- Today
- Holidays
- Birthdays
- Reminders
- Cities
- Atlanta
- Austin
- Baltimore
- Berwyn
- Beverly Hills
- Birmingham
- Boston
- Brooklyn
- Buffalo
- Charlotte
- Chicago
- Cincinnati
- Cleveland
- Columbus
- Dallas
- Denver
- Detroit
- Fort Worth
- Houston
- Indianapolis
- Knoxville
- Las Vegas
- Los Angeles
- Louisville
- Madison
- Memphis
- Miami
- Milwaukee
- Minneapolis
- Nashville
- New Orleans
- New York
- Omaha
- Orlando
- Philadelphia
- Phoenix
- Pittsburgh
- Portland
- Raleigh
- Richmond
- Rutherford
- Sacramento
- Salt Lake City
- San Antonio
- San Diego
- San Francisco
- San Jose
- Seattle
- Tampa
- Tucson
- Washington
Georgia Tech Researchers Develop New Framework to Improve Humanoid Robot Stability
Breakthrough algorithm allows two-legged robots to better navigate unpredictable terrain and recover from disturbances.
Published on Feb. 25, 2026
Got story updates? Submit your updates here. ›
Researchers at Georgia Tech, led by Ye Zhao and robotics Ph.D. student Zhaoyuan Gu, have developed a new framework that provides humanoid robots with a set of pre-defined rules to quickly assess and correct their movements in response to changes in their environment. This allows the robots to maintain stability and recover from disturbances without the need for human intervention. The team tested their framework using the two-legged robot Cassie, demonstrating an 81% improvement in the robot's ability to recover from instability compared to existing methods.
Why it matters
Achieving stable and reliable locomotion is a crucial challenge for humanoid robots as they are inherently prone to instability, especially when navigating dynamic environments. This research represents a significant step forward in enabling two-legged robots to safely and effectively perform tasks in the real world, such as maintenance work on ships or carrying equipment in outdoor settings.
The details
The Georgia Tech team developed a rule-based approach that allows robots to quickly analyze their environment and adjust their gait to maintain balance. Unlike previous methods, this framework does not rely on human intervention, as the robot autonomously assesses and corrects its course. The researchers tested the new system using Cassie, a two-legged robot, within Georgia Tech's Human Augmentation Core Facility, which includes a Computer-Aided Rehabilitation Environment (CAREN) treadmill and a 'BumpEm' system to simulate challenging terrain and disturbances.
- The research team published their findings in an IEEE Transactions on Robotics paper.
- The Office of Naval Research will further test the project at sea in Arlington, Virginia.
The players
Ye Zhao
A researcher leading the team at Georgia Tech developing the new framework for improving humanoid robot stability.
Zhaoyuan Gu
A robotics Ph.D. student at Georgia Tech who is part of the team developing the new framework for improving humanoid robot stability.
Cassie
A two-legged robot used by the Georgia Tech team to test the new framework for improving humanoid robot stability.
Office of Naval Research
An organization that will further test the Georgia Tech team's project at sea in Arlington, Virginia.
What they’re saying
“Robotics engineers should consider not only a robot's mechanical design, but also its algorithms, intelligence, and brain.”
— Zhaoyuan Gu, Robotics Ph.D. Student (newsy-today.com)
“Future research will explore mimicking human recovery mechanisms, such as hopping, to further enhance robotic stability.”
— Ye Zhao, Researcher (newsy-today.com)
What’s next
The Office of Naval Research will further test the project at sea in Arlington, Virginia.
The takeaway
This research represents a significant advancement in enabling humanoid robots to navigate dynamic environments and recover from disturbances, paving the way for their real-world deployment in applications such as maintenance, logistics, and hazardous tasks.
Atlanta top stories
Atlanta events
Feb. 25, 2026
Duel RealityFeb. 25, 2026
Monaleo - Who Did The Body TourFeb. 25, 2026
Tours: Truist Park




