Elad Liebman

Papers

Total Citations

H-Index

About

Elad Liebman is a researcher whose work lies at the intersection of artificial intelligence, robotics, and optimization, with a particular focus on enabling autonomous systems to learn and perform in dynamic, real-world environments. His most cited paper, "Fast and Precise Black and White Ball Detection for RoboCup Soccer" (2018, 25 citations), addresses a fundamental challenge in robot perception, developing algorithms that allow robots to quickly and accurately identify objects under the constraints of competitive play—a critical contribution to the RoboCup domain. Liebman is also a key contributor to the UT Austin Villa robot soccer team, a project that has won multiple RoboCup championships and served as a testbed for innovations spanning AI, multi-agent coordination, and control. His work on "Adaptation of Surrogate Tasks for Bipedal Walk Optimization" (2016) tackles the practical problem of high sample costs in robot learning, proposing methods to train on cheaper, approximate tasks while maintaining performance on the real objective. Through these contributions, Liebman demonstrates a commitment to bridging the gap between theoretical AI and physically grounded robotic systems, with his research helping to push the boundaries of what autonomous robots can achieve in competitive and unstructured settings.