Hyo-Byung Jun
Papers
2
Total Citations
7
H-Index
2
About
Hyo-Byung Jun is a pioneering researcher in the field of collective autonomous robotics, with a focus on how groups of robots can learn and evolve cooperative behaviors. His work bridges reinforcement learning and evolutionary computation, particularly through the use of distributed genetic algorithms and dynamic recurrent neural networks. In his most cited paper (2002, 4 citations), Jun introduced a novel framework where robots generate internal reinforcement signals via fuzzy inference, enabling them to adapt their behaviors without centralized control. Earlier, in his 1998 work (3 citations), he explored the emergence of cooperative behavior by combining reinforcement learning with conditional evolution—a phenomenon inspired by social animal societies. Though citation counts are modest, these foundational studies represent early and influential contributions to the subfield of multi-robot systems, anticipating later advances in swarm intelligence and decentralized learning. Jun’s work is notable for its interdisciplinary approach, merging concepts from artificial life, machine learning, and control theory to address the challenge of achieving high-level cooperation from low-level individual learning.
Research Focus
Key Achievements
Top Papers
- 1
- 2