A Scalable Action-Based Embodied Dataset for Real-World VLA Adaptation — the first high-fidelity retail robotics action dataset built from natural human behavior, not teleoperation.
Domain-specific robot deployment is fundamentally a data problem. High-fidelity naturalistic human behavior — systematically captured and retargeted — is a scalable foundation for robot adaptation. No robot in the loop required.
In-store capture demos
Research Paper
Paper (local copy)
SABER-10K on Hugging Face
RoboBenchMart evaluation
Need the full 44.8K corpus or custom capture?
Contact SalesArticulated object interaction, multi-height shelf reaching, basket loading, floor retrieval, and context-dependent placement — all repeated across hundreds of SKUs in layouts no lab can replicate.
Dense shelves, active restocking, occlusions, varied lighting, reflective packaging, and product deformability create real-world complexity that generic datasets cannot approximate.
A model must see skill families repeatedly across contexts — grasping bottles from different shelf heights, opening fridges from varied approach angles — to achieve reliable deployment.
Embodiment-agnostic motion tokens derived via inverse-dynamics encoding from egocentric video. Captures whole-arm motion, reach trajectories, and grasping dynamics without robot joint labels.
21-point hand landmarks estimated, human-corrected frame-by-frame, then retargeted to robot joint space via Dex-Retargeting. Provides explicit finger-level precision supervision.
SMPL body parameters estimated from the 360° ALIA view, human-corrected, and retargeted to the Unitree G1 humanoid. Provides torso-arm-leg coordination for floor retrieval and extended reach.
100+ hours across multiple real grocery stores with head-mounted GoPro + DreamVu ALIA 360°
LAPA encoding, hand pose estimation, and SMPL body estimation with human QC annotation
Dex-Retargeting to robot hand joint space + SMPL-to-Unitree G1 whole-body retargeting
Shared-backbone multi-task training on GR00T N1.6 with flow-matching objective
Pushing trolleys, packing goods, arranging goods, opening doors, inspecting labels, and handling baskets.
Placing and moving foods, scooping loose goods, inspecting deformable packets, carrying multiple goods, inspecting fruits, closing doors, and placing goods.
| Task | Category | Baseline (RBM FT) | SABER-MM | Change |
|---|---|---|---|---|
| fridge (avg open + close) | Fridge | 0.43 | 0.91 | +112% |
| board_to_board_duff | Board | 0.10 | 0.10 | — |
| board_to_board_nestle | Board | 0.02 | 0.02 | — |
| board_to_board_vanish | Board | 0.02 | 0.11 | +450% |
| pick_from_floor_beans | Floor | 0.04 | 0.17 | +325% |
| pick_from_floor_slam | Floor | 0.02 | 0.17 | +750% |
| pick_to_basket_fanta | Basket | 0.08 | 0.19 | +138% |
| pick_to_basket_nivea | Basket | 0.08 | 0.21 | +163% |
| pick_to_basket_stars | Basket | 0.12 | 0.14 | +17% |
| Mean (all tasks) | 0.134 | 0.293 | +119% |
SABER demonstrates that high-fidelity naturalistic human behavior, systematically captured and retargeted, is a viable and scalable foundation for domain-specific robot adaptation — without a robot in the loop.
LAPA tokens capture whole-arm trajectory, Dex-Retargeting provides finger-level precision, and body retargets supply torso-arm-leg coordination. Together they provide non-overlapping kinematic information.
The 4,800-sample robot-native anchor data proved necessary to stabilize early training even at SABER's scale, suggesting general manipulation signal matters for robust convergence.
SABER-MM teaches models to progress further through each task sequence — mean P≥2/3 of 0.445 vs 0.278 baseline — indicating reaching and grasping are well-learned while placement remains the frontier.
@article{dreamvu2026saber,
title = {SABER: A Scalable Action-Based Embodied Dataset
for Real-World VLA Adaptation},
author = {Menga, Narsimha and Sakurikar, Parikshit and Rouhi, Amirreza
and Reddy, Satya Sai and Govil, Anirudh and Chittajallu, Sri Harsha
and Aggarwal, Rajat and Namboodiri, Anoop and Reddi, Sashi},
year = {2026},
month = {May},
note = {DreamVu Inc.},
url = {https://dreamvu.ai/saber}
}