Hansom Kim
Papers
2
Total Citations
19
H-Index
2
About
Hansom Kim’s research lies at the intersection of robotics, reinforcement learning, and multi-agent systems, with a focus on enabling intelligent, autonomous behavior in complex environments. His early work pioneered the integration of hierarchical deep reinforcement learning with Dynamic Movement Primitives (DMPs), allowing robots to learn and generalize skilled movements from a single demonstration—a significant step toward more adaptable and data-efficient robotic learning. This foundational paper has garnered 16 citations, reflecting its influence in the field of robot skill acquisition. More recently, Kim has tackled the pressing challenge of decentralized multi-agent trajectory planning for quadrotor swarms. His 2025 paper introduces a novel algorithm that guarantees goal convergence even in cluttered, obstacle-rich environments, effectively preventing deadlock or livelock—a critical advancement for scalable, real-world drone operations. By combining theoretical guarantees with practical scalability, Kim’s work is shaping the future of autonomous robotics, from industrial automation to aerial swarm coordination.
Research Focus
Key Achievements
Top Papers
- 1
- 2