Data-Centric Robotics @ RSS 2026

Overview

Natural language processing and computer vision have recently undergone a paradigm shift toward data-driven intelligence, highlighted by the success of large language and vision models trained on massive internet-scale datasets. Robotics is at an analogous inflection point: progress in robot learning is increasingly bottlenecked not only by model architectures and compute, but by the availability, quality, diversity, and structure of robot data. Yet unlike the digital world, the physical world still lacks an “Internet for Robots”—a shared, scalable ecosystem of data, tooling, and evaluation that can reliably support general-purpose physical intelligence.

This workshop will bring together researchers and practitioners to examine a core question: What kinds of data matter most for training robots, and at what scale is data “enough”? We will focus on the end-to-end pipeline—data sources, collection paradigms, scaling laws, dataset composition, curation and weighting, evaluation protocols, and post-deployment data flywheels—highlighting both complementary perspectives and unresolved tensions. The workshop is designed to be highly discussion-driven, using short talks and panels to identify practical bottlenecks and propose actionable research directions.

Call for Papers

Topics of Interest

We welcome submissions related to the following themes:

Data Sources and Philosophies: Web data (semantic knowledge) vs. Simulation data (scalable) vs. Real-world interaction data (grounding). Combining diverse data sources in unified pipelines.
Scalability vs. Quality in Data Collection: Balancing high-fidelity teleoperation with scalable alternatives like human videos or low-cost wearable devices. Weighting data sources during training.
Closing the Loop - Learning After Deployment: Leveraging experiential data, reinforcement learning, and online adaptation to correct failures and build robust data flywheels post-deployment.
Data Evaluation, Analysis, and Interpretability: Defining and measuring data quality. Systematic selection, filtering, and weighting of data. Benchmarks for data curation and understanding data influence on model behavior.

Submission Guidelines

All papers must be submitted through our OpenReview portal (Link TBD).
Submissions must strictly adhere to the RSS 2026 Author Guidelines in terms of potential ethics issues and potential risks of negative social impacts.
To facilitate double-blind review, all manuscripts must be fully anonymized.
All accepted papers are expected to be presented in person at the workshop.
Exceptional submissions will be considered for Best Paper Award and Spotlight Presentations.

Submission Track 1: Proceedings Track

Submissions to the Proceedings Track must present original, unpublished research. Manuscripts should typically be 4-8 pages (format TBD) using the RSS 2026 submission template. Accepted papers in this track may be formally published in the Workshop Proceedings (subject to confirmation).

Submission Portal: TBD

TBD

Submission Deadline

TBD

Notification to Authors

TBD

Camera-ready Deadline

Submission Track 2: Non-Proceedings Track

The Non-Proceedings Track offers a flexible, non-archival venue for sharing a broad range of contributions. This track allows authors to present and promote their work without restrictive publishing constraints.

We warmly welcome: