Deep Learning and Visual SLAM for Autonomous Navigation of UAVs: Status, Challenges, and Future Perspectives

Keyu Long

doi:10.54097/wyseqa62

Authors

Keyu Long

DOI:

https://doi.org/10.54097/wyseqa62

Keywords:

Deep learning, SLAM, unmanned aerial vehicle, autonomous navigation.

Abstract

This paper discusses the application and integration of deep learning and visual SLAM technology in UAV autonomous navigation. With the wide application of UAVs in the fields of transportation, agriculture, military and environmental monitoring, improving the autonomous navigation capabilities of UAVs has become an important demand. This paper first analyses the advantages and disadvantages of deep learning and visual SLAM. Then, this paper emphasizes the core role of deep learning in feature extraction, target recognition and path planning. The key role of visual SLAM in real-time localization and environment mapping is highlighted as well. This paper discusses the combined application of these two technologies and demonstrates how to enhance the stability and accuracy of visual SLAM systems through deep learning in complex dynamic environments. Although the current technology still faces high computational requirements and real-time challenges, this paper proposes future research direction to promote the continued development of UAV autonomous navigation technology.

Downloads

Download data is not yet available.

References

[1] H. Samma and S. El-Ferik, et al. Autonomous UAV Visual Navigation Using an Improved Deep Reinforcement Learning. In IEEE Access, 2024, vol. 12, pp. 79967-79977.

[2] I. M. Murwantara, B. Hardjono, H. Tjahyadi and A. S. Putra, et al. A Consolidation of SLAM and Signal Reference Point for Autonomous Robot Navigation. 2020 IEEE 17th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET), Charlotte, NC, USA, 2020, pp. 108-112.

[3] W. M. Wong, C. Lim, C. -D. Lee, L. Wang, S. -C. Chen and P. -K. Tsung, et al. KRF-SLAM: A Robust AI Slam Based On Keypoint Resampling And Fusion. 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, 2020, pp. 296-299.

[4] M. Dhinakaran, R. T. Rajasekaran, V. Balaji, V. Aarthi and S. Ambika, et al. Advanced Deep Reinforcement Learning Strategies for Enhanced Autonomous Vehicle Navigation Systems. 2024 2nd International Conference on Computer, Communication and Control (IC4), Indore, India, 2024, pp. 1-4.

[5] A. Nazir and M. A. Wani, et al. You Only Look Once - Object Detection Models: A Review. 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, 2023, pp. 1088-1095.

[6] S. Ren, K. He, R. Girshick and J. Sun, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 1 June 2017.

[7] D. Li and X. Chen, et al. Lane Line Segmentation Based on Comparative Analysis of Three Convolutional Neural Networks SegNet, U-Net and Attention-U-Net. 2024 IEEE 2nd International Conference on Control, Electronics and Computer Technology (ICCECT), Jilin, China, 2024, pp. 1002-1009.

[8] C. L. Xu et al., Et al. Research on ORB-SLAM Autonomous Navigation Algorithm. 2019 IEEE 9th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), Suzhou, China, 2019, pp. 1182-1186.

[9] S. Anandharaman, M. Sudhakaran and R. Seyezhai, et al. A low-cost visual navigation and mapping system for Unmanned Aerial Vehicle using LSD-SLAM algorithm. 2016 Online International Conference on Green Engineering and Technologies (IC-GET), Coimbatore, India, 2016, pp. 1-6.

[10] H. Pu, J. Luo, G. Wang, T. Huang, H. Liu and J. Luo, et al. Visual SLAM Integration with Semantic Segmentation and Deep Learning: A Review. In IEEE Sensors Journal, vol. 23, no. 19, pp. 22119-22138, 1 Oct.1, 2023.

[11] Z. Li, W. GAO, H. Chen and S. Zhang, et al. USP-SLAM: Deep Learning Based Visual SLAM with Robust Feature Extraction under Dynamic Environments. 2023 IEEE International Conference on Robotics and Biomimetics (ROBIO), Koh Samui, Thailand, 2023, pp. 1-6.

[12] S. Mokssit, D. B. Licea, B. Guermah and M. Ghogho, et al. Deep Learning Techniques for Visual SLAM: A Survey. In IEEE Access, 2023, vol. 11, pp. 20026-20050.

[13] R. Li, S. Wang and D. Gu, et al. DeepSLAM: A Robust Monocular SLAM System With Unsupervised Deep Learning. in IEEE Transactions on Industrial Electronics, vol. 68, no. 4, pp. 3577-3587, April 2021.

[14] Z. Li, W. GAO, H. Chen and S. Zhang, et al. USP-SLAM: Deep Learning Based Visual SLAM with Robust Feature Extraction under Dynamic Environments. 2023 IEEE International Conference on Robotics and Biomimetics (ROBIO), Koh Samui, Thailand, 2023, pp. 1-6.

[15] B. GAO, H. Lang and J. Ren, et al. Stereo Visual SLAM for Autonomous Vehicles: A Review. 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Toronto, ON, Canada, 2020, pp. 1316-1322.