Papers
4
Total Citations
150
H-Index
3
About
Hao Ju is a leading researcher at the intersection of robotics and artificial intelligence, with a primary focus on deep reinforcement learning and sim-to-real transfer for robotic control. His most impactful work, "Transferring policy of deep reinforcement learning from simulation to reality for robotics" (2022), has garnered 128 citations, establishing a foundational framework for bridging the gap between simulated training environments and real-world robotic applications. Ju’s contributions address critical challenges in robotics—sample efficiency and safety—by developing innovative transfer learning techniques that allow policies trained in simulation to perform reliably in physical systems. His subsequent research, including "Sim-to-Real Policy and Reward Transfer with Adaptive Forward Dynamics Model" (2023) and "Transferring Meta-Policy From Simulation to Reality via Progressive Neural Network" (2024), further refines these methods, enhancing policy robustness and adaptability. Notably, Ju’s earlier work on a robot-assisted system for minimally invasive spine surgery (2008) demonstrates his long-standing commitment to practical, high-impact applications, achieving superior accuracy in percutaneous vertebroplasty. With a career spanning both foundational theory and clinical robotics, Hao Ju continues to shape the future of intelligent, real-world robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4