A multilayer perceptron hazard detector for vision-based autonomous planetary landing

Abstract A hazard detection and target selection algorithm for autonomous spacecraft planetary landing, based on Artificial Neural Networks, is presented. From a single image of the landing area, acquired by a VIS camera during the descent, the system computes a hazard map, exploited to select the best target, in terms of safety, guidance constraints, and scientific interest. ANNs generalization properties allow the system to correctly operate also in conditions not explicitly considered during calibration. The net architecture design, training, verification and results are critically presented. Performances are assessed in terms of recognition accuracy and selected target safety. Results for a lunar landing scenario are discussed to highlight the effectiveness of the system.

[1]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[2]  Edward C. Wong,et al.  Autonomous guidance and control design for hazard avoidance aand safe landing on Mars , 2002 .

[3]  Homer Pien,et al.  Autonomous Hazard Detection and avoidance for Mars exploration , 1991 .

[4]  Ashutosh Saxena,et al.  Learning Depth from Single Monocular Images , 2005, NIPS.

[5]  Christopher A. Grasso,et al.  Optical Navigation Plan and Strategy for the Lunar Lander Altair; OpNav for Lunar and other Crewed and Robotic Exploration Applications , 2010 .

[6]  John G. Daugman,et al.  Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression , 1988, IEEE Trans. Acoust. Speech Signal Process..

[7]  I. Michael Ross,et al.  Direct trajectory optimization by a Chebyshev pseudospectral method , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[8]  Richard Grieve,et al.  Lunar Surface Processes , 2023, Reviews in Mineralogy and Geochemistry.

[9]  José Carlos Príncipe,et al.  Nonlinear Component Analysis Based on Correntropy , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[10]  Erkki Oja,et al.  Independent Component Analysis , 2001 .

[11]  Farzin Amzajerdian,et al.  Doppler lidar sensor for precision navigation in GPS-deprived environment , 2013, Defense, Security, and Sensing.

[12]  Augusto Caramagno,et al.  Consolidated Performance Assessment of Hazard Avoidance Techniques for Vision Based Landing , 2006 .

[13]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[14]  François Anctil,et al.  Comparing Sigmoid Transfer Functions for Neural Network Multistep Ahead Streamflow Forecasting , 2010 .

[15]  C. Jones,et al.  Helicopter flight testing in natural snow and ice , 1983 .

[16]  Paul S. Smith,et al.  Mars Exploration Program 2007 Phoenix landing site selection and characteristics , 2008 .

[17]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[18]  Erwin Mooij,et al.  Stereo Vision Algorithm for Hazard Detection during Planetary Landings , 2014 .

[19]  J. Betts.  Survey of Numerical Methods for Trajectory Optimization , 1998 .

[20]  Andrew E. Johnson,et al.  Helicopter Flight Testing of a Real-Time Hazard Detection System for Safe Lunar Landing , 2013 .

[21]  Jeffrey S. Kargel,et al.  Autonomous real-time landing site selection for Venus and Titan using Evolutionary Fuzzy Cognitive Maps , 2012, Appl. Soft Comput..

[22]  Raymond E. Arvidson,et al.  Phoenix Landing Site Hazard Assessment and Selection , 2009 .

[23]  D. L. Fisher,et al.  The Computer Simulation of Lunar Craters , 1968 .

[24]  Viktor Kerzhanovich,et al.  Rosetta lander Philae , 2007 .

[25]  H. B. Kekre,et al.  Image Segmentation using Extended Edge Operator for Mammographic Images , 2010 .

[26]  Mark S. Nixon,et al.  Feature Extraction and Image Processing , 2002 .

[27]  Behcet Acikmese,et al.  Convex programming approach to powered descent guidance for mars landing , 2007 .

[28]  J. Biele,et al.  Rosetta Lander – Philae: Landing preparations☆ , 2015 .

[29]  Michèle Lavagna,et al.  A semi-analytical guidance algorithm for autonomous landing , 2015 .

[30]  Wen-Jong Shyong,et al.  Lunar Terrain Surface Modeling for the ALHAT Program , 2008, 2008 IEEE Aerospace Conference.

[31]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[32]  H. Masursky,et al.  The Viking Landing Sites: Selection and Certification , 1976, Science.

[33]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[34]  Andres Huertas,et al.  Landing Hazard Detection with Stereo Vision and Shadow Analysis , 2007 .

[35]  Allan R. Klumpp,et al.  Apollo lunar descent guidance , 1974, Autom..

[36]  Roberto Furfaro,et al.  Optimal sliding guidance algorithm for Mars powered descent phase , 2016 .

[37]  M. Watkins,et al.  Selection of the Mars Science Laboratory Landing Site , 2012 .

[38]  Behcet Acikmese,et al.  Minimum-Landing-Error Powered-Descent Guidance for Mars Landing Using Convex Optimization , 2010 .