Papers
1
Total Citations
7
H-Index
1
About
Yufei Li is a rising researcher in autonomous robotics and real-time machine learning systems, with a focus on enabling efficient on-device Deep Reinforcement Learning (DRL). Their most cited work, "R³: On-Device Real-Time Deep Reinforcement Learning for Autonomous Robotics" (2023, 7 citations), addresses a critical bottleneck in deploying DRL on resource-constrained robotic platforms—such as autonomous vehicles and search-and-rescue robots—by proposing a framework that supports continuous model adaptation directly on edge devices. This contribution is pivotal for moving DRL from simulation-heavy training to practical, dynamic environments where real-time learning is essential. Li’s research bridges the gap between theoretical reinforcement learning and real-world robotic deployment, emphasizing computational efficiency and adaptability. With growing recognition for their work in on-device intelligence, Li is establishing a reputation for tackling the hardware-software co-design challenges that define next-generation autonomous systems. Their findings have implications for safer, more responsive robots that can learn and react without cloud dependency, marking Li as a promising voice in the future of embodied AI.
Research Focus
Key Achievements
Top Papers
- 1