modified APF method,” Robotica 42(3), 846–863 (2024).CrossRefGoogle Scholar
Katiyar, S. and Dutta, A., “End-effector path tracking of a 14 DOF rover manipulator system in CG-space framework,” Robotica 42(1), 265–301 (2024).CrossRefGoogle Scholar
Tang, X., Zhou, H. and Xu, T., “Obstacle avoidance path planning of 6-DOF robotic arm based on improved A* algorithm and artificial potential field method,” Robotica 42(2), 457–481 (2024).CrossRefGoogle Scholar
Oh, Y., Kim, Y., Na, K. and Youn, B. D., “A deep transferable motion-adaptive fault detection method for industrial robots using a residual–convolutional neural network,” ISA Transactions 128, 521–534 (2021).CrossRefGoogle ScholarPubMed
Chen, L., Cao, J., Wu, K. and Zhang, Z., “Application of generalized frequency response functions and improved convolutional neural network to fault diagnosis of heavy-duty industrial robot,” Robotics and Computer-Integrated Manufacturing 73, 102228 (2022).CrossRefGoogle Scholar
Bingol, M. C. and Aydogmus, O., “Practical application of a safe human-robot interaction software,” Industrial Robot: The International Journal of Robotics Research and Application 47(3), 359–368 (2020).CrossRefGoogle Scholar
Bingol, M. C. and Aydogmus, O., “Performing predefined tasks using the human–robot interaction on speech recognition for an industrial robot,” Engineering Applications of Artificial Intelligence 95, 103903 (2020).CrossRefGoogle Scholar
Yan, J. and Zhang, M., “A transfer-learning based energy consumption modeling method for industrial robots,” Journal of Cleaner Production 325, 29299 (2021).CrossRefGoogle Scholar
Toquica, J. S., Oliveira, P. S., Souza, W. S. R., Motta, J. M. S. T. and Borges, D. L., “An analytical and a deep learning model for solving the inverse kinematic problem of an industrial parallel robot,” Computers & Industrial Engineering 151, 106682 (2021).CrossRefGoogle Scholar
Rath, B. N. and Subudhi, B., “A robust model predictive path following controller for an autonomous underwater vehicle,” Ocean Engineering 244, 110265 (2022).CrossRefGoogle Scholar
Zheng, Y., Tao, J., Sun, Q., Sun, H., Chen, Z., Sun, M. and Xie, G., “Soft actor–critic based active disturbance rejection path following control for unmanned surface vessel under wind and wave disturbances,” Ocean Engineering 247, 110631 (2022).CrossRefGoogle Scholar
Mondal, S., Ray, R., Reddy, S. and Nandy, S., “Intelligent controller for nonholonomic wheeled mobile robot: A fuzzy path following combination,” Mathematics and Computers in Simulation 193, 533–555 (2022).CrossRefGoogle Scholar
Handler, J., Harker, M. and Rath, G., “Multidimensional path tracking with global least squares solution,” IFAC-PapersOnLine 53, 6189–6194 (2020).CrossRefGoogle Scholar
Maldonado-Ramirez, A., Rios-Cabrera, R. and Lopez-Juarez, I., “A visual path-following learning approach for industrial robots using drl,” Robotics and Computer-Integrated Manufacturing 71, 102130 (2021).CrossRefGoogle Scholar
Wen, Y. and Pagilla, P. R., “A novel 3d path following control framework for robots performing surface finishing tasks,” Mechatronics 76, 102540 (2021).CrossRefGoogle Scholar
Bingol, M. C., Development of Artificial Intelligence-Based Self-Programmable Robot Software Compatible with Industry 4.0 using Human-Robot Interaction PhD thesis (Firat University, Institute of science, 2020).Google Scholar
Yang, Y., Li, Z., Yu, X., Li, Z. and Gao, H., “A trajectory planning method for robot scanning system uuuusing mask r-cnn for scanning objects with unknown model,” Neurocomputing 404, 329–339 (2020).CrossRefGoogle Scholar
Almeida, A., Vicente, P. and Bernardino, A., “Where is my hand? deep hand segmentation for visual self-recognition in humanoid robots,” Robotics and Autonomous Systems 145, 103857 (2021).CrossRefGoogle Scholar
Bilal, D. K., Unel, M., Tunc, L. T. and Gonul, B., “Development of a vision based pose estimation system for robotic machining and improving its accuracy using lstm neural networks and sparse regression,” Robotics and Computer-Integrated Manufacturing 74, 102262 (2022).CrossRefGoogle Scholar
Ying, K.-C., Pourhejazy, P., Cheng, C.-Y. and Cai, Z.-Y., “Deep learning-based optimization for motion planning of dual-arm assembly robots,” Computers & Industrial Engineering 160, 107603 (2021).CrossRefGoogle Scholar
Zhang, W., Gai, J., Zhang, Z., Tang, L., Liao, Q. and Ding, Y., “Double-dqn based path smoothing and tracking control method for robotic vehicle navigation,” Computers and Electronics in Agriculture 166, 104985 (2019).CrossRefGoogle Scholar
Wang, J., Elfwing, S. and Uchibe, E., “Modular deep reinforcement learning from reward and punishment for robot navigation,” Neural Networks 135, 115–126 (2021).CrossRefGoogle ScholarPubMed
Chen, X., Fu, C. and Huang, J., “A deep q-network for robotic odor/gas source localization: Modeling, measurement and comparative study,” Measurement 183, 109725 (2021).CrossRefGoogle Scholar
Zou, Y., Chen, T., Chen, X. and Li, J., “Robotic seam tracking system combining convolution filter and deep reinforcement learning,” Mechanical Systems and Signal Processing 165, 108372 (2022).CrossRefGoogle Scholar
Wen, S., Wen, Z., Di, Z., Zhang, H. and Wang, T., “A multi-robot path-planning algorithm for autonomous navigation using meta-reinforcement learning based on transfer learning,” Applied Software Computing 110, 107605 (2021).CrossRefGoogle Scholar
Bingol, M. C., “Proximal policy optimization-based path generation of an industrial robot,” International Conference on Engineering, Natural and Applied Science 2021 (ICENAS’21) (2021) pp. 322–328.Google Scholar
Kamali, K., Bonev, I. A. and Desrosiers, C., “Real-Time Motion Planning for Robotic Teleoperation Using Dynamic-Goal Deep Reinforcement Learning,” In 2020 17th Conference on Computer and Robot Vision (CRV) (2020) pp. 182–189.Google Scholar
Liu, Z. and Kubota, N., “Hybrid Learning Approach Based on Multi-Objective BehaviorCoordination for Multiple Robots,” In 2007 International Conference on Mechatronics and Automation (2007) pp. 204–209.Google Scholar
Desouky, S. F. and Schwartz, H. M., “A Novel Hybrid Learning Technique Applied to a Self-Learning Multi-Robot System,” In 2009 IEEE International Conference on Systems, Man and Cybernetics (2009) pp. 2616–2623.Google Scholar
Long, J., Mou, J., Zhang, L., Zhang, S. and Li, C., “Attitude data-based deep hybrid learning architecture for intelligent fault diagnosis of multi-joint industrial robots,” Journal of Manufacturing Systems 61, 736–745 (2021).CrossRefGoogle Scholar
Schulman, J., Wolski, F., Dhariwal, P., Radford, A. and Klimov, O., Proximal policy optimization algorithms (2017).Google Scholar
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D. and Wierstra, D., Continuous control with deep reinforcement learning (2015).Google Scholar
Schulman, J., Levine, S., Abbeel, P., Jordan, M. and Moritz, P., “Trust region policy optimization,” International Conference on Machine Learning (2015) pp. 1889–1897.Google Scholar