Abstract
A deep learning approach is presented to detect safe landing locations using LIDAR scans of the Lunar surface. Semantic Segmentation is used to classify hazardous and safe locations from a LIDAR scan during the landing phase. Digital Elevation Maps from the Lunar Reconnaissance Orbiter mission are used to generate the training, validation, and testing dataset. The ground truth is generated using geometric techniques by evaluating the surface roughness, slope, and other hazard avoidance specifications. In order to train a robust model, artificially generated training data is augmented to the training dataset. A UNet-like neural network structure learns a lower dimensional representation of LIDAR scan to retain essential information regarding safety of the landing locations. A softmax activation layer at the bottom of the network ensures that the network outputs a probability of a safe landing spot. The network is also trained with a cost function that prioritizes the false safes to achieve a sub 1% false safes value. The results presented show the effectiveness of the technique for hazard detection. Future work on electing one landing spot based on proximity to the intended landing spot and the size of safety region around it is motivated.
Similar content being viewed by others
References
Amzajerdian, F., Pierrottet, D., Petway, L., Vanek, M.: Development of lidar sensor systems for autonomous safe landing on planetary bodies. In: International Conference on Space Optics – ICSO 2010, International Society for Optics and Photonics, vol. 10565, p 105650M (2017)
Amzajerdian, F., Pierrottet, D., Petway, L.B., Hines, G.D., Roback, V.E., Reisse, R.A.: Lidar sensors for autonomous landing and hazard avoidance. In: AIAA Space 2013 Conference and Exposition, p 5312 (2013)
Amzajerdian, F., Vanek, M., Petway, L., Pierrottet, D., Busch, G., Bulyshev, A.: Utilization of 3D imaging flash lidar technology for autonomous safe landing on planetary bodies. In: Quantum Sensing and Nanophotonic Devices VII, International Society for Optics and Photonics, vol. 7608, p 760828 (2010)
Bradley, A.P.: The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recognit. 30(7), 1145–1159 (1997)
Brady, T., Schwartz, J.: Alhat system architecture and operational concept. In: 2007 IEEE Aerospace Conference, pp 1–13 (2007)
Bulyshev, A., Pierrottet, D., Amzajerdian, F., Busch, G., Vanek, M., Reisse, R.: Processing of three-dimensional flash lidar terrain images generating from an airborne platform. In: Three-Dimensional Imaging, Visualization, and Display 2009, International Society for Optics and Photonics, vol. 7329, p 73290I (2009)
Buslaev, A., Parinov, A., Khvedchenya, E., Iglovikov, V.I., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. ArXiv e-prints (2018)
Cheng, Y., Clouse, D., Johnson, A., Owen, W., Vaughan, A.: Evaluation and improvement of passive optical terrain relative navigation algorithms for pinpoint landing. Spaceflight Mechanics 140 (2011)
Cohen, J.P., Lo, H.Z., Lu, T., Ding, W.: Crater detection via convolutional neural networks. arXiv:1601.00978 (2016)
Di, K., Li, W., Yue, Z., Sun, Y., Liu, Y.: A machine learning approach to crater detection from topographic data. Adv. Space Res. 54(11), 2419–2429 (2014)
Emami, E., Bebis, G., Nefian, A., Fong, T.: Automatic crater detection using convex grouping and convolutional neural networks. In: International Symposium on Visual Computing, pp 213–224. Springer, New York (2015)
Epp, C., Robertson, E., Carson, J.M.: Developing autonomous precision landing and hazard avoidance technology from concepts through terrestrially flight-tested prototypes. In: AIAA Guidance, Navigation, and Control Conference, p 0324 (2015)
Gurung, A., Tamang, S.L.: Image segmentation using multi-threshold technique by histogram sampling. arXiv:1909.05084 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv:0706.1234 (2015)
Ivanov, T., Huertas, A., Carson, J.M.: Probabilistic hazard detection for autonomous safe landing. In: AIAA Guidance, Navigation, and Control (GNC) Conference, p 5019 (2013)
Jaccard, P.: The distribution of the flora in the alpine zone. 1. New Phytol. 11(2), 37–50 (1912)
Jiang, X., Li, S., Tao, T.: Innovative hazard detection and avoidance guidance for safe lunar landing. Proceedings of the institution of mechanical engineers. Part G J. Aerosp. Eng. 230(11), 2086–2103 (2016). https://doi.org/10.1177/0954410015625671
Johnson, A.E., Huertas, A., Werner, R.A., Montgomery, J.F.: Analysis of on-board hazard detection and avoidance for safe lunar landing. In: 2008 IEEE Aerospace Conference, pp 1–9 (2008), https://doi.org/10.1109/AERO.2008.4526301
Johnson, A.E., Montgomery, J.F.: Overview of terrain relative navigation approaches for precise lunar landing. In: 2008 IEEE Aerospace Conference, pp 1–10 (2008)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 (2014)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 807–814 (2010)
Restrepo, C.I., Sostaric, R.R.: Next-generation nasa hazard detection system development. In: AIAA Scitech 2020 Forum, p 0368 (2020)
Riris, H., Sun, X., Cavanaugh, J.F., Ramos-Izquierdo, L., Liiva, P., Jackson, G.B., Schmidt, S., McGarry, J., Smith, D.E.: The lunar orbiter laser altimeter (Lola) on Nasa’s lunar reconnaissance orbiter (Lro) mission. In: Conference on Lasers and Electro-Optics, P. CMQ1. Optical Society of America (2008)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp 234–241. Springer, New York (2015)
Silburt, A., Ali-Dib, M., Zhu, C., Jackson, A., Valencia, D., Kissin, Y., Tamayo, D., Menou, K.: Lunar crater identification via deep learning. Icarus 317, 27–38 (2019)
Thoma, M.: A survey of semantic segmentation. arXiv:1602.06541 (2016)
Trawny, N., Huertas, A., Luna, M.E., Villalpando, C.Y., Martin, K., Carson, J.M., Johnson, A.E., Restrepo, C., Roback, V.E.: Flight testing a real-time hazard detection system for safe lunar landing on the rocket-powered morpheus vehicle. In: AIAA Guidance, Navigation, and Control Conference, p 0326 (2015)
Wang, Y., Wu, B.: Active machine learning approach for crater detection from planetary imagery and digital elevation models. IEEE Trans. Geosci. Remote Sens. pp. 1–13, https://doi.org/10.1109/TGRS.2019.2902198 (2019)
Yan, B., Wang, Y., Feng, L., Zhou, H., Jiang, Z.: Terrain matching based on adaptive digital elevation map. In: 2018 International Conference on Advanced Control, Automation and Artificial Intelligence (ACAAI 2018). Atlantis Press, Paris (2018)
Zhou, Q., Liu, X.: Error analysis on grid-based slope and aspect algorithms. Photogramm. Eng. Remote Sensing 70(8), 957–962 (2004)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
This work is partially supported by NASA Johnson Space Center Grant NNX17AI35A.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Moghe, R., Zanetti, R. A Deep Learning Approach to Hazard Detection for Autonomous Lunar Landing. J Astronaut Sci 67, 1811–1830 (2020). https://doi.org/10.1007/s40295-020-00239-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40295-020-00239-8