Design and implementation of a real-time object detection and localization system using Yolov8n and Ros2
DOI:
https://doi.org/10.17979/ja-cea.2026.47.13754Keywords:
Robotics technology, Perception and sensing, Model validation, Machine Learning, Image processing, Real-time algorithmsAbstract
This paper presents the design and implementation of a real-time visual perception system for bimanual assistive robotics. By retraining a YOLOv8-nano model with a custom, manually labeled dataset and its subsequent integration into the ROS2 ecosystem using an RGB-D depth camera, three-dimensional detection and localization of daily objects are achieved. The system is encapsulated in Docker containers to guarantee portability and reproducibility across different hardware platforms. Experimental results demonstrate optimal performance in terms of computational accuracy and spatial estimation. This validates a modular architecture capable of balancing inference speed and model robustness against environmental variations through data augmentation techniques, laying the operational foundations for the three-dimensional control of upper-limb exoskeletons.
References
Catalán, J. M., Trigili, E., Nann, M., Blanco-Ivorra, A., Lauretti, C., Cordella, F., Ivorra, E., Armstrong, E., Crea, S., Alcañiz, M., et al., 2023. Hybrid brain/neural interface and autonomous vision-guided whole-arm exoskeleton control to perform activities of daily living (adls). Journal of Neuro-Engineering and Rehabilitation 20 (1), 61.
Crea, S., Nann, M., Trigili, E., Cordella, F., Baldoni, A., Badesa, F. J., Catalán, J. M., Zollo, L., Vitiello, N., Aracil, N. G., et al., 2018. Feasibility and safety of shared eeg/eog and vision-guided autonomous whole-arm exoskeleton control to perform activities of daily living. Scientific reports 8 (1), 10823.
Fares, N., Sherratt, R. S., Elhajj, I. H., 2021. Directing and orienting ict healthcare solutions to address the needs of the aging population. In: Healthcare. Vol. 9. MDPI, p. 147.
Frisoli, A., Barsotti, M., Sotgiu, E., Lamola, G., Procopio, C., Chisari, C., 2022. A randomized clinical control study on the efficacy of threedimensional upper limb robotic exoskeleton training in chronic stroke. Journal of neuroengineering and rehabilitation 19 (1), 14.
Irles, C. F., Ruiz, F. J. M., Ivorra, A. B., Cerdán, E. B., Orts, J. M. C., Aracil, N. G., 2024. Diseño mecánico de un exoesqueleto bimanual para la asistencia en actividades de la vida diaria. Jornadas de Automática (45).
Izzo, C., Carrizzo, A., Alfano, A., Virtuoso, N., Capunzo, M., Calabrese, M., De Simone, E., Sciarretta, S., Frati, G., Oliveti, M., et al., 2018. The impact of aging on cardio and cerebrovascular diseases. International journal of molecular sciences 19 (2), 481.
Jocher, G., Chaurasia, A., Qiu, J., 2023. Ultralytics yolov8. URL: https://github.com/ultralytics/ultralytics
Pantoni, L., Poggesi, A., Inzitari, D., 2009. Cognitive decline and dementia related to cerebrovascular diseases: some evidence and concepts. Cerebrovascular Diseases 27 (Suppl. 1), 191–196.
Park, D., Hoshi, Y., Mahajan, H. P., Kim, H. K., Erickson, Z., Rogers, W. A., Kemp, C. C., 2020. Active robot-assisted feeding with a general-purpose mobile manipulator: Design, evaluation, and lessons learned. Robotics and Autonomous Systems 124, 103344.
Salomon, J. A., Vos, T., Hogan, D. R., Gagnon, M., Naghavi, M., Mokdad, A., Begum, N., Shah, R., Karyana, M., Kosen, S., et al., 2012. Common values in assessing health outcomes from disease and injury: disability weights measurement study for the global burden of disease study 2010. The Lancet 380 (9859), 2129–2143.
Tkachenko, M., Malyuk, M., Holmanyuk, A., Liubimov, N., 2020. Label Studio: Data labeling software. Open source software available from https://github.com/HumanSignal/label-studio.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Asier Reig-Lozano, David Martínez-Pascual, Raúl Martín-Batanero, Daniel Rodríguez-López, Luís D. Lledó, Nicolás García-Aracil
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
