1,720,977 research outputs found
Sensitivity Analysis of Adaptive Guidance via Deep Reinforcement Learning for Uncooperative Space Objects Imaging
Full text linkAutonomous Fault Management in Attitude Determination and Control Subsystems: Hardware and Processor in the Loop Testing
Full text linkDeep Reinforcement Learning to Enhance Fly-Around Guidance for Uncooperative Space Objects Smart Imaging
No full textDriven by several potential applications, leading space agencies are increasingly investing in the gradual automation of space missions. Autonomous flight operations may be a key enabler for on-orbit servicing, assembly and manufacturing (OSAM) missions, carrying inherent benefits such as cost and risk reduction. Within the spectrum of proximity operations, this work focuses on autonomous path-planning for the reconstruction of geometry properties of an uncooperative target. The autonomous navigation problem is called active Simultaneous Localization and Mapping (SLAM) problem, and it has been largely studied within the field of robotics. Active SLAM problem may be formulated as a Partially Observable Markov Decision Process (POMDP). Previous works in astrodynamics have demonstrated that is possible to use Reinforcement Learning (RL) techniques to teach an agent that is moving along a pre-determined orbit when to collect measurements to optimize a given mapping goal. In this work, different RL methods are explored to develop an artificial intelligence agent capable of planning suboptimal paths for autonomous shape reconstruction of an unknown and uncooperative object via imaging. Proximity orbit dynamics are linearized and include orbit eccentricity. The geometry of the target object is rendered by a polyhedron shaped with a triangular mesh. Artificial intelligent agents are created using both the Deep Q-Network (DQN) and the Advantage Actor Critic (A2C) method. State-action value functions are approximated using Artificial Neural Networks (ANN) and trained according to RL principles. Training of the RL agent architecture occurs under fixed or random initial environment conditions. A large database of training tests has been collected. Trained agents show promising performance in achieving extended coverage of the target. Policy learning is demonstrated by displaying that RL agents, at minimum, have higher mapping performance than agents that behave randomly. Furthermore, RL agent may learn to maneuver the spacecraft to control target lighting conditions as a function of the Sun location. This work, therefore, preliminary demonstrates the applicability of RL to autonomous imaging of an uncooperative space object, thus setting a baseline for future works
Some aspects of hysteria: a clinical study Su alcuni aspetti dell'isteria: uno studio clinico.
No full textScreening of clones of Solanum spp. for resistance to potato cyst nematodes, Globodera rostochiensis and G. pallida
No full text
Impact of the root-knot nematode, Meloidogyne incognita, on potato during two different growing season
No full text
An unusual case of poisoning due to dithiocarbamates with serious neurological symptoms. Analogy with poisoning due to organo-phosphate substances
No full textOxygen Harvesting from Eukaryotic Green Algae Cultivation on Moon’s Surface
Full text linkThe presence of oxygen in the Earth atmosphere represents the key resource for the human life. Outside that thin layer of atmosphere, every place is naturally unsuitable for life. Nowadays, the vital resources on board the ISS, the only manned outpost in space, are constantly resupplied directly from Earth in an open-loop cycle. Different strategies must be adopted for deep-space manned explorations in order to ensure the mission independence from Earth. The main idea behind this work is to support the incoming manned mission towards the Moon by recycling part of the emitted carbon dioxide and the urine produced by the human crew to feed a green algae cultivation in a dedicated photobioreactor aimed to close-loop oxygen production. Indeed, oxygen availability opens to a variety of new scenarios for planetary colonization and exploration. A great amount of work on this side has been carried out in the context of MELiSSA Project, whose main objective is to set-up a regenerative life support system to reach the highest degree of autonomy to produce water, food, and oxygen by the mission wastes. Leveraging on the MELiSSA Project experiences and on an ISS photobioreactor demonstrator developed by DRL, we propose to use a Chlorella Vulgaris cultivation in a photobioreactor placed in a space system, properly designed for its survival on the Moon’s surface. In this work we present the basic principle of photosynthesis linked to the hyperparameters that mostly affect the Chlorella Vulgaris cultivation, the set-up of the numerical simulations used for the design of the photobioreactor capable to work in Moon environmental conditions and the preliminary sizing of the system from a thermal and power supply point of view
- …
