Jemin Hwangbo

About

Jemin Hwangbo is a pioneering robotics researcher whose work sits at the intersection of legged locomotion, reinforcement learning, and robot control. Best known for his transformative contributions to quadrupedal robotics, Hwangbo has fundamentally reshaped how autonomous robots learn to move through complex, real-world environments. His 2019 paper "Learning agile and dynamic motor skills for legged robots" — now with nearly 1,400 citations — demonstrated that reinforcement learning could produce locomotion behaviors surpassing those achieved through hand-crafted control, establishing a new paradigm for the field. As a central contributor to the ANYmal quadrupedal robot platform (864 citations), he helped engineer one of the most capable and widely studied robotic systems in existence, notable for its torque-controllable, impact-resilient design. His 2022 work on perceptive locomotion in wild environments (729 citations) pushed the boundaries further, enabling robots to navigate challenging terrain using exteroceptive sensing. Beyond locomotion learning, Hwangbo has made methodological contributions in contact dynamics simulation and concurrent policy-estimator training frameworks. His research consistently bridges the sim-to-real gap, producing controllers that perform robustly outside laboratory settings — a benchmark achievement that continues to inspire the next generation of robotics researchers worldwide.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning agile and dynamic motor skills for legged robots

   1,398 citations · 2019
2. 2
   ANYmal - a highly mobile and dynamic quadrupedal robot

   864 citations · 2016
3. 3
   Learning robust perceptive locomotion for quadrupedal robots in the wild

   729 citations · 2022
4. 4
   ANYmal - A Highly Mobile and Dynamic Quadrupedal Robot

   267 citations · 2016
5. 5
   Per-Contact Iteration Method for Solving Contact Dynamics

   230 citations · 2018
6. 6
   Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion

   179 citations · 2022
7. 7
   Perception-less terrain adaptation through whole body control and hierarchical optimization

   162 citations · 2016
8. 8
   Dynamic locomotion and whole-body control for quadrupedal robots

   149 citations · 2017
9. 9
   Learning quadrupedal locomotion on deformable terrain

   147 citations · 2023
10. 10
    Practice Makes Perfect: An Optimization-Based Approach to Controlling Agile Motions for a Quadruped Robot

    117 citations · 2016

Key Collaborators

Contact & Links