Research Article
BibTex RIS Cite

Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration

Year 2025, Volume: 8 Issue: 2, 19 - 20
https://doi.org/10.34248/bsengineering.1594542

Abstract

In this study, the deep learning-based detection performance of instructions for the vehicle was examined through images obtained from a camera mounted on a mobile robotic system. The aim is to enhance the detection performance of a differential robot equipped with a robotic arm in recognizing various visual instructions it may encounter in the field. Traffic lights, direction signs, and speed limit signs were selected as the visual materials to be introduced to the robotic system. By utilizing the YOLOv8 object detection model on the embedded AI computer onboard the vehicle and leveraging the TensorRT accelerator, deep learning-based image processing achieved a high frame rate of 33 FPS and an mAP50 accuracy of 96.6%. This study highlights the advantages and challenges of integrating advanced detection models into autonomous robotic platforms, contributing to future improvements in reliability and efficiency.

References

  • Barba-Guaman L, Eugenio Naranjo J, Ortiz A. 2020. Deep learning framework for vehicle and pedestrian detection in rural roads on an embedded GPU. Electronics, 9(4): 589.
  • Cai ZX, Gu MQ. 2013. Traffic sign recognition algorithm based on shape signature and dual-tree complex wavelet transform. J Cent South Univ, 20(2): 433–439.

Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration

Year 2025, Volume: 8 Issue: 2, 19 - 20
https://doi.org/10.34248/bsengineering.1594542

Abstract

Bu çalışmada, mobil robotik bir sisteme monte edilmiş bir kameradan elde edilen görüntüler aracılığıyla, aracın görsel talimatları algılama performansı derin öğrenme tabanlı yöntemlerle incelenmiştir. Amaç, sahada karşılaşabileceği çeşitli görsel talimatları tanımada diferansiyel bir robota bağlı robotik kolun tespit performansını artırmaktır. Trafik ışıkları, yön tabelaları ve hız sınırı levhaları, robotik sisteme tanıtılacak görsel materyaller olarak seçilmiştir. Araç üzerindeki gömülü yapay zeka bilgisayarında YOLOv8 nesne tespiti modeli kullanılarak ve TensorRT hızlandırıcısından faydalanılarak derin öğrenme tabanlı görüntü işleme, 33 FPS gibi yüksek bir kare hızı ve %96,6 mAP50 doğruluğuna ulaşmıştır. Bu çalışma, gelişmiş tespit modellerinin otonom robotik platformlara entegrasyonunun avantajlarını ve zorluklarını vurgulamakta, gelecekte güvenilirlik ve verimlilik açısından iyileştirmelere katkı sunmaktadır.

References

  • Barba-Guaman L, Eugenio Naranjo J, Ortiz A. 2020. Deep learning framework for vehicle and pedestrian detection in rural roads on an embedded GPU. Electronics, 9(4): 589.
  • Cai ZX, Gu MQ. 2013. Traffic sign recognition algorithm based on shape signature and dual-tree complex wavelet transform. J Cent South Univ, 20(2): 433–439.
There are 2 citations in total.

Details

Primary Language English
Subjects Electrical Engineering (Other)
Journal Section Research Articles
Authors

Ibrahim Shamta 0009-0003-1280-679X

Funda Demir 0000-0001-7707-8496

Publication Date
Submission Date December 2, 2024
Acceptance Date January 9, 2025
Published in Issue Year 2025 Volume: 8 Issue: 2

Cite

APA Shamta, I., & Demir, F. (n.d.). Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration. Black Sea Journal of Engineering and Science, 8(2), 19-20. https://doi.org/10.34248/bsengineering.1594542
AMA Shamta I, Demir F. Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration. BSJ Eng. Sci. 8(2):19-20. doi:10.34248/bsengineering.1594542
Chicago Shamta, Ibrahim, and Funda Demir. “Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration”. Black Sea Journal of Engineering and Science 8, no. 2 n.d.: 19-20. https://doi.org/10.34248/bsengineering.1594542.
EndNote Shamta I, Demir F Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration. Black Sea Journal of Engineering and Science 8 2 19–20.
IEEE I. Shamta and F. Demir, “Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration”, BSJ Eng. Sci., vol. 8, no. 2, pp. 19–20, doi: 10.34248/bsengineering.1594542.
ISNAD Shamta, Ibrahim - Demir, Funda. “Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration”. Black Sea Journal of Engineering and Science 8/2 (n.d.), 19-20. https://doi.org/10.34248/bsengineering.1594542.
JAMA Shamta I, Demir F. Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration. BSJ Eng. Sci.;8:19–20.
MLA Shamta, Ibrahim and Funda Demir. “Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration”. Black Sea Journal of Engineering and Science, vol. 8, no. 2, pp. 19-20, doi:10.34248/bsengineering.1594542.
Vancouver Shamta I, Demir F. Optimizing Visual Instruction Detection in Autonomous Mobile Robots Using Yolov8 and Tensorrt Acceleration. BSJ Eng. Sci. 8(2):19-20.

                                                24890