A method to automatically identify pilot actions from cockpit camera footage is reported in this paper. Although they have long been considered for the enhancement of flight safety, cockpit image recorders have not yet been standard equipment in aircraft cockpits. The rules on Flight Data Recorders have been changed, however, to include a cockpit image recorder as one of the safety devices, and it is recommended to be installed in small aircraft as a substitute for a Flight Data Recorder. With cockpit images becoming available, it would surely be useful for accident analysis as well as for daily flight analysis. Especially for the latter purpose, pilot behavior should be automatically analyzed and classified into specific actions, or procedures. The authors conducted a study to assess the feasibility of automatic detection of pilot actions in the cockpit by a machine learning process. Results show that even with a small amount of training data, the resulting algorithm could identify some typical actions, such as manipulation of the switches on the glare shield, with 80% accuracy. Even in cases with a button and a switch positioned very close to each other, the actions ‘pushing the switch’ and ‘pushing the button’ could be distinguished by the algorithm. The action estimation accuracy improves up to 90% when using the training data focused on the pilot’s body parts, rather than the data focused on the whole body.@en

In this paper, we study the dynamical environment around asteroids to investigate whether ejecta particles from an impact event (artificial or natural) could be temporarily trapped in periodic orbits. If such particles remain about an asteroid, they could potentially jeopardize an orbiting spacecraft in the event of a collision. We make use of invariant manifold theory to assess the conditions - impact location, particle radius, ejection velocity - that cause ejecta particles to get captured in periodic orbits. The analysis is carried out within the dynamical framework of the perturbed Augmented Hill Problem, which takes into account the solar radiation pressure, the effect of eclipses, and the J20 and J40 terms of the asteroid's gravity potential in its spherical harmonics expansion. We analyze millimeter- to centimeter-sized particles and captures into three families of periodic orbits that are robust to large values of the solar radiation pressure acceleration – the traditional a and g’ families of the Hill Problem and the southern halo orbits. We go on to find the impact locations from where ejecta particles are most likely to be captured into periodic orbits via their stable manifolds. As such, we recover the sets of initial states that lead ejecta to temporary orbital capture and show that solar radiation pressure and, subsequently, eclipses, cannot be neglected in these analyses. We apply our analyses to the specific case of JAXA's Hayabusa2 mission that successfully carried out its Small Carry-on Impactor (SCI) operation at asteroid Ryugu in April 2019. For this event, we identify locations on the Sun side of the asteroid at medium latitudes as the best impact locations.@en