SinGAN-Based Asteroid Surface Image Generation

SinGAN-Based Asteroid Surface Image Generation

Yundong Guo, Jeng-Shyang Pan, Chengbo Qiu, Fang Xie, Hao Luo, Huiqiang Shang, Zhenyu Liu, Jianrong Tan
Copyright: © 2021 |Pages: 20
DOI: 10.4018/JDM.2021100103
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

While it is risky considering spacecraft constraints and unknown environment on asteroid, surface sampling is an important technique for asteroid exploration. One of the sample return missions is to seek an optimal landing site, which may be in hazardous terrain. Since autonomous landing is particularly challenging, it is necessary to simulate the effectiveness of this process and prove the onboard optical hazard avoidance is robust to various uncertainties. This paper aims to generate realistic surface images of asteroids for simulations of asteroid exploration. A SinGAN-based method is proposed, which only needs a single input image for training a pyramid of multi-scale patch generators. Various images with high fidelity can be generated, and manipulations such as shape variation, illumination direction variation, super resolution generation are well achieved. The method's applicability is validated by extensive experimental results and evaluations. At last, the proposed method has been used to help set up a test environment for landing site selection simulation.
Article Preview
Top

Introduction

Asteroid sampling plays an important role in deep space exploration. For example, two sample-return missions are undergoing, NASA's OSIRIS-REx to asteroid (101955) Bennu (Beshore, et al., 2015) and JAXA's Hayabusa2 to asteroid (162173) Ryugu (Watanabe, et al., 2017), which use robotic spacecrafts to collect samples from the surface of asteroid and take them back to earth. Based on OSIRIS-REx touch-and-go (TAG) mission design, OSIRIS-REx would fly a TAG trajectory to the asteroid’s surface to obtain a regolith sample (Berry, et al., 2013). And according to detailed description of the OSIRIS-REx asteroid sample return mission, when sampler touched the surface, materials on it (may contain hydrated minerals, organics, etc.) would be collected by Touch-And-Go-Sample-Acquisition Mechanism (TAGSAM), which had been tested many times during microgravity flights (Beshore, et al., 2015). The samples are stored in a separate sealed container inside the sample-return capsule and then taken back to earth.

According to available findings, 3D shapes of asteroids are of great differences. Although a few of asteroids are nearly spherical, most asteroids are with irregular shapes, which is mainly due to the weak gravitational force, e.g., Itokawa is like a peanut (Saito, et al., 2006) and Bennu is more like a walnut (Daly, et al., 2020). In addition, almost all asteroids’ surfaces are pitted and cratered, which means many kinds of stone formations existed in surface terrains (Fujiwara, et al., 2006). The prior concern in missions of asteroid exploration is how to land safely. However, the places of great scientific interest are usually surrounded by rocks and craters (Cui, Ge, and Gao, 2017). Therefore, precise and safe landing must be applied by robot automatically. Obviously, to deal with this complex situation, the spacecraft should be capable of detecting hazards, estimating its touchdown performance, and choosing a safe spot with high accuracy to land based on kinds of sensors (Lauretta, et al., 2017). Four candidate sampling sites on asteroid Bennu were selected by NASA for OSIRIS-REx mission, based on their scores for safety, sampleability, deliverability, and science value. In December 2019, the OSIRIS-REx team chose sites Nightingale and Osprey as the mission’s primary and backup sample collection sites.

Specifically, the surface of asteroid Itokawa was investigated (Zeng, Li, Martin, Tang, and Wang, 2019), which aimed to provide the reference for asteroid landing and sample-return missions. The robust planning of the Hayabusa2-Ryugu proximity operation and landing site selection process was presented (Yamaguchi, Saiki, Tanaka, Takei, and Tsuda, 2018), considering unknown environment on asteroid and the vehicle constraints. The proximity operation was decomposed a landing site selection and in-situ observation. An optimal landing site selection method based on safety index during planetary descent was proposed (Cui, et al., 2017). It developed a criterion for evaluating the safety index of landing area, including terrain safety, fuel consumption and touchdown performance during descent. The motion of surface particles on the asteroid Bennu was investigated (Zhang, Zeng, Circi, and Vulpetti, 2019). A probability-based hazard avoidance guidance algorithm for planetary landing method was developed, which exploited information on the uncertainty of lander position and calculated the probability of collision with each hazard (Yuan, Yu, Cui, Xu, and Luan, 2018). Besides, it indicated that site selection based on images of asteroid is useful and important for validating the method of fuel-optimal control for soft landing on an irregular asteroid, especially for a highly irregular gravitational field (Yang and Baoyin, 2015). In Yang and Baoyin’s research, with the help of asteroid’s images, a convincing fuel-optimal descent trajectory can be determined.

Complete Article List

Search this Journal:
Reset
Volume 35: 1 Issue (2024)
Volume 34: 3 Issues (2023)
Volume 33: 5 Issues (2022): 4 Released, 1 Forthcoming
Volume 32: 4 Issues (2021)
Volume 31: 4 Issues (2020)
Volume 30: 4 Issues (2019)
Volume 29: 4 Issues (2018)
Volume 28: 4 Issues (2017)
Volume 27: 4 Issues (2016)
Volume 26: 4 Issues (2015)
Volume 25: 4 Issues (2014)
Volume 24: 4 Issues (2013)
Volume 23: 4 Issues (2012)
Volume 22: 4 Issues (2011)
Volume 21: 4 Issues (2010)
Volume 20: 4 Issues (2009)
Volume 19: 4 Issues (2008)
Volume 18: 4 Issues (2007)
Volume 17: 4 Issues (2006)
Volume 16: 4 Issues (2005)
Volume 15: 4 Issues (2004)
Volume 14: 4 Issues (2003)
Volume 13: 4 Issues (2002)
Volume 12: 4 Issues (2001)
Volume 11: 4 Issues (2000)
Volume 10: 4 Issues (1999)
Volume 9: 4 Issues (1998)
Volume 8: 4 Issues (1997)
Volume 7: 4 Issues (1996)
Volume 6: 4 Issues (1995)
Volume 5: 4 Issues (1994)
Volume 4: 4 Issues (1993)
Volume 3: 4 Issues (1992)
Volume 2: 4 Issues (1991)
Volume 1: 2 Issues (1990)
View Complete Journal Contents Listing