SERPENT A Spacecraft

Develop an autonomous pose estimation and prediction algorithm through the use of neural networks and computer vision.

Mission will consist of two 6U CubeSats in low Earth orbit. The chaser will run the neural network on an FPGA-based hardware system and will identify the pose of the target satellite in three stages of cooperativeness.

The first phase of the mission involves the use of LED lights positioned on the target in order to simulate a fully cooperative target.

The second phase of the mission will have the LED lights turned off, simulating a neutral, semi-non-cooperative target.

The final phase of the mission consists of the target, with LEDs turned off, performing proximity maneuvers near the chaser, of which the chaser will have no knowledge.

SERPENT went through a large architecture shift from the original double satellite configuration. From SERPENT’s conception through PDR in December 2019, the mission consisted of two satellites, CORAL and KING, that would take images of each other in cooperative and non-cooperative situations, and communicate their true pose data to each other through wifi, to be downlinked to the ground station. However, the nature of two satellites introduced extreme complexity and cost issues, and changes were made at PDR-Delta to reduce the scope of the experiment to have less risk.