Authors : Dr. A. S. Shirkande; Dnyaneshwari Kale; Sonali Deokar; Yash Jagtap

Volume/Issue : Volume 11 - 2026, Issue 10 - October

Google Scholar : https://tinyurl.com/35wxyde8

DOI : https://doi.org/10.38124/ijisrt/26Oct723

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Flying autonomously in poor lighting is hard for unmanned aerial vehicles (UAVs) because obstacles must be both located and understood with little visible light. This survey examines twenty works on vision-based avoidance, LiDAR ranging, multi-modal perception, embedded deep learning, flight-controller and companion-computer design, and low-light or infrared detection. Cameras supply object semantics but degrade in darkness and give no direct range; LiDAR gives dependable distance but cannot name what it detects. Fusing the two compensates for each weakness, while compact neural detectors make onboard recognition increasingly feasible. Drawing on these findings, we propose a quadrotor architecture built around a Pixhawk flight controller and a Raspberry Pi companion computer with a night-vision camera, LiDAR, GPS and a telemetry link. The Raspberry Pi handles image-based classification; the Pixhawk keeps exclusive charge of stabilization and motor control. The design targets low-light surveillance and semi-autonomous navigation, and we outline the metrics needed to validate it: detection accuracy, ranging error, end-to-end latency, energy use and endurance.

Keywords : UAV, Autonomous Drone, LiDAR, Night Vision, Object Detection, YOLO, Raspberry Pi, Pixhawk, Sensor Fusion, Obstacle Avoidance.

References :

1. A. Kumar, S. Jain, R. Khajuria, P. Goswami, and P. Dayal, “Night-vision surveillance: Raspberry Pi-based human detection in dark,” in Data Science and Applications (Lecture Notes in Networks and Systems, vol. 1237). Singapore: Springer, 2025, pp. 471–483, doi: 10.1007/978-981-96-1185-0_36.
2. K. Sarmalkar, S. Jain, and S. Hangal, “Vision based obstacle avoidance system for autonomous aerial systems,” Int. J. Eng. Res. Technol., vol. 9, no. 3, pp. 730–734, 2021, doi: 10.17577/IJERTCONV9IS03154.
3. S. Ramasamy, R. Sabatini, A. Gardi, and J. Liu, “LIDAR obstacle warning and avoidance system for unmanned aerial vehicle sense-and-avoid,” Aerosp. Sci. Technol., vol. 55, pp. 344–358, 2016, doi: 10.1016/j.ast.2016.05.020.
4. B. M. Pedro et al., “On the development of a sense and avoid system for small fixed-wing UAV,” Sensors, vol. 25, no. 8, Art. no. 2460, 2025, doi: 10.3390/s25082460.
5. L. Meier, P. Tanskanen, L. Heng, G. H. Lee, F. Fraundorfer, and M. Pollefeys, “PIXHAWK: A micro aerial vehicle design for autonomous flight using onboard computer vision,” Auton. Robots, vol. 33, nos. 1–2, pp. 21–39, 2012.
6. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 779–788.
7. Dronecode Foundation, “PX4 Autopilot user guide,” 2026. [Online]. Available: https://docs.px4.io
8. MAVLink Development Team, “MAVLink developer guide,” 2026. [Online]. Available: https://mavlink.io
9. Raspberry Pi Ltd., “Raspberry Pi 4 Model B datasheet.” [Online]. Available: https://datasheets.raspberrypi.com
10. u-blox AG, “NEO-6 series data sheet.” [Online]. Available: https://www.u-blox.com
11. Z. Ma, W. Yao, Y. Niu, B. Lin, and T. Liu, “UAV low-altitude obstacle detection based on the fusion of LiDAR and camera,” Auton. Intell. Syst., vol. 1, Art. no. 12, 2021, doi: 10.1007/s43684-021-00014-y.
12. D. Wang, W. Li, X. Liu, N. Li, and C. Zhang, “UAV environmental perception and autonomous obstacle avoidance: A deep learning and depth camera combined solution,” Comput. Electron. Agric., vol. 175, Art. no. 105523, 2020, doi: 10.1016/j.compag.2020.105523.
13. Q. Liang, Z. Wang, Y. Yin, W. Xiong, J. Zhang, and Z. Yang, “Autonomous aerial obstacle avoidance using LiDAR sensor fusion,” PLOS ONE, vol. 18, no. 6, Art. no. e0287177, 2023, doi: 10.1371/journal.pone.0287177.
14. S. Bultmann, J. Quenzel, and S. Behnke, “Real-time multi-modal semantic fusion on unmanned aerial vehicles with label propagation for cross-domain adaptation,” Robot. Auton. Syst., vol. 159, Art. no. 104286, 2023, doi: 10.1016/j.robot.2022.104286.
15. C. Jiang et al., “Object detection from UAV thermal infrared images and videos using YOLO models,” Int. J. Appl. Earth Obs. Geoinf., vol. 112, Art. no. 102912, 2022, doi: 10.1016/j.jag.2022.102912.
16. L. Tan, X. Lv, X. Lian, and G. Wang, “YOLOv4_Drone: UAV image target detection based on an improved YOLOv4 algorithm,” Comput. Electr. Eng., vol. 93, Art. no. 107261, 2021, doi: 10.1016/j.compeleceng.2021.107261.
17. M. Z. Butt, N. Nasir, and R. B. A. Rashid, “A review of perception sensors, techniques, and hardware architectures for autonomous low-altitude UAVs in non-cooperative local obstacle avoidance,” Robot. Auton. Syst., vol. 173, Art. no. 104629, 2024.
18. X. Zhu, X. Zhao, J. Liu, W. Feng, and X. Fan, “Autonomous navigation and obstacle avoidance for orchard spraying robots: A sensor-fusion approach with ArduPilot, ROS, and EKF,” Agronomy, vol. 15, no. 6, Art. no. 1373, 2025, doi: 10.3390/agronomy15061373.
19. G. E. M. Abro, A. M. Khan, and S. M. Baghlaf, “A modular framework for advanced UAV control using Pixhawk–Raspberry Pi integration,” in Proc. IEEE Symp. Wireless Technol. Appl. (ISWTA), 2025, doi: 10.1109/ISWTA68114.2025.11329763.
20. A. Alkhatib et al., “A survey on obstacle detection and avoidance methods for UAVs,” Drones, vol. 9, no. 3, Art. no. 203, 2025, doi: 10.3390/drones9030203.