Papers
11
Total Citations
302
H-Index
8
About
Kevin Green is a leading researcher in bipedal robotics, specializing in the intersection of trajectory optimization, reinforcement learning, and dynamic locomotion. His most impactful work centers on the Cassie robot, where he pioneered fast online multi-step motion planning that simultaneously optimizes center of mass motion, footholds, and compliance—a breakthrough cited over 135 times. Green’s contributions extend to sim-to-real learning, enabling bipedal robots to handle unsensed dynamic loads and execute agile maneuvers like dynamic turning and blind stair traversal without terrain estimation. Notably, he optimized running gaits for the 100m dash, comparing performance to human athletes and pushing the boundaries of robotic speed. With a total citation count exceeding 300, his work has been published in top robotics venues and has directly advanced the robustness and athleticism of legged systems. Green’s research is essential reading for anyone interested in bridging model-based control and learning for real-world locomotion.
Research Focus
Key Achievements
Top Papers
- 1Fast Online Trajectory Optimization for the Bipedal Robot Cassie135 citations · 2018
- 2Learning Task Space Actions for Bipedal Locomotion45 citations · 2021
- 3
- 4Sim-to-Real Learning for Bipedal Locomotion Under Unsensed Dynamic Loads29 citations · 2022
- 5
- 6Dynamic Bipedal Turning through Sim-to-Real Reinforcement Learning14 citations · 2022
- 7Design and control of a recovery system for legged robots10 citations · 2016
- 8Blind Bipedal Stair Traversal via Sim-to-Real Reinforcement Learning9 citations · 2021
- 9
- 10Learning Task Space Actions for Bipedal Locomotion3 citations · 2020