Research on Deep Learning-Based Intelligent Kiln Car Unstacking Robot Vision Recognition and Path Planning

Xueli Liu

doi:10.62677/IJETAA.2505136

Authors

Xueli Liu Ziwen Co., Limited, Hong Kong Author

DOI:

https://doi.org/10.62677/IJETAA.2505136

Keywords:

Deep learning, Robot vision, Path planning, Intelligent unstacking, Industrial automation

Abstract

With the advancement of Industry 4.0, intelligent manufacturing has imposed higher requirements for automated production. Kiln car unstacking, as a critical process in the ceramics and building materials industries, suffers from low efficiency and high safety risks when performed manually. This paper presents an intelligent kiln car unstacking robot system based on deep learning that integrates vision recognition and path planning technologies. The system employs an improved YOLOv8 algorithm for product detection and localization, enhancing recognition accuracy through attention mechanisms and multi-scale feature fusion techniques. For path planning, an intelligent planner based on the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm is designed, incorporating prioritized experience replay and LSTM technology to achieve efficient navigation in dynamic environments. The system adopts a hierarchical architecture comprising perception, decision-making, and execution layers, ensuring real-time performance and reliability through multi-sensor fusion. Experimental results demonstrate that the improved YOLOv8 algorithm achieves 95.2% detection accuracy, representing an 8.7% improvement over the baseline. The TD3 path planning algorithm achieves a 96.8% success rate with 12.3% shorter path lengths and 45.6% reduced planning time. In practical industrial testing, the system improves work efficiency by 73.5% and reduces error rates by 89.2% compared to manual operations, validating the effectiveness of deep learning technology in complex industrial environments and providing important technical reference for intelligent manufacturing applications.

Downloads

Download data is not yet available.

References

H. Liu, K. Li, and H. Shi, “Quality management model for intelligent manufacturing full value chain based on quality 4.0,” Science & Technology Review, vol. 43, no. 4, pp. 101–112, 2025.

L. Zhou, L. Zhang, and N. Konz, “Computer vision techniques in manufacturing,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 53, no. 1, pp. 105–117, 2022.

R. Singh, J. Ren, and X. Lin, “A review of deep reinforcement learning algorithms for mobile robot path planning,” Vehicles, vol. 5, no. 4, pp. 1423–1451, 2023.

Y. Tian, Q. Ye, and D. Doermann, “YOLOv12: Attention-centric realtime object detectors,” arXiv preprint arXiv:2502.12524, 2025.

Y. Lin, Z. Zhang, Y. Tan, H. Fu, and H. Min, “Efficient TD3 based path planning of mobile robot in dynamic environments using prioritized experience replay and LSTM,” Scientific Reports, vol. 15, no. 1, pp. 1–16, 2025.

B. Zhao, Y. Wu, C. Wu, and R. Sun, “Deep reinforcement learning trajectory planning for robotic manipulator based on simulation-efficient training,” Scientific Reports, vol. 15, no. 1, p. 8286, 2025.

O. Haffner, E. Kucera, and D. Rosinov ˇ a, “Applications of machine learning and computer vision in industry 4.0,” Applied Sciences, vol.14, no. 6, p. 2431, 2024.

Y. Wang, Y. Jiang, J. Jiang, H. Zhang, H. Tan, W. Peng, and K. Zeng, “Key technologies of robot perception and control and their applications in intelligent manufacturing,” Acta Automatica Sinica, vol. 49, no. 3, pp.494–513, 2023.

P. Kumar, D. Singh, and J. Bhamu, “Machine vision in industry 4.0: Applications, challenges and future directions,” in Machine Vision for Industry 4.0, CRC Press, 2022, pp. 263–284.

L. Shao, E. Zhang, J. Duan, and Q. Ma, “Enriched multi-scale cascade pyramid features and guided context attention network for industrial surface defect detection,” Engineering Applications of Artificial Intelligence, vol. 123, p. 106369, 2023.

L. Chen, L. Yang, T. Jie, M. Haoyuan, L. Yu, F. Shenbing, and G. Li, “Enhanced self-attention-based rapid CNN for detecting dense objects in varying illumination,” Cognitive Computation, vol. 17, no. 1, pp. 1–20,2025.

X. Han, J. Chang, and K. J. P. C. S. Wang, “You only look once: Unified, real-time object detection,” Procedia Computer Science, vol. 183, no. 1, pp. 61–72, 2021.

R. Khanam and M. Hussain, “A Review of YOLOv12: Attention-Based Enhancements vs. Previous Versions.,” arXiv preprint arXiv:2504.11995,2025.

Y. Tong, G. Yue, L. Fan, G. Lyu, D. Zhu, Y. Liu, and C. Tian, “YOLOFaster: An efficient remote sensing object detection method based on AMFFN,” Science Progress, vol. 107, no. 4, p. 00368504241280765,2024.

C. Ji, X. Zhao, and J. Wang, “A multi-scale detection method for striped fabric defects enhanced by coordinate attention,” in International Workshop on New Approaches for Multidimensional Signal Processing, Springer, 2025, pp. 303–315.

C. S. Tan, R. Mohd-Mokhtar, and M. R. Arshad, “A comprehensive review of coverage path planning in robotics using classical and heuristic algorithms,” IEEE Access, vol. 9, pp. 119310–119342, 2021.

W. Li, Z. Deng, P. Xie, and G. Xu, “Mobile robot path planning based on optimized TD3 neural network,” in 2024 4th International Conference on Electronic Information Engineering and Computer (EIECT), IEEE, 2024, pp. 129–133.

H. Zhao, Y. Guo, X. Li, Y. Liu, and J. Jin, “Hierarchical control framework for path planning of mobile robots in dynamic environments through global guidance and reinforcement learning,” IEEE Internet of Things Journal, 2024.

J. Luo, J. Chen, Z. Peng, J. Li, W. Wu, and G. Zhou, “Experimental system for robot grasping based on machine vision,” Experimental Technology & Management, vol. 39, no. 4, 2022.

M. Servi, A. Profili, R. Furferi, and Y. Volpe, “Comparative evaluation of Intel RealSense D415, D435i, D455 and Microsoft Azure Kinect DK sensors for 3D vision applications,” IEEE Access, 2024.

L. Nwankwo, C. Fritze, K. Bartsch, and E. Rueckert, “ROMR: A ROSbased open-source mobile robot,” HardwareX, vol. 14, p. e00426, 2023.

J. Qin, S. Zhang, Y. Wang, F. Yang, X. Zhong, and W. Lu, “Improved skeleton-based activity recognition using convolutional block attention module,” Computers and Electrical Engineering, vol. 116, p. 109231,2024.

J. F. Hu, J. Sun, Z. Lin, J. H. Lai, W. Zeng, and W. S. Zheng, “APANet: Auto-path aggregation for future instance segmentation prediction,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.44, no. 7, pp. 3386–3403, 2021.

H. Kumar, A. Koppel, and A. Ribeiro, “On the sample complexity of actor-critic method for reinforcement learning with function approximation,” Machine Learning, vol. 112, no. 7, pp. 2433–2467, 2023.

P. Liu, X. Ma, J. Ding, and C. Gu, “Multi-agent collaborative path planning algorithm with reinforcement learning and combined prioritized experience replay in Internet of Things,” Computers and Electrical Engineering, vol. 116, p. 109193, 2024.