This dataset stores authoritative timestamps and metadata in Parquet tables and stores frame payloads in video containers. Video presentation timestamps are not used for synchronization; use tables/frames.parquet and videoframeidx. - datasetmanifest.parquet: converted sessions in this dataset root - sessions/ /metadata/streams.parquet: stream IDs and modalities - sessions/ /metadata/videos.parquet: stream-to-video mapping - sessions/ /tables/frames.parquet: authoritative timestamps, frame indices, clock domains, and hashes - sessions/ /tables/robotstates.parquet: robot states, if present - sessions/ /metadata/calibration.json: calibration and transform conventions - sessions/…
Organization
Dynamic Autonomy and Intelligent Robotics Lab @ UPenn
DAIRLab
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers2
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.