ORBITAL UNCERTAINTY ESTIMATION SUPPORT FOR AUTONOMOUS SPACE DEBRIS OBSERVATION

The continually increased space debris have posed great impact risks to existing space systems and human space flight. Accurate knowledge of propagation errors of space debris orbit is essential for many types of uses, such as space surveillance network tasking, conjunction analysis etc. Unfortunately, propagation error is not available for a two-line element (TLE). In this paper, a new TLE uncertainty estimation method based on neural network model is proposed. Object properties, space environment and predicted time-span are considered as the input of the network, the propagation errors in the direction of downrange, normal and conormal are as the output of the network. In order to assure the chosen orbit for training is not stable, only debris and rocket bodies are used. The network's effciency is demonstrated with some objects with continuous TLE data. Overall, the method proves accurate, computationally fast, and robust, and is applicable to any object in the satellite catalogue, especially for those newly launched objects.