Splat2Act: From Captured Scenes to Personalized VLA Manipula
Overview
Source roundup from published reports. Claims below are attributed to their publishers, not independently verified. arXiv Robotics — research abstracts: Splat2Act: From Captured Scenes to Personalized VLA Manipulation. Splat2Act is an automated real-to-sim-to-real pipeline that personalizes a pretrained vision-language-action (VLA) policy to a specific scene and object set using only a handheld phone scan and images of the user's objec…
Generated from attributed reports · Updated 1 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · navigable area: 104.87 other · Basis not reported
“atting and collision geometry, automatically discovers tabletop and non-tabletop receptacles, constructs feasible pickup tasks, and generates successful demonstrations with a privileged simulation oracle, with only scene and object capture required from a human. Applied to 101 scanned campus environments with a median navigable area of 104.87 m$^2$ and 7 receptacles, the pipeline yields 852 receptacles and over 68,00”
Exact source · revision 1Source owner not reported
Reported quantity · receptacles: 852 other · Basis not reported
“atting and collision geometry, automatically discovers tabletop and non-tabletop receptacles, constructs feasible pickup tasks, and generates successful demonstrations with a privileged simulation oracle, with only scene and object capture required from a human. Applied to 101 scanned campus environments with a median navigable area of 104.87 m$^2$ and 7 receptacles, the pipeline yields 852 receptacles and over 68,00”
Exact source · revision 1Source owner not reported
Reported quantity · tasks: 12 other · Basis not reported
“63.9% success on a 12-task subset, closely tracking its 66.7% simulated success on those tasks. These results suggest that automated real-to-sim-to-real training can personalize VLA manipulation policies using only simulation-oracle data.”
Exact source · revision 1Source owner not reported
Reported quantity · scenes: 101 other · Basis not reported
“atting and collision geometry, automatically discovers tabletop and non-tabletop receptacles, constructs feasible pickup tasks, and generates successful demonstrations with a privileged simulation oracle, with only scene and object capture required from a human. Applied to 101 scanned campus environments with a median navigable area of 104.87 m$^2$ and 7 receptacles, the pipeline yields 852 receptacles and over 68,00”
Exact source · revision 1Source owner not reported
Evidence dependency changes (1)
- 2026-10-13T07:18:44.523Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSplat2Act: From Captured Scenes to Personalized VLA Manipulation
Splat2Act is an automated real-to-sim-to-real pipeline that personalizes a pretrained vision-language-action (VLA) policy to a specific scene and object set using only a handheld phone scan and images of the user's objects. The method constructs photorealistic digital twins with 3D Gaussian Splatting and collision geometry, automatically discovers receptacles, and generates successful demonstrations. Applied to 101 campus environments, the pipeline yields 852 receptacles and over 68,000 pickup demonstrations. The strongest personalized policy achieves 62.5% aggregate pickup success in the target scene, with 63.9% success on a real robot.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).