# AI x Robotics: Data, Infrastructure & Evaluation

> Three talks on robot data pipelines, storage for production RAG, and simulation-based evaluation of robot policies, in English in Hongo.

This event has ended.

- When: Wed, November 4, 2026 18:00–21:00 JST
- Where: Bunkyo City, Japan · In person
- Region: Kanto (Tokyo)
- Organizer: Tokyo AI
- Language: EN
- Source: Luma — https://lu.ma/eup5p5n0
- Page: https://japantech.info/events/luma-eup5p5n0/

## Summary

An English-language Tokyo AI evening on the infrastructure that lets physical AI scale: moving robot data from fleets into training, building persistent data platforms for production AI, and evaluating learned robot policies before spending scarce time on real hardware. It is aimed at robotics and ML engineers, researchers, data infrastructure practitioners and technical founders.

Petr Khrapchenkov (AIRoA) covers the production pipeline that processes thousands of hours of robot data each month, from ingress through storage to query. Hiroshi Hashimoto (Wasabi Technologies Japan) discusses the storage foundations of production RAG, with an MCP demo. Ryo Watanabe (Muso Action) shows how physics simulation with Isaac Lab Arena, Real2Sim scenes and cloud GPUs are used to evaluate imitation-learning policies. Each 30-minute slot includes Q&A, followed by an hour of networking at KERNEL HONGO in Bunkyo.

## About the community

A not-for-profit AI community connecting engineers, researchers, investors, product managers and corporate innovation leaders building AI in Japan. It runs regular English-language technical talks, research evenings and networking events, and links the local AI ecosystem with the global one.

#robotics #physical-ai #data-infrastructure #rag #simulation #imitation-learning #mlops #data-pipelines #mcp #robot-learning