<name>Rerun</name> <description>Rerun provides a physical data platform for robotics AI, offering unified ingestion, storage, visualization, and query of multi-format robot logs. Its open‑source SDK enables developers
Funding
$3.2M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
CVFounders
Product
Problem
Debugging and analyzing data from spatial and embodied AI systems, such as robotics and computer vision applications, is challenging due to the complexity and multimodality of the data. Existing tools often lack the flexibility and real-time capabilities needed to effectively visualize and understand these complex datasets.
Solution
Rerun provides an open-source visualization infrastructure designed specifically for spatial and embodied AI data. The platform offers a flexible SDK for logging multimodal data, coupled with a powerful viewer for both real-time and recorded data analysis. Rerun simplifies the process of understanding complex systems by providing tools to model data, visualize it interactively, and query it efficiently. The viewer can be embedded in other applications and supports various languages, enabling users to build custom visualization tools.
Target Audience
The primary users are researchers and engineers working in spatial and embodied AI, including robotics, computer vision, and related fields, who need tools for visualizing and debugging complex datasets.
Features
- SDKs for C++, Python, and Rust for logging data from various sources
- Native and web-based viewer for interactive visualization of multimodal data
- Time-aware Entity Component System for modeling complex data relationships
- Query APIs for extracting time-aligned datasets
- Support for geospatial data visualization with GeoPoints and GeoLineStrings archetypes
- H.264 support for video visualization
- Ability to view and query Rerun data as dataframes
- Column-oriented API for handling large time-series datasets