Detection of Martian dust storms using mask regional convolutional neural networks

Martian dust plays a crucial role in the meteorology and climate of the Martian atmosphere. It heats the atmosphere, enhances the atmospheric general circulation, and affects spacecraft instruments and operations. Compliant with that, studying dust is also essential for future human exploration. In this work, we present a method for the deep-learning-based detection of the areal extent of dust storms in Mars satellite imagery. We use a mask regional convolutional neural network, consisting of a regional-proposal network and a mask network. We apply the detection method to Mars daily global maps of the Mars global surveyor, Mars orbiter camera. We use center coordinates of dust storms from the eight-year Mars dust activity database as ground-truth to train and validate the method. The performance of the regional network is evaluated by the average precision score with $$50\%$$ 50 % overlap ($$mAP_{50}$$ m A P 50 ), which is around $$62.1\%$$ 62.1 % .

Competing cognitive pressures on human exploration in the absence of trade-off with exploitation

Exploring novel environments through sequential sampling is essential for efficient decision-making under uncertainty. In the laboratory, human exploration has been studied in situations where exploration is traded against reward maximisation. By design, these ‘explore-exploit’ dilemmas confound the behavioural characteristics of exploration with those of the trade-off itself. Here we designed a sequential sampling task where exploration can be studied and compared in the presence and absence of trade-off with exploitation. Detailed model-based analyses of choice behaviour revealed specific exploration patterns arising in situations where information seeking is not traded against reward seeking. Human choices are directed toward the most uncertain option available, but only after an initial sampling phase consisting of choice streaks from each novel option. These findings outline competing cognitive pressures on information seeking: the repeated sampling of the current option (for hypothesis testing), and the directed sampling of the most uncertain option available (for structure mapping).

Brine-Induced Tribocorrosion Accelerates Wear on Stainless Steel: Implications for Mars Exploration

Tribocorrosion is a degradation phenomenon of material surfaces subjected to the combined action of mechanical loading and corrosion attack caused by the environment. Although corrosive chemical species such as materials like chloride atoms, chlorides, and perchlorates have been detected on the Martian surface, there is a lack of studies of its impact on materials for landed spacecraft and structures that will support surface operations on Mars. Here, we present a series of experiments on the stainless-steel material of the ExoMars 2020 Rosalind Franklin rover wheels. We show how tribocorrosion induced by brines accelerates wear on the materials of the wheels. Our results do not compromise the nominal ExoMars mission but have implications for future long-term surface operations in support of future human exploration or extended robotic missions on Mars.

Visual SLAM-Based Robotic Mapping Method for Planetary Construction

With the recent discovery of water-ice and lava tubes on the Moon and Mars along with the development of in-situ resource utilization (ISRU) technology, the recent planetary exploration has focused on rover (or lander)-based surface missions toward the base construction for long-term human exploration and habitation. However, a 3D terrain map, mostly based on orbiters’ terrain images, has insufficient resolutions for construction purposes. In this regard, this paper introduces the visual simultaneous localization and mapping (SLAM)-based robotic mapping method employing a stereo camera system on a rover. In the method, S-PTAM is utilized as a base framework, with which the disparity map from the self-supervised deep learning is combined to enhance the mapping capabilities under homogeneous and unstructured environments of planetary terrains. The overall performance of the proposed method was evaluated in the emulated planetary terrain and validated with potential results.