Rerun

Rerun is a robotics and physical-AI data platform used for ingesting, visualising, and analysing data from robot experiments and production workloads.

Key facts

  • Type: Robotics data and visualisation platform
  • Role in source: Presented as infrastructure for understanding what robots perceive and do during experiments [src-076]
  • Use case: Collecting, sorting, replaying, and analysing sensor, perception, and robot-run data [src-076]
  • Associated theme: Physical AI requires a data loop, not only robot hardware or model code [src-076]

What it does

The source positions Rerun as part of the tooling layer needed when robotics projects become data-rich. Cameras, sensors, logs, and model outputs need to be inspected and replayed so builders can understand failures, train better models, and make robot behaviour debuggable [src-076].

Related concepts

Source references

  • [src-076] Back to Engineering (iulia) – physical AI, robotics, and data science cluster (41 videos, 2018-12-16 to 2026-05-10)

Robin Cartier perspective

This page is part of Robin Cartier's working AI knowledge graph: a practical research layer for production AI, recommendation systems, experimentation, GEO, and agentic web readiness.

The useful next step is to connect this concept back to applied product leadership and operating models.

Recommended next

Keep reading from this thread

From 491 indexed pages and articles.

  1. Wiki concept Robotics Data Loop The robotics data loop is the cycle of collecting sensor and robot-run data, replaying and analysing it, learning from failures, improving models or Related by rerun
  2. Wiki concept ROS The Robot Operating System, is the standard robotics middleware layer used to move from isolated hardware projects toward modular robot systems. Related by 076
  3. Insight Recommendation Systems in Production How recommendation systems become production decisioning systems through signals, ranking, constraints, feedback loops, and experimentation Readers have engaged with this next