Papers
1
Total Citations
7
H-Index
1
About
Dr. Junli Ren is a leading researcher in humanoid robotics, with a primary focus on perceptive locomotion and whole-body control. Their most-cited work, "Learning Humanoid Locomotion with Perceptive Internal Model" (2025, 7 citations), tackles a fundamental challenge: enabling humanoid robots to navigate complex, unstructured terrains by integrating real-time sensory feedback. Unlike quadruped robots that can rely on "blind" policies, humanoids demand precise perception due to their high degrees of freedom and unstable morphology. Ren’s key contribution lies in developing a framework that fuses proprioceptive and exteroceptive signals into an internal model, allowing the robot to anticipate and adapt to terrain variations—a critical step toward robust, real-world deployment. This work bridges the gap between simulation and physical hardware, offering a scalable solution for dynamic environments. Though early in its citation trajectory, the paper has already influenced subsequent studies in reinforcement learning for humanoid control. Ren’s research continues to push the boundaries of legged locomotion, with implications for disaster response, industrial automation, and assistive robotics. Their work exemplifies how principled integration of perception and control can unlock the full potential of humanoid platforms.
Research Focus
Key Achievements
Top Papers
- 1Learning Humanoid Locomotion with Perceptive Internal Model7 citations · 2025