NVIDIA Develops SONIC Framework for Advanced Humanoid Robot Control and Movement
- Published
- Source
- InterestingEngineering.com
Researchers at NVIDIA have developed a large-scale framework named SONIC that enables humanoid robots to perform a variety of natural movements, including running, jumping, and grasping, using simple commands. Unlike traditional controllers that are limited to specific tasks, SONIC employs a single policy trained on over 100 million motion frames, allowing for improved generalization and adaptability in motion.
The significance of SONIC lies in its ability to address the limitations of existing humanoid robotics control systems, which often rely on small neural networks tailored for individual tasks. By treating motion tracking as a scalable learning challenge, SONIC utilizes extensive human motion data to create a robust training signal, enhancing the robot's capability to execute diverse behaviors seamlessly.
Looking ahead, SONIC's architecture supports multimodal control, allowing inputs from video, text, and music to influence robot movements. The framework has already demonstrated impressive performance, achieving a 99.2 percent success rate in real-world applications. Future developments may focus on enhancing higher-level perception and reasoning to further advance humanoid autonomy.
Original report
New humanoid robot system lets machines run, jump and dance with simple commands
InterestingEngineering.com · Jijo MalayilThis 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
RobotToday Weekly November 9–13, 2026 RobotToday · 6 days ago
- 9
- 10
- 11
- 12
Related Suppliers
NVIDIA Robotics
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)
Israeli deep learning optimization startup acquired by NVIDIA in May 2024 for ~$300M; known for AutoNAC neural architecture search technology.
Piezo Sonic
Tokyo company making compact long-life high-torque ultrasonic (piezo) motors, with space-qualified variants and autonomous mobile robots.
WITTMANN BATTENFELD Deutschland GmbH
German subsidiary of WITTMANN Group supplying injection molding machines, linear robots, and automation peripherals to plastics processors.
Acheron Labs
Vienna-based robotics software startup building an LLM-driven control layer that lets Unitree's G1 humanoid and Go2 quadruped follow spoken commands.
Humanola
US start-up founded in 2025 offering VR teleoperation software for humanoids and robot arms and turning each operator session into robot-learning training data.
KAIST Hubo Lab (Humanoid Robot Research Center)
KAIST humanoid research centre that built HUBO and won the 2015 DARPA Robotics Challenge with DRC-HUBO+; it now develops a 3.25 m/s next-gen humanoid.
Assured Robot Intelligence
San Diego robot-AI start-up founded by Lerrel Pinto and Xiaolong Wang, building humanoid foundation models; acquired by Meta in May 2026.
Telefactor Robotics
US specialist in teleoperated robot vision, dexterous grippers, and control interfaces for bomb disposal and hazardous environment robots.
Roceso Technologies
Singapore soft robotics medical device company; maker of EsoGLOVE, a hand rehabilitation exoskeleton with FDA, CE, HSA, and TGA approvals in 30+ countries.
Noitom Robotics Technology (Shenzhen) Co., Ltd. 诺亦腾机器人
Shenzhen embodied-AI data company building motion-capture and teleoperation datasets for humanoid robots.
Maxinsights
San Francisco vendor, founded 2024, of annotated egocentric video, hand/body mocap and tactile data for training robot VLA and world action models.
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.