Juan Pereda

Papers

Total Citations

H-Index

About

Juan Pereda is a researcher whose work bridges the frontiers of robotics, artificial intelligence, and multi-agent systems. His most influential contribution, "Selective Method Based on Auctions for Map Inspection by Robotic Teams" (2011, 6 citations), introduces an innovative auction-based coordination strategy that enables teams of robots to efficiently partition and inspect unknown environments. This work has been foundational for researchers exploring decentralized decision-making in swarm robotics, demonstrating how market-inspired mechanisms can optimize exploration tasks without central control. Earlier, Pereda contributed to the field of robot control with his study on "Comparative Analysis of Artificial Neural Network Training Methods for Inverse Kinematics Learning" (2006, 2 citations), where he systematically evaluated different neural network training algorithms for solving the complex inverse kinematics problem in robotic manipulators. This early work provided practical insights for engineers seeking to implement learning-based control in real-world robotic systems. Though his citation counts reflect a focused, specialized audience, Pereda's research has advanced practical solutions for multi-robot coordination and intelligent control, making his work a valuable reference for students and researchers interested in auction-based task allocation and neural network applications in robotics.