Hostname: page-component-669899f699-rg895 Total loading time: 0 Render date: 2025-04-24T11:41:10.715Z Has data issue: false hasContentIssue false
  • English
  • Français

Deep learning-based landmark detection and localization for autonomous robots in outdoor settings

Published online by Cambridge University Press:  16 April 2025

M. Anuradha Open the ORCID record for M. Anuradha [Opens in a new window] ,
V. Bibin Christopher ,
Francis H. Shajin  and
S. V. Annlin Jeba
M. Anuradha*
Affiliation:
Department of Computer Science and Engineering, S.A. Engineering College, Tamil Nadu, India
V. Bibin Christopher
Affiliation:
Department of Computing Technologies, School of Computing, Faculty of Engineering and Technology, SRM Institute of Science and Technology, Kattankulathur, Chennai, Tamil Nādu, India
Francis H. Shajin
Affiliation:
Department of Electronics and Communication Engineering, Xpertmindz Innovative Solutions Private Limited, Kuzhithurai, Tamil Nadu, India
S. V. Annlin Jeba
Affiliation:
Department of Computer Science and Engineering, Sree Buddha College of Engineering, Pattoor, Kerala, India
*
Corresponding author: M. Anuradha; Email: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

Navigation is an important skill required for an autonomous robot, as information about the location of the robot is necessary for making decisions about upcoming events. The objective of the localization technique is “to know about the location of the collected data.” In previous works, several deep learning methods were used to detect localization, but none of them gives sufficient accuracy. To address this issue, an Enhanced Capsule Generation Adversarial Network and optimized Dual Interactive Wasserstein Generative Adversarial Network for landmark detection and localization of autonomous robots in outdoor environments (ECGAN-DIWGAN-RSO-LAR) is proposed in this manuscript. Here, the outdoor robot localization dataset is taken from the Virtual KITTI dataset. It contains two phases, which are landmark detection and localization. The landmark detection phase is determined using Enhanced Capsule Generation Adversarial Network for detecting the landmark of the captured image. Then the robot localization phase is determined using Dual Interactive Wasserstein Generative Adversarial Network (DIWGAN) for determining the robot location coordinates as well as compass orientation from identified landmarks. After that, the weight parameters of the DIWGAN are optimized by Rat Swarm Optimization (RSO) algorithm. The proposed ECGAN-DIWGAN-RSO-LAR is implemented in Python. The efficiency of the proposed ECGAN-DIWGAN-RSO-LAR technique shows higher accuracy of 22.67%, 12.45 %, and 8.89% compared to the existing methods.

Keywords

enhanced capsule generation adversarial networkdual interactive Wasserstein generative adversarial networkrobot localizationrat swarm optimizationlandmark detection
Type
Research Article
Information
Robotica , First View , pp. 1 - 17
Copyright
© The Author(s), 2025. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Panigrahi, P. K. and Bisoy, S. K., “Localization strategies for autonomous mobile robots: A review,” J. King Saud Univ.-Comput. Inf. Sci. (2021).CrossRefGoogle Scholar
Wan, L., Sun, Y., Sun, L., Ning, Z. and Rodrigues, J. J., “Deep learning based autonomous vehicle super resolution DOA estimation for safety driving,” IEEE Trans. Intell. Transp. 22(7), 4301–4315 (2020).CrossRefGoogle Scholar
Ma, Y., Wang, Z., Yang, H. and Yang, L., “Artificial intelligence applications in the development of autonomous vehicles: A survey,” IEEE/CAA J. Automat. Sinica 7(2), 315–329 (2020).CrossRefGoogle Scholar
Chen, S., Dong, J., Ha, P., Li, Y. and Labi, S., “Graph neural network and reinforcement learning for multi-agent cooperative control of connected autonomous vehicles,” Comput.-AIDED Civil Infrast Inf. 36(7), 838–857 (2021).CrossRefGoogle Scholar
Xiong, Z., Cai, Z., Han, Q., Alrawais, A. and Li, W., “ADGAN: Protect your location privacy in camera data of auto-driving vehicles,” IEEE Trans. Ind. Inf. 17(9), 6200–6210 (2020).Google Scholar
Luo, Q., Cao, Y., Liu, J. and Benslimane, A., “Localization and navigation in autonomous driving: Threats and countermeasures,” IEEE Wirel Commun. 26(4), 38–45 (2020).Google Scholar
Li, C., Fu, Y., Yu, F. R., Luan, T. H. and Zhang, Y., “Vehicle position correction: A vehicular blockchain networks-based GPS error sharing framework,” IEEE Trans. Intell. Transp. 22(2), 898–912 (2020).CrossRefGoogle Scholar
Chen, S., Liu, B., Feng, C., Vallespi-Gonzalez, C. and Wellington, C., “3d point cloud processing and learning for autonomous driving: Impacting map creation, localization, and perception,” IEEE Signal Proc. Mag. 38(1), 68–86 (2020).CrossRefGoogle Scholar
Esfahani, M. A., Wang, H., Wu, K. and Yuan, S., “AbolDeepIO: A novel deep inertial odometry network for autonomous vehicles,” IEEE Trans. Intell. Transp. 21(5), 1941–1950 (2019).CrossRefGoogle Scholar
Taghavifar, H., Hu, C., Qin, Y. and Wei, C., “EKF-neural network observer based type-2 fuzzy control of autonomous vehicles,” IEEE Trans. Intell. Transp. 22(8), 4788–4800 (2020).Google Scholar
Hu, C., Chen, Y. and Wang, J., “Fuzzy observer-based transitional path-tracking control for autonomous vehicles,” IEEE Trans. Intell. Transp. 22(5), 3078–3088 (2020).Google Scholar
Yaqoob, I., Khan, L. U., Kazmi, S. A., Imran, M., Guizani, N. and Hong, C. S., “Autonomous driving cars in smart cities: Recent advances, requirements, and challenges,” IEEE Network 34(1), 174–181 (2019).CrossRefGoogle Scholar
Wang, L., Fan, X., Chen, J., Cheng, J., Tan, J. and Ma, X., “3D object detection based on sparse convolution neural network and feature fusion for autonomous driving in smart cities,” Sustain. Cities Soc. 54, 102002 (2020).CrossRefGoogle Scholar
Toft, C., Maddern, W., Torii, A., Hammarstrand, L., Stenborg, E., Safari, D., Okutomi, M., Pollefeys, M., Sivic, J., Pajdla, T. and Kahl, F., “Long-term visual localization revisited,” IEEE Trans. Pattern Anal. 44(4), 2074–2088 (2020).CrossRefGoogle Scholar
Guo, Y., Xu, Y. and Li, S., “Dense construction vehicle detection based on orientation-aware feature fusion convolutional neural network,” Automat. Constr. 112, 103124 (2020).CrossRefGoogle Scholar
Annapoorna, B.R., and Babu, D.R. “Detection and localization of cotton based on deep neural networks.” Materials Today: Proceedings, 80 (2023) pp.3328-3332.Google Scholar
Annapoorna, B.R; Mrs. Shanthi, M. B; and Dr. Jitendranath, Mungara "A Secure Packet Hiding Technique For Preventing Jamming Attacks," International Journal Of Smart Sensor And Adhoc Network: 3(1), (2012) Article 7.Google Scholar
Nimeshika, G.N., and Subitha, D.. “Enhancing Alzheimer’s disease classification through split federated learning and GANs for imbalanced datasets.” PeerJ Computer Science, 10 (2024) p.e2459.CrossRefGoogle Scholar
Fusic, S. J., Kanagaraj, G., Hariharan, K. and Karthikeyan, S., “Optimal path planning of autonomous navigation in outdoor environment via heuristic technique,” Transp. Res. Interdiscip. perspect. 12, 100473 (2021).Google Scholar
dataset-https://europe.naverlabs.com/research/computer-vision/proxy-virtual-worlds-vkitti-2/.Google Scholar
Grabowsky, D. P., Conrad, J. M. and Browne, A. F., “A Breadcrumb System for Assisting Outdoor Autonomous Robots with Path Identification and Localization”,” In: SoutheastCon (IEEE, 2021) pp. 1–6.Google Scholar
Shamsolmoali, P., Zareapoor, M., Shen, L., Sadka, A. H. and Yang, J., “Imbalanced data learning by minority class augmentation using capsule adversarial networks,” Neurocomputing 459, 481–493 (2021).Google Scholar
Hu, Z., Xue, H., Zhang, Q., Gao, J., Zhang, N., Zou, S., Teng, Y., Liu, X., Yang, Y., Liang, D. and Zhu, X., “DPIR-Net: Direct PET image reconstruction based on the Wasserstein generative adversarial network,” IEEE Trans. Radiat. Plasma Med. Sci. 5(1), 35–43 (2020).Google Scholar
Li, C., Wang, S., Zhuang, Y. and Yan, F., “Deep sensor fusion between 2D laser scanner and IMU for mobile robot localization,” IEEE Sens. J. 21(6), 8501–8509 (2019).CrossRefGoogle Scholar
Chen, X., Läbe, T., Milioto, A., Röhling, T., Behley, J. and Stachniss, C., “OverlapNet: A Siamese network for computing LiDAR scan similarity with applications to loop closing and localization,” Auton. Robot. 46(1), 61–81 (2022).Google Scholar
Li, G., Yu, L. and Fei, S., “A deep-learning real-time visual SLAM system based on multi-task feature extraction network and self-supervised feature points,” Measurement 168, 108403 (2021).Google Scholar
Wen, S., Zhao, Y., Yuan, X., Wang, Z., Zhang, D. and Manfredi, L., “Path planning for active SLAM based on deep reinforcement learning under unknown environments,” Intell. Serv. Rob. 13(2), 263–272 (2020).Google Scholar
Chhikara, P., Tekchandani, R., Kumar, N., Chamola, V. and Guizani, M., “DCNN-GA: A deep neural net architecture for navigation of UAV in indoor environment,” IEEE Internet Things J. 8(6), 4448–4460 (2020).CrossRefGoogle Scholar
Hu, H., Qiao, Z., Cheng, M., Liu, Z. and Wang, H., “Dasgil: Domain adaptation for semantic and geometric-aware image-based localization,” IEEE Trans. Image Process. 30, 1342–1353 (2020).Google ScholarPubMed
Tian, R., Zhang, Y., Feng, Y., Yang, L., Cao, Z., Coleman, S. and Kerr, D., “Accurate and robust object-oriented SLAM with 3D quadric landmark construction in outdoor environment. arXiv preprint 2110.08977 (2021).Google Scholar
Dhiman, G., Garg, M., Nagar, A., Kumar, V. and Dehghani, M., “A novel algorithm for global optimization: Rat swarm optimizer,” J. Amb. Intell. Hum. Comput. 12(8), 8457–8482 (2021).CrossRefGoogle Scholar
Wilson, A. J., Kiran, W. S., Radhamani, A. S. and Bharathi, M. P., “Optimizing energy-efficient cluster head selection in wireless sensor networks using a binarized spiking neural network and honey badger algorithm,” Knowl-BASED Syst. 112039 (2024).Google Scholar
Kanth, R. R. and Jacob, T. P., "Enhanced Capsule Generative Adversarial Network with Blockchain Fostered Intrusion Detection System for Enhancing Cyber security in Cloud," In: 2023 2nd International Conference on Smart Technologies and Systems for Next Generation Computing (ICSTSN) (IEEE, 2023) pp. 1–6.Google Scholar