Hybrid Sensor-Fusion Navigation Algorithm Based on Fuzzy Logic for ESP32 Autonomous Robots
Keywords:
hybrid navigation, fuzzy logic, sensor fusion, ESP32-S3, line followerAbstract
Autonomous mobile robots in hospitals and logistics warehouses require rapid mode switching between line following and obstacle avoidance in real-time without losing position. The simple threshold approach widely adopted in industry yields slow transitions and frequent confusion when obstacles appear at the line edge. This study designs a hybrid navigation algorithm that combines a two-input fuzzy logic controller (obstacle distance and line status) with a complementary filter fusing IMU MPU6050 and QTR-8 line sensors, executed on ESP32-S3 using fixed-point arithmetic for computational efficiency. The system was tested on a hospital-corridor-like track with three scenarios covering sudden obstacles, sharp turns, and no-line areas. Across 60 trials, the system achieved a 96.3 percent success rate with zero collisions. The average transition time from line-following to obstacle-avoidance was 170 ms with a 23 ms standard deviation. Average power consumption was 2.4 watts and the control cycle latency was 6.2 ms at 100 Hz with a CPU load of 34 percent. Total component cost was IDR 850,000. The results demonstrate that combining fuzzy logic with fixed-point arithmetic can deliver navigation performance on low-cost hardware.
References
- A. R. Javed, Y. B. Zikria, S. ur Rehman, F. Shahzad, dan Z. Jalil, "Future Smart Cities Requirements, Emerging Technologies, Applications, Challenges, and Future Aspects," Cities, vol. 129, hal. 103794, 2022, doi: 10.1016/j.cities.2022.103794.
- W. Li et al., "A Comprehensive Survey on Machine Learning-Based Big Data Analytics for IoT-Enabled Smart Healthcare System," Mobile Netw. Appl., vol. 26, hal. 234–252, 2021, doi: 10.1007/s11036-020-01700-6.
- S. F. Nadirah, "Narrative Review: Penerapan Internet of Things dalam Monitoring Kesehatan Pasien Jarak Jauh," J. Sains Sist. Inf., vol. 3, no. 1, 2024, doi: 10.31602/tji.v3i1.17487.
- D. Rahmanda dan Martiano, "Sistem Pintu Rumah Berbasis IoT dengan Fitur Identifikasi Wajah Menggunakan Telegram," J. Sist. Inf. Teknol. Jaringan (SISFOTEKJAR), vol. 5, no. 1, hal. 31–36, 2024, doi: 10.63703/sisfotekjar.v5i1.29.
- M. H. Alfirdaus dan Martiano, "Perancangan dan Implementasi Sistem Monitoring Kualitas Udara Berbasis IoT," J. Sist. Inf. Teknol. Jaringan (SISFOTEKJAR), vol. 5, no. 1, hal. 24–30, 2024, doi: 10.63703/sisfotekjar.v5i1.28.
- A. F. Batubara dan Martiano, "Implementasi IoT untuk Sistem Monitoring Penggunaan Daya Listrik Secara Real-Time pada Lingkungan Rumah Tangga," J. Sist. Inf. Teknol. Jaringan (SISFOTEKJAR), vol. 5, no. 2, hal. 42–48, 2024, doi: 10.63703/sisfotekjar.v5i2.31.
- T. Lei, G. Li, C. Luo, L. Zhang, L. Liu, dan R. S. Gates, "An Informative Planning-Based Multi-Layer Robot Navigation System as Applied in a Poultry Barn," Intell. Robot., vol. 2, no. 4, hal. 313–332, 2022, doi: 10.20517/ir.2022.18.
- Y. Cui et al., "Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review," IEEE Trans. Intell. Transp. Syst., vol. 23, no. 2, hal. 722–739, 2022, doi: 10.1109/TITS.2020.3023541.
- X. Zhou et al., "Deep-Learning-Enhanced Multitarget Detection for End-Edge-Cloud Surveillance in Smart IoT," IEEE Internet Things J., vol. 8, no. 16, hal. 12588–12596, 2021, doi: 10.1109/JIOT.2021.3077449.
- J. Chen et al., "Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing," IEEE Trans. Ind. Inform., 2024, doi: 10.1109/TII.2019.2909473.
- S. Liang et al., "Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles," IEEE Trans. Intell. Transp. Syst., 2022, doi: 10.1109/TITS.2022.3146020.
- R. A. Amin, M. Hasan, V. Wiese, dan R. Obermaisser, "FPGA-Based Real-Time Object Detection and Classification System Using YOLO for Edge Computing," IEEE Access, vol. 12, hal. 73268–73278, 2024, doi: 10.1109/ACCESS.2024.3404623.
- J. S. Murthy, G. M. Siddesh, W.-C. Lai, B. D. Parameshachari, S. N. Patil, dan K. L. Hemalatha, "ObjectDetect: A Real-Time Object Detection Framework for Advanced Driver Assistant Systems Using YOLOv5," Wirel. Commun. Mob. Comput., vol. 2022, Art. no. 9444360, 2022, doi: 10.1155/2022/9444360.
- S. Fang, Z. Zhang, dan Y. Cao, "Improved Mask R-CNN Multi-Target Detection and Segmentation for Autonomous Driving in Complex Scenes," Sensors, vol. 23, no. 8, Art. no. 3853, 2023, doi: 10.3390/s23083853.
- U. Nepal dan H. Eslamiat, "Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs," Sensors, vol. 22, no. 2, Art. no. 464, 2022, doi: 10.3390/s22020464.
- M. Kraft, M. Piechocki, B. Ptak, dan K. Walas, "Autonomous, Onboard Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Unmanned Aerial Vehicle," Remote Sens., vol. 13, no. 5, Art. no. 965, 2021, doi: 10.3390/rs13050965.
- J. Wei, "A Review of YOLO Algorithm and Its Applications in Autonomous Driving Object Detection," IEEE Access, 2025, doi: 10.1109/ACCESS.2025.3559815.
- C. Y. Wang, A. Bochkovskiy, dan H. Y. M. Liao, "YOLOv1 to YOLOv10: The Fastest and Most Accurate Real-Time Object Detection Systems," APSIPA Trans. Signal Inf. Process., 2024, doi: 10.1561/116.20240014.
- H. Ren et al., "DCW-YOLO: Road Object Detection Algorithms for Autonomous Driving," IEEE Access, vol. 13, hal. 64020–64031, 2025, doi: 10.1109/ACCESS.2025.3556311.
- P. Liu, Z. Yang, D. Yang, dan T. Sun, "Design of an Interactive Visualization System for the Process Workflow of an Intelligent Sub-Assembly Workshop," J. Comput. Electron. Inf. Manag., vol. 16, no. 1, 2025, doi: 10.54097/hmwtzp15.
