Real-Time Hazard-Free Planetary Landing using Deep Recurrent Neural Network

Authors

  • Janhavi Hemant Borse Department of Computer Engineering, SKNCOE, Savitribai Phule Pune University, Pune-India
  • Dipti Durgesh Patil Department of Information Technology, MKSSS's Cummins College of Engineering for women, Savitribai Phule Pune University, Pune-India
  • Vinod Kumar Director, Promotion Directorate, IN-SPACe, Executive Secretary, ASI Department of Space, Govt. of India, Bengaluru, INDIA – 560094

Keywords:

Convolutional Neural Network, Deep Neural Network, Hazard Detection, Terrain, Space Navigation, Space Guidance

Abstract

Accurate understanding and interpretation of the underlying field of view (FoV) are paramount in a real-time planetary landing. This understanding helps detect hazardous bodies and bypasses unfavourable situations well in advance. Existing planetary landing missions rely on the 3-dimensional digital elevation models (DEM) and achieve terrain-relative navigation. These DEMs are used as a reference for spotting the hazards on the pre-defined landing site. These are computationally intensive and time-consuming pattern-matching tasks. The primary concern is the existence of such DEMs before the missions and high storage requirements. This study aims to tackle the abovementioned drawbacks and build a robust intelligent system for autonomous hazard-free planetary landing. This paper utilizes the advanced deep learning approach for accurately detecting and positioning the hazards in the current FoVs using vision sensors of the spacecraft. Deep convolutional neural networks are utilized for feature extraction purposes. These features are further utilized by the recurrent neural network's region proposal algorithm to spot the distinct regions inside the current FoV. These proposals are the keys to detecting the hazards like craters and boulders. The detection results are interpreted by classifying the hazards into craters and boulders. It also classifies the safe landing region as a plain surface. Further, the classes are positioned accurately using the bounding boxes of the coco model. Transfer learning is used to build and train the network. The work also includes the creation of a valid planetary dataset required for generating a ground truth. The overall results are validated through comparative judgments and exhaustive analysis. Experimental results show that the transfer learning approach for hazard detection and localization achieved excellent results.

Downloads

Download data is not yet available.

References

V. K. Janhavi Borse, Dipti Patil, "DEEP SEMANTIC CLASSIFICATION OF VISUAL INPUTS FOR HAZARD-FREE LUNAR LANDING," vol. 3, no. June, pp. 14–18, 2021.

R. L. Hardy, "Multiquadric equations of topography and other irregular surfaces," J. Geophys. Res., vol. 76, no. 8, pp. 1905–1915, Mar. 1971, doi: 10.1029/jb076i008p01905.

K. S. P. Lancaster, "Surface generated by moving least squares methods," Math Comp, vol. 37, pp. 141–158, 1981.

J. Song, D. Rondao, and N. Aouf, "Deep learning-based spacecraft relative navigation methods: A survey," Acta Astronaut., vol. 191, pp. 22–40, Feb. 2022, doi: 10.1016/J.ACTAASTRO.2021.10.025.

D. E. Smith, M. T. Zuber, G. A. Neumann, and F. G. Lemoine, "Topography of the Moon from the Clementine lidar," J. Geophys. Res. E Planets, vol. 102, no. E1, pp. 1591–1611, 1997, doi: 10.1029/96JE02940.

"A tutorial on synthetic aperture radar," ieeexplore.ieee.org, doi: 10.1109/MGRS.2013.2248301.

M. Hidaka, M. Takahashi, T. Ishida, and S. Fukuda, "Terrain relative navigation enhanced with sar for moon's shadowed regions," AIAA Scitech 2020 Forum, vol. 1 PartF, no. January, pp. 3–14, 2020, doi: 10.2514/6.2020-0946.

M. S. R. A. C. Cook, P. D. Spudis, "Lunar topography and basins mapped using a Clementine stereo digital elevation model," Lunar Planet Sci, vol. 1, p. 1281, 2002.

J. Ping, Q. Huang, J. Yan, J. Cao, G. Tang, and R. Shu, "Lunar topographic model CLTM-s01 from Chang'E-1 laser altimeter," Sci. China, Ser. G Physics, Mech. Astron., vol. 52, no. 7, pp. 1105–1114, Jul. 2009, doi: 10.1007/s11433-009-0144-8.

H. Araki et al., "Lunar global shape and polar topography derived from Kaguya-LALT laser altimetry," Science (80-. )., vol. 323, no. 5916, pp. 897–900, Feb. 2009, doi: 10.1126/science.1164146.

Z. Cai, C. Zheng, Z. Tang, and D. Qi, "Lunar digital elevation model and elevation distribution model based on Chang'E-1 LAM data," Sci. China Technol. Sci., vol. 53, no. 9, pp. 2558–2568, Aug. 2010, doi: 10.1007/s11431-010-3180-8.

Epic Games, "Unreal Engine," 2019. https://www.unrealengine.com.

"Roboflow Software." Roboflow Software, [Online]. Available: https://roboflow.com/.

S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, 2017, doi: 10.1109/TPAMI.2016.2577031.

R. Girshick, J. Donahue, T. Darrell, J. Malik, U. C. Berkeley, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 1, p. 5000, 2014, doi: 10.1109/CVPR.2014.81.

M. Sandler, A. Howard, M. Zhu, and A. Zhmoginov, "Sandler_MobileNetV2_Inverted_Residuals_CVPR_2018_paper.pdf," pp. 4510–4520, 2018.

S. D. Joseph Redmon and A. F. , Ross Girshick, "You Only Look Once: Unified, Real-Time Object Detection," ACM Int. Conf. Proceeding Ser., 2018, doi: 10.1145/3243394.3243692.

J. H. Borse, D. D. Patil, V. Kumar, and S. Kumar, "Soft Landing Parameter Measurements for Candidate Navigation Trajectories Using Deep Learning and AI-Enabled Planetary Descent," Math. Probl. Eng., vol. 2022, 2022, doi: 10.1155/2022/2886312.

J. Borse*, D. Patil and V. Kumar, "Tracking Keypoints from Consecutive Video Frames Using CNN Features for Space Applications", Tehnički glasnik, vol.15, no. 1, pp. 11-17, 2021. [Online]. doi: 10.31803/tg-20210204161210.

Janhavi H. Borse and Dipti D. Patil, “Empirical Analysis of Feature Points Extraction Techniques for Space Applications” International Journal of Advanced Computer Science and Applications (IJACSA), 12(9), 2021. doi: 10.14569/IJACSA.2021.0120910.

Revathy, S. ., & Priya, S. S. . (2023). Enhancing the Efficiency of Attack Detection System Using Feature selection and Feature Discretization Methods. International Journal on Recent and Innovation Trends in Computing and Communication, 11(4s), 156–160. https://doi.org/10.17762/ijritcc.v11i4s.6322

Basaligheh, P. (2021). A Novel Multi-Class Technique for Suicide Detection in Twitter Dataset. Machine Learning Applications in Engineering Education and Management, 1(2), 13–20. Retrieved from http://yashikajournals.com/index.php/mlaeem/article/view/14

Downloads

Published

21.09.2023

How to Cite

Borse, J. H. ., Patil, D. D. ., & Kumar, V. . (2023). Real-Time Hazard-Free Planetary Landing using Deep Recurrent Neural Network. International Journal of Intelligent Systems and Applications in Engineering, 11(4), 502–510. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/3585

Issue

Vol. 11 No. 4 (2023)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.