Allan Axelrod

Papers

Total Citations

H-Index

About

Allan Axelrod is a researcher advancing the frontier of multi-agent robotics and autonomous decision-making under uncertainty. His primary research areas include coordinated multi-agent systems, stochastic optimization, and information-theoretic search strategies. Axelrod’s major contributions lie in developing algorithms that enable robots to operate intelligently in partially observable environments with limited communication. In his most-cited work, "Agbots 2.0: Weeding Denser Fields with Fewer Robots" (2020, 9 citations), he introduces a novel strategy combining Entropic Value-at-Risk (EVaR) with the Gittins index, allowing agricultural robots to dynamically balance exploration and exploitation when weed density is unknown. This approach significantly improves efficiency in dense fields, reducing the number of robots needed while maintaining high weeding performance. His earlier work, "Aided Optimal Search: Data-Driven Target Pursuit from On-Demand Delayed Binary Observations" (2018, 4 citations), tackles the challenge of target tracking with intermittent, delayed feedback. Though his citation counts are modest, Axelrod’s contributions are notable for their practical focus on real-world deployment constraints, such as partial information and resource limitations. His research bridges theoretical optimization with tangible applications in precision agriculture and autonomous search, offering valuable insights for students and researchers working on scalable, robust multi-agent systems.