Daniel Alexander Ford

University of Arizona, IBM Research - Almaden

Papers

Total Citations

H-Index

About

Daniel Alexander Ford’s research bridges the frontiers of artificial intelligence and data storage systems, with a focus on autonomous exploration and efficient archival architectures. His most influential work, “Infomax control for acoustic exploration of objects by a mobile robot” (2011, 19 citations), introduces a pioneering framework where reinforcement learning optimizes control policies for partially observable Markov decision processes (POMDPs) using information gain as an intrinsic motivation. This approach enables robots to autonomously explore environments without predefined tasks, advancing lifelong learning and active sensing. In earlier contributions, Ford addressed critical challenges in tertiary storage. His paper “A log-structured organization for tertiary storage” (2002, 7 citations) proposes a system that conceals jukebox robotics and media complexities behind a uniform, random-access interface, significantly improving data management efficiency. Building on this, “Redundant Arrays of Independent Libraries (RAIL): The StarFish tertiary storage system” (1998, 4 citations) introduces a redundant array design that enhances reliability and performance in large-scale archival systems. Ford’s work demonstrates a unique ability to apply computational principles across domains, from robotic exploration to storage architecture, making him a notable figure in both AI-driven robotics and systems engineering.