Small spacecraft are increasingly expected to perform complex missions despite strict constraints in mass, power, and onboard computation. Meeting these demands requires advances in autonomy that enable ef- fective decision-making, adaptive control, and robust state estimation within resource-limited platforms. This thesis develops optimization- and machine-learning–based methods to improve spacecraft autonomy across guidance, navigation, and control (GNC), perception, and onboard decision-making, building on flight-relevant small spacecraft systems. Achieving onboard autonomy introduces challenges across multiple sub- systems. Increased computational workloads raise thermal dissipation, motivating new thermal management strategies for reliable operation in planetary and deep-space environments. For attitude and orbit control, this work investigates propellant-free approaches based on magnetorquer Lyapunov control and differential-drag formation flying, enabling precise maneuvering on constrained platforms. In navigation, visual-inertial tech- niques are developed for GPS-denied environments by tightly integrating computer vision with inertial sensing, while machine learning methods improve feature extraction and uncertainty-aware landmark detection for robust localization with limited prior information. The thesis further presents near real-time georectification methods that directly register satel- lite imagery to planetary reference frames, supporting onboard mapping and situational awareness. Together, these contributions demonstrate how optimization and learning can enhance the autonomy, reliability, and scientific value of small satellite missions, enabling more capable exploration and operations in dynamic and uncertain space environments.