Researchers have developed a system that can autonomously drive spacecraft across space and around celestial objects.
Researchers at the Georgia Institute of Technology and the NASA Goddard Space Flight Center recently developed AstroSLAM, an algorithm based on SLAM that can allow spacecraft to navigate more autonomously. The expected goal is to make future spacecraft destined for deep-space missions (for example, visiting and surveying asteroids) more autonomous.
Simultaneous localization and mapping (SLAM) is a promising technology that can be used to improve the navigation of autonomous systems, helping them to map their surrounding environment and track other objects within it. Currently, it is mainly applied to terrestrial vehicles and mobile robots, but it can also be extended to spacecraft.
The current process requires a large team of human operators on the ground to downlink images captured from spacecraft and analyze them offline to create digital terrain maps, which equates to careful choreograph the maneuvers of the spacecraft. An autonomous model that can recreate the shape of nearby asteroids and navigate the spacecraft with minimal intervention from Earth would be extremely valuable, as it could speed up and potentially speed up the deep space mission.
AstroSLAM, the solution developed by Tsiotras and his colleagues, can autonomously generate the location and orientation of the spacecraft relative to that of nearby asteroids or other small celestial objects. This is achieved by analyzing a sequence of images taken from a camera on board the spacecraft as it orbits the celestial body of interest.
It can estimate the relative position and orientation of the spacecraft fully autonomously. This information can be used to plan and execute various maneuvers in orbit, including landing on nearby celestial bodies. The model can also generate images of the 3D shape of a nearby celestial body, estimating its size and gravitational parameters.
The researchers tested their technology in a series of tests, using real data obtained by NASA during legacy space missions and high-fidelity artificial data generated using a spacecraft simulator at Georgia Tech. . Their findings are promising, suggesting that AstroSLAM could eventually enable autonomous spacecraft operation in a variety of scenarios.