real-robot data collection

To address the challenges of large-scale, slow-loading, and hard-to-generalize multimodal robotic trajectory data (video, text, numerical), this paper proposes a cloud-native trajectory data management framework. We design EBML—a self-contained binary format supporting hybrid lossy/lossless compression—achieving up to 70× compression over RLDS without sacrificing downstream task accuracy. We introduce a novel memory-mapped decoding cache coupled with load-balanced, multi-stream parallel video decoding, accelerating decoding by 50× versus LeRobot. The full system maintains model performance even under 75× aggressive compression. This work establishes an efficient, scalable data infrastructure for training large-scale Transformer models across diverse robots and tasks.

This work addresses critical bottlenecks in humanoid robotics—namely data silos, high acquisition costs, and inconsistent evaluation—stemming from the absence of a unified physical interaction data infrastructure, which hinders the scalable advancement of Physical AI. The study introduces the concept of “embodied interaction data” to characterize humanoid robot data and proposes a hierarchical architecture that integrates general standards with capability-specific ones. It emphasizes preserving the complete relational structure among robot embodiment, actions, tasks, environments, and outcomes, while ensuring physical consistency across multimodal data in terms of temporal alignment, coordinate frames, and calibration. Building upon the ISO/WD 26264-1 draft, the authors establish a horizontal data infrastructure encompassing metadata, provenance, quality control, and versioning, alongside domain-specific semantic specifications for manipulation, locomotion, and human–robot interaction. This framework provides an interpretable, shareable, and reusable data foundation to enable cross-platform, cross-task, and cross-institutional co-evolution in Physical AI.

This work addresses two core challenges in large-scale robotic manipulation datasets: (1) designing high-value diversity dimensions to enhance data utility, and (2) efficiently retrieving task-aligned demonstrations from existing datasets. To this end, we introduce a programmable data generation framework that explicitly models controllable diversity variables—including camera pose, object categories, and spatial layout. Our analysis reveals, for the first time, that camera pose and spatial arrangement are critical determinants of both dataset diversity and task alignment. We further propose a task-oriented demonstration retrieval algorithm grounded in geometric-semantic joint alignment. Evaluated on real-world datasets including DROID, our method improves downstream policy performance by up to 70%. Crucially, insights and gains observed in simulation generalize successfully to physical robot platforms, demonstrating robust cross-domain transferability.

This study addresses the persistent gap between theoretical control performance and its practical realization in real-world robotic systems, often caused by inadequate discretization, insufficient real-time guarantees, and weak error handling in control software. For the first time from a software engineering perspective, the authors systematically analyze 184 open-source robotic controllers through code review, empirical analysis, and test evaluation, uncovering common deficiencies in application scenarios, implementation details, and verification practices. The findings reveal that most implementations fail to properly account for critical system constraints, and their testing strategies inadequately validate the theoretical assurances they claim. This work highlights a significant disconnect between implementation quality and theoretical promises, offering concrete directions and practical guidelines for developing reliable, verifiable robotic control software.

Converting ROS bags into machine learning datasets often relies on ad hoc scripts, resulting in substantial engineering overhead and inefficient iteration. This work introduces, for the first time, the principles of software build systems to robotic dataset construction, proposing a reproducible, incremental generation method grounded in artifact- and dependency-graph semantics. We present Bagzel, an open-source tool built on Bazel, which supports export to the nuScenes format and incorporates Bagzel-xattr for server-side metadata management. Experimental evaluation demonstrates that, on a 20.4 GB dataset, hot builds achieve up to a 386.26× speedup and incremental builds are accelerated by 7.21×, with performance gains further amplified as dataset scale increases.

This work addresses the limited reproducibility of behavioral validation in robotic simulation testing, which often stems from insufficiently documented test configurations, execution protocols, and post-processing procedures. To overcome this, the study proposes a deep integration of data provenance and FAIR (Findable, Accessible, Interoperable, Reusable) principles throughout the entire test generation pipeline—rather than merely appending them to final datasets. The authors extend an existing simulation testing framework by embedding machine-readable, structured metadata at every stage, thereby enabling end-to-end traceable validation workflows. This approach significantly enhances the reproducibility of mobile robot navigation datasets. Additionally, the project distills practical FAIR implementation guidelines tailored to robotics, identifying key challenges such as vocabulary alignment, attribute selection, and adoption of community standards, and offers actionable recommendations for addressing them.

This work addresses the lack of scalable, trustworthy evaluation methods and physically plausible training data for general-purpose robotic policies, compounded by the high cost and poor reproducibility of real-world robot experiments. To overcome these challenges, the authors propose a human↔simulation↔robot bidirectional alignment framework supported by a cloud-native toolchain. Leveraging the JoySim simulator—integrated with reconstruction, rendering, and realism-enhancement modules—they implement a high-fidelity digital twin on the JD Cloud platform. Human demonstrations are transformed into physically consistent trajectories, annotations, and visual observations, while simulation serves dual roles as a scalable evaluation layer and a data filter. This approach substantially improves both the efficiency of data generation and the reliability of policy evaluation.

To address scalability and collaborative efficiency bottlenecks in storing, indexing, and sharing large-scale unstructured robot data (e.g., ROS bags, MCAP), this paper proposes a modular local-cloud architecture. The architecture integrates S3-compatible object storage, Dockerized processing pipelines, and dual-mode Web/CLI interfaces, introducing the novel “Action Runner” mechanism to automate end-to-end workflows—including data validation, format standardization, metadata indexing, and benchmarking. It enables unified management of heterogeneous robot data formats and has been deployed to reliably host over 30 TB of real-world research data. Empirical evaluation demonstrates significant improvements in data discoverability, reuse rate, and cross-team collaboration. The system establishes a reproducible, scalable infrastructure paradigm for data-intensive robotics research.

Robotics faces a severe reproducibility crisis: approximately 70% of algorithms cannot be independently reproduced, primarily due to dependency conflicts and environment setup complexity arising from multilingual, fragmented toolchains. To address this, we propose a unified, cross-platform package management framework tailored for robotics and AI. Our approach introduces three core innovations: (1) a project-level lockfile mechanism ensuring bit-for-bit cross-platform reproducibility; (2) unified dependency resolution across conda-forge and PyPI ecosystems via a single entry point; and (3) integration of a high-performance SAT solver, accelerating dependency resolution by 10×. Deployed across over 5,300 open-source projects, the framework reduces environment configuration time from hours to minutes. It significantly lowers the barrier to experimental reproducibility and provides foundational infrastructure for collaborative, reproducible research in robotics and AI.