Session
Poster Session 3
Location
Salt Palace Convention Center, Salt Lake City, UT
Abstract
In this work, attitude determination and control (ADC) of a Floating–Satellite(FloatSat)1 through artificial intelligence is proposed. More specifically, Deep Reinforcement Learning (DRL) will be used to generate an optimal control policy for small satellites. This project evaluated an attitude control policy based on deep reinforcement learning using stable–baseline3 (a library which implements the DRL algorithms in PyTorch).2 This Artificially intelligent attitude control was realized for a one-dimensional laboratory-based satellite, which is specifically designed to train the students for satellites and their subsystems.
Document Type
Event
Attitude Control of a Floating Satellite (FloatSat) via Deep Reinforcement Learning
Salt Palace Convention Center, Salt Lake City, UT
In this work, attitude determination and control (ADC) of a Floating–Satellite(FloatSat)1 through artificial intelligence is proposed. More specifically, Deep Reinforcement Learning (DRL) will be used to generate an optimal control policy for small satellites. This project evaluated an attitude control policy based on deep reinforcement learning using stable–baseline3 (a library which implements the DRL algorithms in PyTorch).2 This Artificially intelligent attitude control was realized for a one-dimensional laboratory-based satellite, which is specifically designed to train the students for satellites and their subsystems.
