This report reviews state-of-the-art artificial intelligence/machine learning (AI/ML) hardware and software technologies supporting autonomy on small, inexpensive platforms. It focuses on commodity hardware components and widely available software ecosystems for deep learning, the subset of AI/ML that uses multilayered neural networks to deliver best-in-class performance and accuracy for the low-level tasks that drive higher-level applications of autonomy.
Deep learning combines recent developments in high performance deep neural networks, massively parallel computing architectures, and hardware-optimized software components with large collections of real-world training data to support autonomy for small, inexpensive platforms.