RealMan Robotics launches RealSource, a multi-modal real-world robot dataset

Embodied AI data and training platform comes from 10 real-world simulated environments

By Robotics 24/7 Staff    December 20, 2025         

RealMan Robotics launches RealSource, a multi-modal real-world robot dataset

RealMan Robotics

RealMan Robotics' RealSource platform generates real-world robot data for embodied AI.

Email Sign Up

Get news, papers, media and research delivered. Sign up for our free newsletters.

Stay up-to-date with news and resources you need to do your job. Research industry trends, compare companies and get weekly market intelligence with Robotics 24/7.

Robotics 24/7 newsletter
RealMan Robotics launches RealSource, a multi-modal real-world robot dataset

RealMan Robotics

RealMan Robotics' RealSource platform generates real-world robot data for embodied AI.

Embodied intelligence, modular robotic systems and ultra-lightweight humanoid robotic arm company RealMan Robotics announced the open-source release of RealSource. The China-based company describes RealSource as the world’s first high-quality, largest-modality multi-modal real-world robot dataset.

Designed to address the industry’s shortage of fully aligned real-world data, the company said the dataset provides essential support for next-generation robot perception, planning, and control algorithms in both academia and industry.

High-fidelity data across 10 real-world scenarios 

The dataset is built entirely on 10 real-world simulated environments within the company’s Beijing Humanoid Robot Data Training Center, and features two defining characteristics: exceptional data quality and the world’s most complete multi-modal coverage.

The 3,000 m² facility features two distinct zones:

  • Training Zone: High-volume, efficient robot training for foundational manipulation tasks.
  • Scenario Zone (“Robot University”): Ten real-world environments, including smart home & eldercare, daily living, agriculture, new retail, automotive assembly, and catering.

RealMan said that the robots perform lifelike tasks such as opening refrigerator doors, folding laundry and sorting materials on factory lines. Data collection is conducted outside the “laboratory greenhouse,” directly addressing the complexity, noise and diversity of real-world environments. The company said that this ensures high realism, strong practicality and superior generalization across scenarios.

Key metrics collected in the dataset include:

  • 100% modality completeness
  • 78% noise-resistance
  • 82.1% smoothness

RealMan said these metrics set a new benchmark for real-world embodied intelligence datasets.

Multi-modal data with six core advantages

RealMan said that the dataset covers the full perception-decision-execution chain, integrating RGB images, joint angles & velocities, six-axis force, end-effector pose, action commands, timestamps and camera parameters.

All sensors are aligned to a unified physical coordinate system, developing the following advantages:

  • Ultra-low frame loss (<0.5%): Continuous, reliable recording even at high speed.
  • High-precision motion control: Millisecond-level joint data for smooth, accurate operations.
  • Factory-calibrated for out-of-the-box use: No extra calibration required.
  • Generalization-oriented collection: Tasks repeated under diverse object, environment and lighting conditions.
  • Exoskeleton teleoperation: 1:1 human-to-robot motion mapping for high-fidelity demonstration.

RealMan said its robots are designed to match adult human arm proportions, achieving high integration with real-world tasks.

 

Latest in Sortation

Latest in Artificial Intelligence

Article Topics

Artificial Intelligence   Industrial Automation   Robot Arm   Components   Motion Control   Sensors   Cameras   Software   Data Management   Simulation   News   Press Release   Assembly   China   Data Management   Humanoid   Open Source   Perception   Sortation  

All topics

Enjoyed this article? Add Robotics 24/7 as a preferred source in Google Search.

Editors' Picks

Jensen Huang resigns as NVIDIA CEO amid affairs scandal
Jensen Huang resigns as NVIDIA CEO amid affairs scandal

Colette Kress, current EVP and CFO of NVIDIA named interim CEO

SoftBank’s proposed $5.4B acquisition of ABB Robotics blocked by China
SoftBank’s proposed $5.4B acquisition of ABB Robotics blocked by China

China's Office of the Working Mechanism for Foreign Investment Security…

White House targets robotics imports in new national security trade review
White House targets robotics imports in new national security trade review

President Trump orders a review of robotics imports over national security…

OSARO SightWorks advances AI-powered robotic picking and packing
OSARO SightWorks advances AI-powered robotic picking and packing

Platform helps robots adapt to complex tasks