{"688239":{"#nid":"688239","#data":{"type":"news","title":" Humanoid Robots Make Confident Strides Toward Walking Stability","body":[{"value":"\u003Cp\u003E\u201cHumanoid robots are coming.\u201d\u003C\/p\u003E\u003Cp\u003EWhile this statement might cause anxiety for some, for one Georgia Tech research team, working with humanlike robots couldn\u2019t be more exciting.\u003C\/p\u003E\u003Cp\u003EBipedal \u2014 or two-legged \u2014 autonomous robots can be quite agile. This makes them useful for performing tasks on uneven terrain, such as carrying equipment through outdoor environments or performing maintenance on an ocean-going ship. However, unstable or unpredictable conditions also increase the possibility of a robot wipeout.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe researchers, led by \u003Ca href=\u0022https:\/\/research.gatech.edu\/people\/ye-zhao\u0022\u003EYe Zhao\u003C\/a\u003E, director of the Georgia Tech \u003Ca href=\u0022https:\/\/lab-idar.gatech.edu\/\u0022\u003ELaboratory for Intelligent Decision and Autonomous Robots\u003C\/a\u003E (LIDAR), and Zhaoyuan Gu, a robotics Ph.D. student, wanted to develop a real-time planning and control framework that guarantees a robot\u0027s safety and recovery when traversing difficult terrain. The autonomous nature of this framework means the robots can make their own decisions without direct assistance from a human. For example, if an unexpected obstacle appears in its path, a robot equipped with this new framework could catch itself instead of falling.\u003C\/p\u003E\u003Cp\u003EUntil now, there\u2019s been a significant lack of research into how a robot recovers when its direction shifts \u2014 for example, a robot losing balance when a truck makes a quick turn. The team aims to fix this research gap.\u0026nbsp;\u003C\/p\u003E\u003Ch4\u003E\u003Cstrong\u003EPutting the Project Pieces Together\u003C\/strong\u003E\u003C\/h4\u003E\u003Cp\u003EIn an \u003Ca href=\u0022https:\/\/doi.org\/10.1109\/TRO.2025.3582820\u0022\u003E\u003Cem\u003EIEEE Transactions on Robotics\u003C\/em\u003E\u003C\/a\u003E paper, the researchers describe a first-of-its-kind strategy that gives robots a clear set of rules for reacting when something changes in its path. These rules help the robot make quicker decisions and take more confident steps. When the robot senses that its current plan might not keep it stable, it uses these rules to adjust its next few steps, so it can continue moving safely. In earlier experiments, which lacked this framework, two-legged robots struggled to identify a solution for stability and were prone to falling.\u003C\/p\u003E\u003Cp\u003EThe researchers implemented the new framework with Cassie, a two-legged robot. Inside Tech\u2019s 3,000-square-foot \u003Ca href=\u0022https:\/\/research.gatech.edu\/robotics\/human-augmentation-core\u0022\u003EHuman Augmentation Core Facility\u003C\/a\u003E, the Cassie robot confidently walks on a Computer-Aided Rehabilitation Environment (CAREN) \u2014 a treadmill system that can be programmed to move in any direction at different times. When the team realized CAREN is limited in how much force it can inflict, they added a BumpEm system, which creates a stronger jerk to further stress-test Cassie\u2019s gait.\u003C\/p\u003E\u003Ch4\u003E\u003Cstrong\u003EThe Results\u003C\/strong\u003E\u003C\/h4\u003E\u003Cp\u003EThrough these experiments, the researchers found that their new programming framework outperforms state-of-the-art methods with more certainty, faster decision-making, higher collision avoidance, and the ability to reliably walk on moving platforms and varying types of terrain.\u003C\/p\u003E\u003Cp\u003EZhao said, \u201cThe results we got through this project are very impressive. They\u2019re the most comprehensive and extensive hardware results we\u2019ve published so far.\u201d\u003C\/p\u003E\u003Cp\u003EThough significant, the real-world results weren\u2019t perfect. The robot doesn\u2019t perform as well when moving downhill, which requires it to take riskier steps and walk less efficiently. However, the only time Cassie completely failed to recover its gait was during a difficult scenario involving a very wide step and a cross-legged maneuver. Recovery simply wasn\u2019t feasible given the spatial limits of the narrow treadmill.\u003C\/p\u003E\u003Ch4\u003E\u003Cstrong\u003ENext Steps for Walking Robots\u003C\/strong\u003E\u003C\/h4\u003E\u003Cp\u003EOverall, the researchers\u2019 framework increases by 81% Cassie\u2019s ability to recover from instability. The team noted that bipedal stability in robotics needs further research. If these walking robots are to be fully integrated into our society, they must be reliable.\u003C\/p\u003E\u003Cp\u003E\u201cThis paper may serve as a foundation for continued work on walking robots,\u201d said Zhao. \u201cOur work may inspire further research that can imitate or learn from the framework we\u2019ve created.\u201d\u003C\/p\u003E\u003Cp\u003EOther ways of walking recovery are yet to be tested. For example, humans often hop to counteract instability or uneven footing; mirroring this with two-legged robots could be the next step in the team\u2019s research.\u003C\/p\u003E\u003Cp\u003EThey would like to eventually enable the use of autonomous two-legged robots in marine environments, where ship maintenance and operations require risky, strenuous labor. Ideally, these robots could reliably, safely, and efficiently perform these kinds of tasks.\u003C\/p\u003E\u003Cp\u003EThe project will be tested at sea through the Office of Naval Research in Arlington, Virginia.\u003C\/p\u003E\u003Cp\u003E\u201cHumanoid robots are coming to your homes, coming to the factories, coming to logistics. They\u0027re going to show up on the street. It\u2019s exciting,\u201d said Gu.\u003C\/p\u003E\u003Cp\u003ERobotics engineers should consider not only a robot\u2019s mechanical design, but also its algorithms, intelligence, and brain. Being able to safely and regularly interact with these robots requires this foundational work.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003E\u2014 By Chloe Morris\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003E\u201cRobust-Locomotion-By-Logic: Perturbation-Resilient Bipedal Locomotion via Signal Temporal Logic Guided Model Predictive Control.\u201d \u003Ca href=\u0022https:\/\/ieeexplore.ieee.org\/document\/11049016\u0022\u003Ehttps:\/\/doi.org\/10.1109\/TRO.2025.3582820\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cem\u003EFunding for this research is provided by the Office of Naval Research Young Investigator Program and the National Science Foundation CAREER Program.\u003C\/em\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cem\u003EResearchers on this project include LIDAR Director Ye Zhao, Ph.D. student Zhaoyuan Gu, and master\u2019s students Yuntian Zhao, Yipu Chen, and Rongming Guo. Other contributors from the\u003C\/em\u003E\u003Ca href=\u0022https:\/\/power.me.gatech.edu\/\u0022\u003E\u003Cem\u003E Physiology of Wearable Robotics Lab\u003C\/em\u003E\u003C\/a\u003E\u003Cem\u003E include \u003C\/em\u003E\u003Ca href=\u0022https:\/\/research.gatech.edu\/people\/gregory-sawicki\u0022\u003E\u003Cem\u003EGregory Sawicki\u003C\/em\u003E\u003C\/a\u003E\u003Cem\u003E, director, and Jennifer Leestma (Ph.D. ROBO, 2024).\u0026nbsp;\u003C\/em\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cem\u003EThis research is also supported by the \u003C\/em\u003E\u003Ca href=\u0022https:\/\/vip.gatech.edu\/teams\/entry\/1281\/\u0022\u003E\u003Cem\u003EAgile Locomotion and Manipulation team\u003C\/em\u003E\u003C\/a\u003E\u003Cem\u003E, part of Georgia Tech\u2019s Vertically Integrated Projects program.\u003C\/em\u003E\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EGeorgia Tech researchers have developed a new \u201cthinking\u201d technology for two-legged robots, increasing their balance and agility.\u0026nbsp;\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Georgia Tech researchers have developed a new \u201cthinking\u201d technology for two-legged robots, increasing their balance and agility.\u00a0"}],"uid":"28766","created_gmt":"2026-02-13 14:34:19","changed_gmt":"2026-02-19 15:05:30","author":"Shelley Wunder-Smith","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2026-02-18T00:00:00-05:00","iso_date":"2026-02-18T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"679321":{"id":"679321","type":"image","title":"humanoid-robotos.png","body":"\u003Cp\u003EYipu Chen (seated) and Zhaoyuan Gu (standing) on the CAREN treadmill system\u003C\/p\u003E","created":"1771337425","gmt_created":"2026-02-17 14:10:25","changed":"1771337425","gmt_changed":"2026-02-17 14:10:25","alt":"Two individuals on a large circular motion platform in a research lab, with one person seated cross\u2011legged on the platform and another suspended in a harness wearing a Georgia Tech exoskeleton system.","file":{"fid":"263464","name":"humanoid-robotos.png","image_path":"\/sites\/default\/files\/2026\/02\/17\/humanoid-robotos.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2026\/02\/17\/humanoid-robotos.png","mime":"image\/png","size":13065997,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2026\/02\/17\/humanoid-robotos.png?itok=xpm563Bv"}},"679359":{"id":"679359","type":"video","title":"Cassie Robot Walking on the CAREN Treadmill","body":"\u003Cp\u003EThe Cassie robot walks confidently on the CAREN treadmill, making adjustments to its gait as the platform moves.\u003C\/p\u003E","created":"1771444600","gmt_created":"2026-02-18 19:56:40","changed":"1771444600","gmt_changed":"2026-02-18 19:56:40","video":{"youtube_id":"klhX6qFRZEs","video_url":"https:\/\/youtu.be\/klhX6qFRZEs"}}},"media_ids":["679321","679359"],"groups":[{"id":"1188","name":"Research Horizons"}],"categories":[],"keywords":[],"core_research_areas":[{"id":"39521","name":"Robotics"}],"news_room_topics":[{"id":"71881","name":"Science and Technology"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EMedia contact:\u003Cbr\u003E\u003Cbr\u003E\u003Ca href=\u0022mailto:swundersmith3@gatech.edu\u0022\u003EShelley Wunder-Smith\u003C\/a\u003E\u003Cbr\u003EDirector of Research Communications\u003Cbr\u003EGeorgia Institute of Technology\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}