QUANXTA Zero is an integrated hardware-software system by X Square Robot (自变量机器人) for industrial-scale data collection for embodied artificial intelligence, introduced in 2026. It addresses three major challenges: limited training data, inefficient data collection and inconsistent data quality.
The system is embodiment-free — demonstrations are recorded by a human using a wearable rig, without a robot, which the company says reduces data-collection cost by about 60%. Available variants are: Zero-G0 (VR headset + backpack + dual grippers, whole-body mobile manipulation), Zero-G1 (headband + dual grippers; capturing vision, touch and audio) and Zero-E0 (lightweight headband, first-person context capture with six cameras).
The rig uses Universal Manipulation Interface (UMI) grippers, captures multimodal data (vision, touch, audio) and provides 1 ms synchronization and 100% frame-level alignment. It supports movement, dual-arm manipulation, lifting and whole-body behaviors.
Embodied data-collection rig · serves as: Sensing, Sensor Data Ingestion, Teleoperation Support, Device Synchronization, Perception.
Which group QUANXTA Zero belongs to and how it is built
A subcategory covering portable or wearable platforms for industrial-scale collection of multimodal demonstration data (vision, touch, audio, action trajectories), often “embodiment-free”, used to train robot policies without the robot itself.
A component type: a complete hardware rig for embodied data collection — combining cameras (first-person view), tactile and audio sensors and UMI-standard grippers, with frame-level synchronization. Enables fast, low-cost collection of human demonstrations without a robot.
What QUANXTA Zero can detect and measure in its environment
