The invention relates to a method of predicting a trajectory of a given satellite, including training a machine learning algorithm to predict the trajectory of the given satellite from a data set of given satellite, the algorithm being encoded in a programming language; integrating the trained algorithm, on an integrated circuit, by converting the programming language into a hardware description language; and predicting the trajectory of the given satellite given by the integrated algorithm, from a data set of the given satellite. The training and integrating are performed on the ground on a computer comprising at least one processor and the predicting is performed on board the given satellite embarking the integrated circuit.

A method and satellite for capture-less management of orbital debris objects, include controlling a satellite having opposing thrusters to be maintained at a predetermined distance from an orbital debris object to be managed, i.e., paired with the orbital debris object. Management may include fine tracking of the orbital debris object and/or operating the opposing thrusters to apply force to the orbital debris object to generate a model of the orbital debris object, to change the attitude of the orbital debris object, to deorbit the orbital debris object, and/or breakup the orbital debris object.

There is provided a vehicle for protecting an entity against directed-energy weapons, comprising: a housing; and a shield for absorbing or reflecting a laser beam, the shield, in use, extending in a plane from the housing. There is also provided a system of vehicles and a method of coordinating a plurality of vehicles to protect an entity against directed-energy weapons.

Systems and methods for describing, simulating and/or optimizing spaceborne systems and missions. Configurations for spaceborne systems are generated and validated based on simulation output.

Systems and methods for describing, simulating and/or optimizing spaceborne systems and missions. Configurations for spaceborne systems are generated and validated based on simulation output.

For model predictive control for a spacecraft formation, a method calculates a virtual point that represents a plurality of spacecraft orbiting in a spacecraft formation. The method calculates an outer polytope boundary and an inner polytope boundary relative to the virtual point for a given spacecraft of the plurality of spacecraft. The method maneuvers the given spacecraft to within the inner polytope boundary using model predictive control (MPC) to minimize fuel consumption.

A safety check method for checking a neural network output state onboard a spacecraft includes executing a neural network model onboard a spacecraft, which includes calculating a neural network output based on a current navigation state of the spacecraft, propagating the navigation state with the neural network output to a next target epoch to determine a next navigation state of the spacecraft, and evaluating whether the neural network output and the next navigation state are within predetermined bounds. When the neural network output and the next navigation state are within the predetermined bounds, the method is incremented to a next tick. When the neural network output and the next navigation state are determined to be outside the predetermined bounds, a corrective action may be taken.

Systems and methods for high performance, professional-grade photography and filmmaking in a spacecraft during space flights are provided. The systems may include an imaging studio, which is a partially enclosed volume within a spacecraft. The imaging studio may enable photography during microgravity coast phases of space flight while allowing astronauts to tend to non-photographic activities. The imaging studio may allow for commercially-valuable imagery that includes a background of an illuminated, curved Earth horizon. Imagery may also involve, among other things, a unique microgravity environment. Such imagery, without use of an imaging studio as described herein, may otherwise require artificial visual effects that may appear less realistic. Additionally, the novelty of capturing images during an actual space flight may itself be valuable.

An example method executed by a controller onboard a spacecraft generates a mission plan in real-time that guides the spacecraft along a space autonomous mission to rendezvous with two or more orbiting target objects. The method includes establishing potential permutations for all possible unique maneuver sequences in which to visit the two or more orbiting target objects, and for each potential permutation, determining a collision-free maneuver plan for defining orbit trajectories to intercept each of the two or more orbiting target objects for each of the possible unique maneuver sequences. An optimal permutation is determined that meets viewing constraints of the two or more orbiting target objects, a viewing priority, and fuel constraints of the spacecraft. A mission visit plan is generated using the optimal permutation, and the spacecraft executes the plan to rendezvous with and inspect the two or more orbiting target objects.

Techniques for accounting for rotational bias of an inertial measurement unit in a setting where momentum is conserved are presented. The techniques include: obtaining, from an inertial measurement unit, an initial magnitude of momentum and initial directional rotational rates; iteratively updating an estimate of bias of magnitude of momentum and estimates of bias of directional rotational rates based at least on the obtaining and based at least on readings from the inertial measurement unit; adjusting directional rotational rates obtained from the inertial measurement unit to account for the estimates of bias of directional rotational rates, where bias adjusted directional rotational rates are determined; and providing the bias adjusted directional rotation rates.