NVIDIA Showcases Microduck Robots Performing Somersaults and Recovering from Falls
- Published
- Source
- InterestingEngineering.com
During the GTC Berlin event, four Microduck robots, each about 10 inches tall, showcased their abilities by walking, tumbling, and attempting somersaults. Developed by Pollen Robotics, these small bipeds demonstrated their agility and responsiveness under the guidance of NVIDIA CEO Jensen Huang, who issued commands that led to both successful movements and humorous mishaps.
The demonstration underscored the advanced computing capabilities behind the Microducks, which were trained in the cloud using NVIDIA's powerful systems. Their movements were refined within an Omniverse digital twin on an RTX Spark machine, highlighting the integration of cutting-edge technology in robotics. The performance illustrated not only the robots' potential but also the challenges they face in real-time interactions.
Looking ahead, the Microduck robots, equipped with 15 motors and various sensors, offer a glimpse into the future of robotic mobility and interaction. Their ability to perform tasks like picking up objects and roller-skating adds versatility to their design. No further timeline was disclosed at the time of publication.
Original report
NVIDIA’s tiny robots steal the show with somersaults, stumbles and funny falls
InterestingEngineering.com · Atharva GosaviThis briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
Related Suppliers
NVIDIA Robotics
United States
NVIDIA robotics division delivering Isaac simulation and training tools, Jetson edge compute modules, and Omniverse digital twin frameworks for physical AI.
Deci AI (Acquired by NVIDIA)
Israel
Israeli deep learning optimization startup acquired by NVIDIA in May 2024 for ~$300M; known for AutoNAC neural architecture search technology.
Pollen Robotics
France
Bordeaux, France humanoid-robot maker founded 2016 by Matthieu Lapeyre and Pierre Rouanet, now part of Hugging Face since April 2025.
Mondo Robotics 妙动科技
Hong Kong
Hong Kong-registered maker of Beni, a 1.75 kg self-balancing 4K camera robot; Kickstarter raised about EUR 1.7M in 2026.
Robot Advisors
United States
US-based robotics consulting firm founded 2023 in Rye, NH; provides objective, data-driven guidance for warehouse and supply chain robotic automation selection.
Anima Technology Pte. Ltd.
Singapore
Physical-AI data startup whose AXIS platform turns browser users into operators of MuJoCo-based simulated robots to crowdsource manipulation trajectories.
Hybrid Robotics Lab, UC Berkeley
United States
UC Berkeley lab led by Prof. Koushil Sreenath researching nonlinear control of legged and aerial robots; creator of the open-source Berkeley Humanoid Lite.
Agility Robotics
United States
US humanoid robot maker behind Digit, first commercially deployed humanoid in logistics; spun out of Oregon State University in 2015.
Songying Technology 松应科技
China
Songying Technology (ORCA3D) is a Shanghai physics-AI simulation software maker for embodied-AI robot training, backed by early-stage VC investors.
Ultralytics
United States
Frederick, Maryland computer vision company founded by Glenn Jocher; creator of the YOLO object detection model family and a cloud training platform.
phospho (YC W24)
France
French AI robotics startup (YC W24) providing open-source phosphobot toolkit and hardware kits to train Vision-Language-Action models on low-cost robot arms.
Accenture
Ireland
Dublin-based global consulting giant offering robotics integration, AI orchestration, and automation services across manufacturing, logistics, and healthcare.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
