arXiv:2609.23910v1 Announce Type: cross Abstract: Simulation-based evaluation provides a scalable and repeatable alternative to real-world evaluation of vision-language-action (VLA) policies. However...
arXiv:2606. 04708v1 Announce Type: cross Abstract: Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging.
PIVOT is a new multi‑trajectory dataset and evaluation framework that captures real‑world scenes with diverse camera paths, preserving both sensor‑derived measured poses and COLMAP‑optimized poses along with calibrated and optimized intrinsics. It defines three benchmark families—seen vs. unseen trajectory generalization, measured vs. optimized pose sensitivity, and calibrated vs. optimized intrinsics sensitivity—and introduces a directed pose‑space Chamfer distance to assess pose coverage. The first version of PIVOT includes five scenes recorded with a DJI Mini 4 Pro and offers an open processing and Nerfstudio‑based evaluation toolchain, revealing a consistent quality gap between held‑out and unseen trajectories and significant sensitivity to pose source and camera intrinsics.
RoboPhys-3D is a 3D‑grounded embodied world model benchmark built on RoboTwin 2.0, featuring 50 manipulation tasks, 5,000 episodes, and 25,000 multi‑view ground‑truth videos. It evaluates video world models by processing both generated and ground‑truth videos through the same 3D reconstruction pipeline, allowing the separation of reconstruction‑induced from generation‑induced errors. The benchmark defines 50 metrics across four sub‑dimensions—pixel fidelity, 3D geometry consistency, state understanding, and task completeness—and introduces the Average Full Score and RoboPhyscore for holistic assessment, with RoboPhyscore showing strong correlation with human judgments.
Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI data to train large-scale Vision-Language-Action (VLA) models remains fundamentally challenging. We identify two critical mismatches: wrist-mounted fisheye views, with severe radial distortion and local gripper-centric perspectives, are out-of-distribution for pretrained VLMs; and human-collected trajectories frequently violate kinematic limits, incur collisions, or exceed controller bandwidth, teaching VLA policies physically infeasible actions.
The paper introduces 3DROID, a dataset of renderable 3D Gaussian scenes that are anchored to a robot’s metric workspace and include per-scene reliability metrics. It examines how the reliability of camera extrinsics and pose conditioning affect the fidelity of 3D Gaussian representations, proposing a calibration-aware pipeline that improves novel-view rendering when extrinsics are trustworthy. The resulting dataset, available on Hugging Face, provides robot manipulation researchers with metric-scale, pose-anchored 3D data and reliability annotations.
WARP-VLA is a Vision‑Language‑Action model designed to be robust to variations in wrist‑camera viewpoints. It uses a Mixture‑of‑Experts architecture where each expert learns a view‑specific feature transformation, and a router selects the appropriate expert based on implicit view cues, eliminating the need for explicit camera extrinsic parameters. Experiments on the LIBERO benchmark show that WARP‑VLA doubles the success rate of pi‑0.5 from 39.2% to 78.3% under wrist‑view perturbations, and real‑robot tests confirm that the simulation‑learned adaptation transfers to diverse deployment settings.
arXiv:2610.10479v1 Announce Type: cross Abstract: A simulation of a real robot workspace must preserve task-relevant interactions, while policies developed in it must operate on observations availabl...
arXiv:2607. 05396v1 Announce Type: cross Abstract: Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on actual scenarios.
arXiv:2607. 19190v1 Announce Type: cross Abstract: Real-to-sim conversion for robotic interaction with objects remains labor-intensive because it requires more than visual reconstruction: a streamlined real2sim process must recover scene geometries and object states, infer physical parameters, and assemble actors, objects, cameras, poses, and trajectories into a runnable physical simulation.
arXiv:2608.21402v1 Announce Type: cross Abstract: World action models (WAMs) jointly denoise future video frames and robot actions, and the video prior is expected to generalize their control. Camera...
InfiNoVA is a data‑augmentation framework that transforms synchronized multi‑camera demonstrations into a dense, geometrically consistent set of training views by reconstructing each manipulation trajectory as a time‑varying 3D Gaussian. The method renders novel observations from sampled camera poses while preserving the original state‑action pairs, improving frame‑level fidelity and temporal consistency compared to generative synthesis. Across four real‑world manipulation tasks, policies trained with InfiNoVA achieve 5.4× higher average success under unseen randomized viewpoints than VISTA‑based augmentation and 1.7× higher success than training on all five physical camera views.