ブログ

Reality AI Tools^® includes functionality to monitor the status of data collection automatically, tracking consistency, quality, and coverage.

ルネサスエレクトロニクスは、約10年にわたり、数々の機能安全ワーキンググループのアクティブメンバーとして関連する規格に大きく貢献してきました。現在、機械学習やAI、高性能コンピューティングハードウェアの進化により、高効率な安全ソリューション構築が推し進められています。これを受けて、エンジニアが機能安全システムを設計する際には、システム障害の防止であれ、将来リスクの予測と軽減であれ、さまざまな人工知能モデルの統合も必要となってきているのです。

RealityCheck ADは、Realty AIのAIソフトウェアを実行するエッジノード、1つ以上のセンサー、さらに機器のモニタリングやより高度なモデルの開発を行うためのクラウド上のエンジニアリングワークステーションで構成されています。

Software is becoming the new sensor. This shift in thinking opens the door to incorporating more complex, AI-based algorithms, rather than just simple condition thresholds.

In this blog we demonstrate Edge AI solutions for the kinds of real engineering problems that our customers use Reality AI software for every day, running on real hardware they might actually deploy.

While building machine learning models on sensor and signal data, many customers hit a point where they're not getting the desired result. Here's a process we go through to find the best path forward.

To get your machine learning model to the point where it’s ready for field testing, you’ll want to collect several thousand observations that cover a broad a range of the variation expected.

As sensor and MCU costs decreased, an ever-increasing number of organizations have attempted to exploit this by adding sensor-driven embedded AI to their products.

The more sophisticated machine learning tools that are optimized for signal problems and embedded deployment can cut months, or even years, from an R&D cycle.

A project is something created by an individual/small team in a lab and works in a limited range of conditions; a product works everywhere and in all kinds of unpredictable conditions.