Hazard detection is critical for enabling autonomous landing on planetary surfaces. Current state-of-the-art methods leverage traditional computer vision approaches to automate identification of safe terrain from input digital elevation models (DEMs). However, performance for these methods can degrade for input DEMs with increased sensor noise. At the same time, deep learning techniques have been developed for various applications. Nevertheless, their applicability to safety-critical space missions has been often limited due to concerns regarding their outputs' reliability. In response to this background, this paper proposes an uncertainty-aware learning-based method for hazard detection and landing site selection. The developed approach enables reliable safe landing site selection by: (i) generating a safety prediction map and its uncertainty map together via Bayesian deep learning and semantic segmentation; and (ii) using the generated uncertainty map to filter out the uncertain pixels in the prediction map so that the safe landing site selection is performed only based on the certain pixels (i.e., pixels for which the model is certain about its safety prediction). Experiments are presented with simulated data based on a Mars HiRISE digital terrain model and varying noise levels to demonstrate the performance of the proposed approach.

In the aerial supply delivery problem, an un-manned aircraft needs to deliver supplies as close as possible to the desired goal location. This involves choosing and landing at a landing site that is closest to or most accessible from the desired goal location. The problem is complicated by the fact that the status of candidate landing sites is unknown before the mission begins, and instead the aircraft needs to compute a sequence according to which it flies and senses the candidate landing sites in order to land as quickly as possible. The problem of computing this sequence corresponds to planning under uncertainty about environment. In this paper, we show how it can be solved efficiently via a recently developed probabilistic planning framework, called Probabilistic Planning with Clear Preferences (PPCP). We show that the problem satisfies the Clear Preferences assumption required by PPCP,and therefore all the theoretical guarantees continue to hold. The experimental results in simulation show that our approachcan solve large-scale problems in real-time while experiments on a physical quad-rotor provide proof of concept.