Hafiyanda Razan
Papers
3
Total Citations
12
H-Index
2
About
Hafiyanda Razan is a robotics researcher focused on bridging the gap between simulation and the real world for autonomous mobile robots. His primary research areas include reinforcement learning, sim-to-real transfer learning, and autonomous navigation for omnidirectional robots. Razan’s major contribution lies in developing policies that allow robots trained in simulated environments to effectively operate in complex, real-world settings. His most cited work, “Using sim-to-real transfer learning to close gaps between simulation and real environments through reinforcement learning” (2021, 6 citations), directly addresses this challenge. In related studies, he applied Deep Deterministic Policy Gradient (DDPG) to enable an omnidirectional robot to find paths while avoiding both static and dynamic obstacles, aiming to alleviate labor shortages in the distribution industry. His 2020 paper on policy transfer for warehouse support (4 citations) demonstrates a practical application of his methods. Though early in his career, Razan’s focused work on making reinforcement learning viable for real robot control is a meaningful step toward practical, autonomous warehouse assistants.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3