Future space exploration missions on solar system bodies will require landing safely and precisely, with an accuracy of ~100 m at touchdown. This accomplishment is made challenging by vehicle design limitations, the dearth of onboard situational awareness, and the limited knowled
...
Future space exploration missions on solar system bodies will require landing safely and precisely, with an accuracy of ~100 m at touchdown. This accomplishment is made challenging by vehicle design limitations, the dearth of onboard situational awareness, and the limited knowledge of the variability of the landing terrain. To date, only the Chinese Chang’e-3 has implemented
hazard detection and avoidance capabilities, within its Guidance, Navigation, and
Control (GN&C) subsystem, therefore being able to actively adjust its trajectory. On the contrary, the majority of the space landers only had the ability to execute autonomously a small series of simple and programmed commands. Therefore, past missions have essentially landed "blind" in regions deemed relatively safe, forcing landing site selection to be capability-limited rather than scientifically driven. In this thesis, hazard detection was investigated as a mean to increase autonomy for planetary landings and to further decrease the risk of a landing failure, employing equipment readily available on space missions. The analysis has been limited to the framework of Structure-from-Motion (SfM) where the input images are acquired from a single moving camera and thus the
scene is reconstructed from the resulting video sequence. A software package was developed and tested to compute depth maps from adjacent descent images, captured at half altitude from one to the other. The basic pinhole camera model was selected to address the measurement taken from synthetic surface images, rendered in the Planet and Asteroid Natural scene Generation Utility (PANGU). To assess the hazardousness of the terrain, hazard maps are computed combining slope, roughness, and shadow information. In contrast to the results of the Jet Propulsion Laboratory (JPL) NASA, it has been shown that rocks and boulders are not well resolved from shape recovery with both low- and high-elevation image pairs. Thus, their presence on the surface has been accounted through an adapted version of theHarris Corner detector directly on the input images. Two different mission scenarios were simulated: 1) a perfect
vertical motion forward along the camera pointing direction and 2) a 45° angle dropping trajectory for a more realistic approaching descent phase, with a 40° imaging sensor line-of-site offset. Furthermore, the limitations of the developed algorithm were tested under ordinary operative conditions. For the former scenario, the results show that the overall quality of the recovered depth maps does not appear adequate enough for landing site selection. As a matter of fact, the locations around the image centre can not be correctly assessed. This represents a significant problem since these locations are the most convenient in terms of distance and guidance costs. On the contrary, the latter descent sequence indicates that below 300maltitude the software is a suitable candidate for hazard detection, with total correct detection on average >94% and the
percentage of undetected hazards below the allowable maximum 1%.
To assess the algorithm robustness to errors in camera position, a Monte Carlo simulation was performed. Thereupon, random uncertainties within the interval [-0.5 0.5] meters were taken into account for the altitude of both camera poses. The errors for the computed Digital Elevation Model (DEM) are bounded to the maximum allowable only when both altitudes are affected by small deviation of similar magnitude and same sign (approximately 10 cm), peaking to 250%-300% increase for the other values of the considered interval. Moreover, concerning the robustness to errors in camera orientation, deviations of the camera pointing direction were considered only along the plane containing both the normal to the surface and the camera axis. Already differences greater than +0.05°, in the imaging sensor line-of-site, are responsible for exorbitant errors in the DEM for all altitudes. These results clearly indicate that the developed SfMalgorithmis not suitable as a stand-alone method for hazard detection and landing site selection.
