Enhancing Collision Avoidance in Mobile Robots Using YOLOv5: A Lightweight Approach for Unstructured Environments

Saleel H. Abood; Hussein. M. H. Al-Khafaji; Mohanned M. H. Al-Khafaji

doi:10.18196/jrc.v6i2.25856

Authors

Saleel H. Abood University of Technology-Iraq
Hussein. M. H. Al-Khafaji University of Technology-Iraq
Mohanned M. H. Al-Khafaji University of Technology-Iraq

DOI:

https://doi.org/10.18196/jrc.v6i2.25856

Keywords:

Convolution Neural Network, YOLOv5 Detector, Object Detection, Mobile Robot, Collision Avoidance, Unstructured Environments, Real-Time Performance

Abstract

Mobile robots play a crucial role in Industry 4.0, particularly in dynamic and unstructured environments where moving obstacles present significant challenges. This study applies the YOLOv5 object detection algorithm to enhance robotic perception and obstacle avoidance. The primary objective is to improve the accuracy and speed of object detection in real-time scenarios, ensuring safer and more efficient navigation for robots. The research contribution lies in developing a lightweight YOLOv5 model optimised for robotic applications, capable of detecting objects with high accuracy. The model was trained on a diverse dataset of 10,700 images, including static and dynamic objects such as chairs, fans, fire extinguishers, and humans, captured under various conditions and orientations. The dataset was divided into training (70%), validation (15%), and testing (15%) subsets. The proposed model achieved a mean average precision (mAP) of 0.73 at a confidence threshold of 0.374, demonstrating superior performance compared to the YOLOv4 model in terms of accuracy and processing speed. Notably, the model excelled in detecting static objects such as chairs, achieving a perfect recognition rate of 1.00, while encountering challenges with moving objects such as humans due to motion blur and rapid changes in body posture. These findings highlight the model’s potential for real-time applications in industrial and unstructured environments. In conclusion, this study demonstrates that the enhanced YOLOv5 model significantly improves object detection and collision avoidance capabilities in robotic systems.

References

Z. Bai, "Advancements in robotics engineering: Transforming industries and society," in Int. Conf. Machine Learning and Automation, 2023, doi: 10.54254/2755-2721-/32/20230861.

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788, 2016.

Ş. Çiğdem, I. Meidute-Kavaliauskiene, and B. Yıldız, "Industry 4.0 and industrial robots: A study from the perspective of manufacturing company employees," Logistics, vol. 7, no. 1, p. 17, 2023.

D. Duan et al., "Industrial robots and firm productivity," Structural Change and Economic Dynamics, vol. 67, pp. 388–406, 2023.

D. A. Zebari, D. Q. Zeebaree, A. M. Abdulazeez, H. Haron, and H. N. A. Hamed, "Improved threshold-based and trainable fully automated segmentation for breast cancer boundary and pectoral muscle in mammogram images," IEEE Access, vol. 8, pp. 1–12, Nov. 2020, doi: 10.1109/ACCESS.2020.3036072.

J. Redmon and A. Farhadi, "YOLOv3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018.

A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "YOLOv4: Optimal speed and accuracy of object detection," arXiv preprint arXiv:2004.10934, 2020.

P. H. Rosen, E. Heinold, E. Fries-Tersch, and S. Wischniewski, “Advanced robotics and automation: implications for occupational safety and health,” Brussel: European Agency for Safety and Health at Work. vol. 10, p. 789276, 2022.

S. K. Sahoo and B. B. Choudhury, "Challenges and opportunities for enhanced patient care with mobile robots in healthcare," J. Mechatronics Artif. Intell. Eng., vol. 4, no. 2, pp. 83–103, 2023.

M. L. Ali and Z. Zhang, "The YOLO framework: A comprehensive review of evolution, applications, and benchmarks in object detection," Computers, vol. 13, no. 12, p. 336, 2024.

A. Sundaresan Geetha, M. A. R. Alif, M. Hussain, and P. Allen, “Comparative Analysis of YOLOv8 and YOLOv10 in Vehicle Detection: Performance Metrics and Model Efficacy,” Vehicles, vol. 6, no. 3, pp. 1364-1382, 2024.

J. Terven, D.-M. Córdova-Esparza, and J.-A. Romero-González, "A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS," Machine Learning and Knowledge Extraction, vol. 5, no. 4, pp. 1680–1716, 2023.

Z. Fatima, S. Zardari, and M. H. Tanveer, "Advancing industrial object detection through domain adaptation: A solution for industry 5.0," Actuators, vol. 13, no. 12, 2024.

W. Hanafi and M. Tamali, "Implementing distributed collaboration and applying the YOLO algorithm to robots," Studies in Engineering and Exact Sciences, vol. 5, no. 1, pp. 277–296, 2024.

D. H. Dos Reis, D. Welfer, M. A. De Souza Leite Cuadros, and D. F. T. Gamarra, "Mobile robot navigation using an object recognition software with RGBD images and the YOLO algorithm," Appl. Artif. Intell., vol. 33, no. 14, pp. 1290–1305, 2019.

A. Aljaafreh et al., "A real-time olive fruit detection for harvesting robot based on YOLO algorithms," Acta Technologica Agriculturae, vol. 26, no. 3, pp. 121–132, 2023.

G. Liu, Y. Hu, Z. Chen, J. Guo, and P. Ni, "Lightweight object detection algorithm for robots with improved YOLOv5," Eng. Appl. Artif. Intell., vol. 123, p. 106217, 2023.

Q. Song, S. Li, Q. Bai, J. Yang, X. Zhang, Z. Li, and Z. Duan, "Object detection method for grasping robot based on improved YOLOv5," Micromachines, vol. 12, no. 11, p. 1273, 2021.

Z. Chen, X. Li, L. Wang, Y. Shi, Z. Sun, and W. Sun, "An object detection and localization method based on improved YOLOv5 for the teleoperated robot," Appl. Sci., vol. 12, no. 22, p. 11441, 2022.

F. Wang and X. Li, "Research on Warehouse Object Detection for Mobile Robot Based on YOLOv5," 2023 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), pp. 1196-1200, 2023.

Z. Li, C. Pang, C. Dong, and X. Zeng, "R-YOLOv5: A lightweight rotational object detection algorithm for real-time detection of vehicles in dense scenes," IEEE Access, vol. 11, pp. 61546–61559, 2023.

R. Khanam and M. Hussain, "What is YOLOv5: A deep look into the internal features of the popular object detector," arXiv preprint arXiv:2407.20892, 2024.

G. Lavanya and S. D. Pande, "Enhancing real-time object detection with YOLO algorithm," EAI Endorsed Trans. Internet Things, vol. 10, 2024.

A. S. Geetha, "Comparing YOLOv5 variants for vehicle detection: A performance analysis," arXiv preprint arXiv:2408.12550, 2024.

P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, "A review of YOLO algorithm developments," Procedia Comput. Sci., vol. 199, pp. 1066–1073, 2021.

K. Saranya, J. J. R. Jegaraj, K. R. Kumar, and G. V. Rao, "Artificial intelligence based selection of optimal cutting tool and process parameters for effective turning and milling operations," J. Inst. Eng. (India): Ser. C, vol. 99, pp. 381–392, Aug. 2018.

S. Han, X. Dong, X. Hao, and S. Miao, "Extracting objects’ spatial–temporal information based on surveillance videos and the digital surface model," ISPRS Int. J. Geo-Inf., vol. 11, no. 2, p. 103, 2022.

J. Lim, J. Lee, C. An, and E. Park, "Enhancing real‐time traffic volume prediction: A two‐step approach of object detection and time series modelling," IET Intell. Transp. Syst., vol. 18, no. 12, pp. 2744–2758, 2024.

G. Jocher et al., "ultralytics/yolov5: v6.2-yolov5 classification models, apple m1, reproducibility, clearml and deci.ai integrations," Zenodo, 2022.

C. Limberg, A. Melnik, A. Harter, and H. J. Ritter, "YOLO - You only look 10647 times," arXiv preprint arXiv:2201.06159, 2022.

Z. Wang et al., "Improved small object detection algorithm CRL-YOLOv5," Sensors, vol. 24, no. 19, p. 6437, 2024.

S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, "Path aggregation network for instance segmentation," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 8759-8768, 2018.

A. Benjumea, I. Teeti, F. Cuzzolin, and A. Bradley, "YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles," arXiv preprint arXiv:2112.11798, 2023.

D. C. Ciresan, U. Meier, J. Masci, L. Maria Gambardella, and J. Schmidhuber, "Flexible, high performance convolutional neural networks for image classification," in Proc. 22nd Int. Joint Conf. Artif. Intell., vol. 22, no. 1, 2011.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Adv. Neural Inf. Process. Syst., vol. 25, 2012.

G. I. Molina Learning to detect deepfakes: Benchmarks and algorithms. M.S. thesis, Universitat Pompeu Fabra, 2020.

P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. CVPR 2001, vol. 1, 2001.

Y. Xiao, X. Wang, P. Zhang, F. Meng, and F. Shao, "Object detection based on Faster R-CNN algorithm with skip pooling and fusion of contextual information," Sensors, vol. 20, no. 19, p. 5490, Sep. 2020.

C. C. Aggarwal. Neural Networks and Deep Learning: A Textbook. Cham: Springer, 2018.

K. Gaurav, A. K. Sahoo, and S. K. Mishra, "Nonlinear system identification using functional link multilayer perceptron artificial neural networks," Int. J. Eng. Res., vol. 10, no. 44, p. 6, 2015.

D. A. Zebari, D. Q. Zeebaree, A. M. Abdulazeez, H. Haron, and H. N. A. Hamed, "Improved threshold based and trainable fully automated segmentation for breast cancer boundary and pectoral muscle in mammogram images," IEEE Access, vol. 8, pp. 1–12, Nov. 2020.

S. Liu et al., "DAB-DETR: Dynamic anchor boxes are better queries for DETR," arXiv preprint arXiv:2201.12329, 2022.

T. Kong, F. Sun, H. Liu, Y. Jiang, L. Li and J. Shi, "FoveaBox: Beyound Anchor-Based Object Detection," in IEEE Transactions on Image Processing, vol. 29, pp. 7389-7398, 2020.

V. Varadarajan, D. Garg, and K. Kotecha, "An efficient deep convolutional neural network approach for object detection and recognition using a multi-scale anchor box in real-time," Future Internet, vol. 13, no. 12, p. 307, 2021.

S.-S. Park, V.-T. Tran, and D.-E. Lee, "Application of various YOLO models for computer vision-based real-time pothole detection," Appl. Sci., vol. 11, no. 23, p. 11229, 2021.

B. R. Paudel, D. Senarathna, H. Wang, S. Tragoudas, Y. Hu and S. Jiang, "Predicting YOLO Misdetection by Learning Grid Cell Consensus," 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 643-648, 2021.

C. Limberg, A. Melnik, A. Harter, and H. Ritter, "YOLO--You only look 10647 times," arXiv preprint arXiv:2201.06159, 2022.

S. N. Tesema and E. -B. Bourennane, "Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection," 2021 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), pp. 145-152, 2021.

C. Limberg, A. Melnik, H. Ritter, and H. Prendinger, "YOLO: You Only Look 10647 Times," INSTICC, pp. 153–160, 2023.

D. Novaković, N. Vasić, S. Novaković, D. Kostić, R. Bianchini, "{DeepDive}: Transparently identifying and managing performance interference in virtualized environments," in 2013 USENIX Annual Technical Conference (USENIX ATC 13), pp. 219-230, 2013.

D. Jayakumar and S. Peddakrishna, "Performance evaluation of YOLOv5-based custom object detection model for campus-specific scenario," Proc.-Int. J. Exp. Res. Rev., 2024.

R. Kaur and S. Singh, "A comprehensive review of object detection with deep learning," Digit. Signal Process., vol. 132, p. 103812, 2023.

C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors," Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 7464-7475, 2023.

T. Diwan, G. Anirudh, and J. V. Tembhurne, "Object detection using YOLO: Challenges, architectural successors, datasets and applications," Multimed. Tools Appl., vol. 82, no. 6, pp. 9243–9275, Mar. 2023.

S. Zhang, C. Qu, C. Ru, X. Wang, and Z. Li, "Multi-objects recognition and self-explosion defect detection method for insulators based on lightweight GhostNet-YOLOv4 model deployed on board UAV," IEEE Access, vol. 11, pp. 61546–61559, 2023.

T. Gandor and J. Nalepa, "First gradually, then suddenly: Understanding the impact of image compression on object detection using deep learning," Sensors, vol. 22, no. 3, p. 1104, 2022.

D. Zhao, F. Shao, L. Yang, X. Luo, Q. Liu, H. Zhang, and Z. Zhang, “Object detection based on an improved YOLOv7 model for unmanned aerial-vehicle patrol tasks in controlled areas,” Electronics, vol. 12, no. 23, p. 4887, 2023.

J. H. Kim, N. Kim, Y. W. Park, and C. S. Won, "Object detection and classification based on YOLO-V5 with improved maritime dataset," J. Mar. Sci. Eng., vol. 10, no. 3, p. 377, 2022.

A. R. Pathak, M. Pandey, and S. Rautaray, “Application of deep learning for object detection,” Procedia computer science, vol. 132, pp. 1706-1717, 2018.

S. Liu, H. Zhou, C. Li, and S. Wang, "Analysis of Anchor-Based and Anchor-Free Object Detection Methods Based on Deep Learning," 2020 IEEE International Conference on Mechatronics and Automation (ICMA), pp. 1058-1065, 2020.