Mozhgan Navardi
Papers
1
Total Citations
2
H-Index
1
About
Mozhgan Navardi is a researcher at the forefront of embodied AI and robot learning, specializing in hierarchical reinforcement learning (HRL) and sim-to-real transfer for multi-goal navigation. Her major contribution, the "ReProHRL" framework, tackles the persistent challenge of training robots to navigate complex, real-world environments with sparse rewards. By combining hierarchical agents with a novel progressive training strategy that leverages simulation for initial learning and real-world fine-tuning, her work bridges the critical gap between controlled lab settings and practical deployment. This approach, detailed in her 2023 paper, has already garnered attention for its potential to make autonomous navigation more robust and sample-efficient. Navardi’s research directly addresses the limitations of standard RL algorithms in multi-goal scenarios, offering a scalable pathway for robots to operate effectively outside of simulation. Her work is foundational for advancing autonomous systems in logistics, service robotics, and assistive technologies, positioning her as a key voice in the next generation of intelligent, real-world robot learning.
Research Focus
Key Achievements
Top Papers
- 1