From Human Motion to Robot Intelligence

AgileMaster

Humanoid Teleoperation Solution

Built for Teleoperation and robot demonstration data collection, AgileMaster combines high-precision full-body IMU motion capture with Human-to-Robot Mapping to deliver structured, high-fidelity motion data for humanoid robots, robotic arms, Isaac GR00T workflows, imitation learning, VLA training, simulation, and digital twin applications.
Request a Demo
TRUSTED BY INDUSTRY LEADERS & ECOSYSTEM PARTNERS
loop_logo_nvidia
loop_logo_ur
loop_logo_fr
loop_logo_tm
loop_logo_uni
loop_logo_ma
loop_logo_te
loop_logo_ag
loop_logo_ins
loop_logo_alt

Accelerating Physical AI and Humanoid Robotics

j-mex AgileMaster is a Teleoperation solution built primarily for humanoid robots, with support for robotic arms and multiple robot embodiments. Through high-precision full-body motion capture and Human-to-Robot Mapping, AgileMaster transforms real human motion into robot control signals and structured training data.

Combined with robot execution and synchronized data recording, AgileMaster enables practical workflows for Teleoperation, imitation learning, VLA training, simulation, and digital twin integration—accelerating the path from human demonstration to real-world robot deployment.

Accelerate Robot Training from Human Demonstration to Execution

High-quality robot training starts with reliable human motion data and efficient Human-to-Robot Mapping. AgileMaster streamlines the path from human demonstration to robot execution by improving motion data fidelity, mapping efficiency, and robot setup—helping teams collect training data faster across humanoid and robotic arm platforms.
banner 02
High-Fidelity Full-Body Motion Data
The Challenge
Traditional motion capture approaches may focus primarily on end-effector poses or limited body segments, leaving out the multi-joint motion context needed for complex robot manipulation and training tasks.
The AgileMaster Advantage
AgileMaster captures synchronized full-body, multi-joint human motion using high-precision IMU sensing and low-latency motion streaming, providing detailed and consistent demonstration data for Teleoperation, imitation learning, and VLA training workflows.
banner 03
Human-to-Robot Mapping
The Challenge
Human and robot bodies differ in joint structure, range of motion, and kinematic constraints. Converting human demonstrations into executable robot motion often requires extensive manual mapping and robot-specific development.
The AgileMaster Advantage

AgileMaster uses Human-to-Robot Mapping and Retargeting to translate human motion into robot-compatible control signals while accounting for robot topology, joint ranges, and motion constraints.

For arm control, developers can switch between end-effector and humanoid arm control modes, with motion and coordinate data streamed through ROS2 for robot integration and execution.

banner 04
Faster Robot Setup & Deployment
The Challenge

Traditional robot setup often involves programming or graphical path editing, followed by repeated test runs, adjustments, and path optimization—making task setup time-consuming and difficult to iterate.

The AgileMaster Advantage

AgileMaster combines Teleoperation with simulation workflows in NVIDIA Isaac Sim, allowing developers to demonstrate and refine robot operations more intuitively before deployment.

Validated motion and operation paths can then support automated routine development, reducing repetitive setup and accelerating robot task deployment.

Three Core Capabilities to Accelerate Robot Development

AgileMaster brings together three core capabilities—End-to-End Teleoperation, Human-to-Robot Mapping, and NVIDIA Robotics Ecosystem Integration—to streamline robot control, motion retargeting, simulation, and training data workflows for Physical AI development.

End-to-End Teleoperation

AgileMaster combines high-precision full-body motion capture with low-latency motion streaming to enable stable, responsive robot control and demonstration data collection.

Designed for multiple robot embodiments, AgileMaster supports humanoid robots, cobots, and robotic arms, with configurable integration for different robot platforms and task requirements.

Key Capabilities
  • Low-latency real-time motion streaming
  • Full-body and multi-joint robot control
  • Humanoid, cobot, and robotic arm support
  • Robot demonstration data collection
  • Custom robot integration

Human-to-Robot Mapping

AgileMaster uses proprietary Motion Retargeting technology to translate human skeletal motion into executable multi-axis robot joint control signals in real time.

Built-in Skeleton Topology Switching enables developers to quickly switch between humanoid and cobot / robotic arm configurations, while accounting for different robot structures, joint ranges, and motion constraints.

Motion and coordinate data can be streamed through ROS2 for robot control, integration, and downstream development.

Key Capabilities
  • Real-time Motion Retargeting
  • Human-to-Robot Mapping
  • Skeleton Topology Switching
  • End-effector and humanoid arm control modes
  • Multi-axis Joint Control
  • ROS2 motion and coordinate output

NVIDIA Robotics Ecosystem Integration

AgileMaster integrates with widely adopted robotics standards and NVIDIA robotics development tools to connect human demonstration, simulation, robot execution, and training data workflows.

With support for URDF and ROS2, AgileMaster can integrate with NVIDIA Isaac Sim and Isaac Lab for Teleoperation, simulation, validation, and robot training data collection, while extending into Isaac GR00T and VLA training workflows.

This provides developers with a more streamlined path from human motion and simulation to real-world robot development.

Key Capabilities
  • ROS2 and URDF support
  • NVIDIA Isaac Sim integration
  • NVIDIA Isaac Lab workflows
  • Simulation and Digital Twin development
  • Isaac GR00T workflow support
  • VLA training workflows
  • Sim-to-Real development

j-mex AgileMaster
Humanoid Teleoperation Solution Operational Architecture

Architecture 0204

Powering Diverse Robot Applications

banner 08
Teleoperation
Ideal for hazardous environments and high-precision tasks — ensuring operator safety and accurate mission execution.
banner 01
Embodied AI Training
Rapidly generate high-quality, high-fidelity demonstration data for VLA (Vision-Language-Action) training and Imitation Learning.
banner 09
Industrial Digital Twin
Combine Teleoperation with Isaac Sim/Lab to synchronize real robot states in a virtual environment in real time — enabling digital twin monitoring, operation validation, and workflow optimization for production lines, while reducing physical testing risks and costs.
banner 05
Learning from Demonstration
Enable manipulators or collaborative robot arms (Cobots) to learn intuitively from direct human motion demonstrations — dramatically simplifying programming complexity.

From Capture to Autonomous Execution: 4 Steps to Train Your Robot

Four core steps to train robots using j-mex AgileMaster:

num 1

Motion Data Capture

A human operator wearing the V100-R suit controls the robot in real time, capturing precise motion data.
num 2

Sensor Data Collection

The robot collects sensor data during teleoperation, enhancing its understanding of motion and the environment.
num 3

Policy Learning

Motion and sensor data are combined for deep learning, refining the robot’s movement patterns.
num 4

Autonomous Execution

The robot autonomously performs learned actions under various conditions, powered by its trained policy.

Core Hardware: MoCap Suit V100-R Plus

V100 R Plus Photo

High-Performance Motion Capture for Advanced Robotics

The V100-R Plus is a professional-grade motion capture suit specifically engineered for high-end robotic motion training and Vision-Language-Action (VLA) collaboration. Built on full-body IMU motion capture and human movement science, it transforms complex human dynamics into smooth, kinematics-based robot joint control.
  • Professional Precision: Features 15 nine-axis IMU sensors with integrated high-precision finger capture for detailed motion mapping.
  • Real-Time Performance: Delivers a 100 Hz data output rate, ensuring millisecond-level synchronization for teleoperation and imitation learning.
  • Industrial Stability: Designed with an advanced transponder architecture to provide stable, low-latency data streaming in demanding environments.
  • Seamless Integration: Native support for ROS2 (Humble and Jazzy), NVIDIA Isaac Sim, and URDF importing for rapid deployment across humanoid and cobot platforms.
View Full Product Details

Integrated with Global Robotics Leaders

j-mex AgileMaster is engineered to power next-generation Physical AI and robotic learning with high-precision motion data. We are proud to be officially featured on the Franka Robotics Partners page, validating our seamless compatibility and robust teleoperation capabilities for advanced collaborative robotic systems. 🔗 View Franka Robotics Official Partners Page ↗

FAQ

Traditional mocap systems output human skeletal data. j-mex AgileMaster includes our proprietary Motion Retargeting algorithm that directly outputs robot-ready joint signals (orientation and motion) via ROS2 protocol — no extra conversion tools required.

Out-of-the-box support for several mainstream Humanoid robots and Cobot Arms, with built-in skeleton topology switching. You can also import custom Robot URDFs.

Yes! j-mex is an NVIDIA Omniverse Ready Partner. j-mex Teleoperation Starter Kit can stream motion data directly to Isaac Sim/Lab — not only for control simulation, but also for integration with GR00T Mimic pipeline or VLA training flow.

Ready to Unlock the Potential of Humanoid Robots and Embodied AI?

Contact us today to experience the millisecond-level seamless conversion from human motion to robot execution firsthand, and accelerate your robotics and AI projects.
Name

Resources / Downloads & Documentation

Scroll to Top