AbstractMillisecond pulsars (MSPs) are a class of radio pulsars with extremely stable rotation. Their excellent timing stability can be used to study a wide variety of astrophysical phenomena. In particular, a large sample of these pulsars can be used to detect low-frequency gravitational waves. We have developed a precision pulsar timing backend for the NASA Deep Space Network (DSN), which will allow the use of short gaps in tracking schedules to time pulses from an ensemble of MSPs. The DSN operates clusters of large dish antennas (up to 70-m in diameter), located roughly equidistant around the Earth, for communication and tracking of deep-space spacecraft. The backend system will be capable of removing entirely the dispersive effects of propagation of radio waves through the interstellar medium in real-time. We will describe our development work, initial results, and prospects for future observations over the next few years.
Scheduling the NASA Deep Space Network with Deep Reinforcement Learning
