X Square Robot announces the open-source release of XRZero-G0, a hardware-software co-designed framework for robot-free data collection, trainable policy generation, and real-robot evaluation. Alongside it, the team releases G0-Dataset, a large-scale validated multimodal dataset produced by XRZero-G0, providing reproducible high-quality robot-free data for the global robotics community.<\/p>\n
Bridging robot-free and real-world perception<\/b><\/p>\n
Physical robots perceive the world through multiple viewpoints, typically a head-mounted camera for global context and wrist-mounted cameras for fine-grained manipulation. In contrast, most robot-free systems rely only on wrist-view observations from human demonstrators, creating a gap between training and deployment.<\/p>\n
XRZero-G0 addresses this gap with a multi-view aligned sensing system that aligns human demonstration with robot observation spaces.<\/p>\n The system combines a head-mounted camera and dual wrist cameras to capture both global context and detailed hand-object interactions. These synchronized observations are mapped into a shared representation compatible with robot perception.<\/p>\n A wearable VR interface and interchangeable grippers allow human operators to generate demonstrations that are directly transferable to different robot embodiments, enabling high-throughput robot-free data collection across diverse environments.<\/p>\n Making robot-free demonstrations truly trainable<\/b><\/p>\n Data quality has been a critical barrier in robot-free learning. XRZero-G0 formalizes trainability governance via a closed-loop Collection\u2013Inspection\u2013Training\u2013Evaluation pipeline:<\/p>\n This pipeline improves the usability of robot-free demonstrations, with experiments showing an effective data yield of around 85% under controlled experimental settings, significantly increasing the proportion of trainable samples.<\/p>\n A 10:1 mixing law reduces real-robot data requirements<\/b><\/p>\n A key finding of the XRZero-G0 study is that robot-free data and real-robot data can complement each other effectively.<\/p>\n Controlled experiments show that combining approximately 10 robot-free episodes with 1 real-robot episode achieves performance comparable to purely real-robot datasets in evaluated tasks.<\/p>\n Robot-free data provides broad behavioral coverage and task understanding, while a small amount of real-robot data anchors embodiment-specific factors such as motor latency and friction. This strategy reduces the need for real-robot data by up to 20\u00d7 under experimental conditions.<\/p>\n G0-Dataset scales XRZero-G0 into a 2,000-hour dataset<\/b><\/p>\n Built on XRZero-G0, G0-Dataset provides over 2,000 hours of validated multimodal demonstrations spanning vision, tactile, and audio modalities.<\/p>\n The dataset integrates robot-free collection, automated quality inspection, mixed-data training, and real-robot evaluation for research purposes. G0-Dataset supports large-scale pretraining and cross-embodiment transfer experiments, providing a reproducible open resource for robotics research.<\/p>\n Zero-shot transfer across robot embodiments<\/b><\/p>\n Experiments indicate that policies trained with XRZero-G0 exhibit improved generalization across collection environments, including varying robot poses, table heights, and viewpoints.<\/p>\n They also demonstrate zero-shot cross-embodiment transfer ability in evaluated settings, where policies trained with mixed data can be transferred to unseen robot platforms without task-specific fine-tuning.<\/p>\n Building an open ecosystem<\/b><\/p>\n By open-sourcing XRZero-G0 and releasing G0-Dataset, X Square Robot provides hardware designs, automated inspection pipelines, training methodologies, and high-quality datasets to the research community.<\/p>\n These resources aim to accelerate the development of general-purpose robots and scalable embodied AI, supporting a transition toward more systematic and large-scale data generation approaches.<\/p>\n XRZero-G0 and G0-Dataset are now publicly available for researchers and developers worldwide.<\/p>\n Project Homepage: https:\/\/x2robot.com\/x2go<\/a> Media Inquiries: contact@x2robot.com<\/a><\/p>\n <\/p>\n XRZero-G0: A framework for high-quality robot-free data collection and embodied AI training<\/i><\/p>\n SHENZHEN, China<\/span>, June 10, 2026<\/span> \/PRNewswire\/ — Scaling embodied AI has long been bottlenecked by data.\u00a0Teleoperating real robots is expensive and slow, yielding only a limited number of demonstrations per day. While robot-free data collection offers a promising alternative, the lack of systematic quality control and training integration has limited its effectiveness for policy learning.<\/p>\n X Square Robot announces the open-source release of XRZero-G0, a hardware-software co-designed framework for robot-free data collection, trainable policy generation, and real-robot evaluation. Alongside it, the team releases G0-Dataset, a large-scale validated multimodal dataset produced by XRZero-G0, providing reproducible high-quality robot-free data for the global robotics community.<\/p>\n Bridging robot-free and real-world perception<\/b><\/p>\n Physical robots perceive the world through multiple viewpoints, typically a head-mounted camera for global context and wrist-mounted cameras for fine-grained manipulation. In contrast, most robot-free systems rely only on wrist-view observations from human demonstrators, creating a gap between training and deployment.<\/p>\n XRZero-G0 addresses this gap with a multi-view aligned sensing system that aligns human demonstration with robot observation spaces.<\/p>\n The system combines a head-mounted camera and dual wrist cameras to capture both global context and detailed hand-object interactions. These synchronized observations are mapped into a shared representation compatible with robot perception.<\/p>\n A wearable VR interface and interchangeable grippers allow human operators to generate demonstrations that are directly transferable to different robot embodiments, enabling high-throughput robot-free data collection across diverse environments.<\/p>\n Making robot-free demonstrations truly trainable<\/b><\/p>\n Data quality has been a critical barrier in robot-free learning. XRZero-G0 formalizes trainability governance via a closed-loop Collection\u2013Inspection\u2013Training\u2013Evaluation pipeline:<\/p>\n This pipeline improves the usability of robot-free demonstrations, with experiments showing an effective data yield of around 85% under controlled experimental settings, significantly increasing the proportion of trainable samples.<\/p>\n A 10:1 mixing law reduces real-robot data requirements<\/b><\/p>\n A key finding of the XRZero-G0 study is that robot-free data and real-robot data can complement each other effectively.<\/p>\n Controlled experiments show that combining approximately 10 robot-free episodes with 1 real-robot episode achieves performance comparable to purely real-robot datasets in evaluated tasks.<\/p>\n Robot-free data provides broad behavioral coverage and task understanding, while a small amount of real-robot data anchors embodiment-specific factors such as motor latency and friction. This strategy reduces the need for real-robot data by up to 20\u00d7 under experimental conditions.<\/p>\n G0-Dataset scales XRZero-G0 into a 2,000-hour dataset<\/b><\/p>\n Built on XRZero-G0, G0-Dataset provides over 2,000 hours of validated multimodal demonstrations spanning vision, tactile, and audio modalities.<\/p>\n The dataset integrates robot-free collection, automated quality inspection, mixed-data training, and real-robot evaluation for research purposes. G0-Dataset supports large-scale pretraining and cross-embodiment transfer experiments, providing a reproducible open resource for robotics research.<\/p>\n Zero-shot transfer across robot embodiments<\/b><\/p>\n Experiments indicate that policies trained with XRZero-G0 exhibit improved generalization across collection environments, including varying robot poses, table heights, and viewpoints.<\/p>\n They also demonstrate zero-shot cross-embodiment transfer ability in evaluated settings, where policies trained with mixed data can be transferred to unseen robot platforms without task-specific fine-tuning.<\/p>\n Building an open ecosystem<\/b><\/p>\n By open-sourcing XRZero-G0 and releasing G0-Dataset, X Square Robot provides hardware designs, automated inspection pipelines, training methodologies, and high-quality datasets to the research community.<\/p>\n These resources aim to accelerate the development of general-purpose robots and scalable embodied AI, supporting a transition toward more systematic and large-scale data generation approaches.<\/p>\n XRZero-G0 and G0-Dataset are now publicly available for researchers and developers worldwide.<\/p>\n Project Homepage: https:\/\/x2robot.com\/x2go<\/a>![\"\"](\"https:\/\/mma.prnasia.com\/media2\/2996511\/image1.jpg?p=medium600\" "\\"\\"")
<\/a>
<\/span><\/p>\n<\/div>\n\n
Paper: https:\/\/arxiv.org\/abs\/2604.13001<\/a>
Code: https:\/\/github.com\/X-Square-Robot\/XRZero-G0<\/a>
Open Dataset: https:\/\/huggingface.co\/datasets\/x-square-robot\/XRZero-G0-3K<\/a>\u00a0<\/p>\n<\/a>
<\/span><\/p>\n<\/div>\n\n
Paper: https:\/\/arxiv.org\/abs\/2604.13001<\/a>
Code: https:\/\/github.com\/X-Square-Robot\/XRZero-G0<\/a>
Open Dataset: https:\/\/huggingface.co\/datasets\/x-square-robot\/XRZero-G0-3K<\/a>\u00a0<\/p>\n