Shallow blue

摘要

We report on Shallow Blue (SB), an autonomous chess-playing agent designed on a limited budget with off-the-shelf consumer components. The system combines vision, piece manipulation, and decision-making functions to allow autonomous play against humans. SB demonstrates the increasing sophistication available to educators and students with consumer grade hardware, as well as the growth of opportunities for integrated software and hardware design by advanced undergraduate students. The paper documents the design, implementation, performance, and ongoing development of SB and its component systems.