🗾ITmedia AI+ (日本)•Stalecollected in 83m
TGR-D Partners RICOS for AI Racing Aerodynamics
💡AI cuts racing aero sim time—tool for ML engineers in sim-heavy fields
⚡ 30-Second TL;DR
What Changed
RICOS and TGR-D signed entrustment contract for ML-based aero analysis
Why It Matters
This accelerates AI integration in high-stakes engineering like motorsports, potentially cutting simulation times from days to minutes for broader automotive applications.
What To Do Next
Trial RICOS AI-CAE demos for speeding up your CFD or FEA simulations.
Who should care:Researchers & Academics
Key Points
- •RICOS and TGR-D signed entrustment contract for ML-based aero analysis
- •AI-CAE enables fast prediction of CAE results for racing cars
- •Focuses on improving motorsports aerodynamic performance
- •Proprietary RICOS technology applied to real-world racing development
🧠 Deep Insight
AI-generated analysis for this event.
🔑 Enhanced Key Takeaways
- •RICOS's AI-CAE technology specifically utilizes deep learning to replace traditional iterative fluid dynamics simulations, reducing analysis time from hours to seconds.
- •The partnership leverages Toyota's massive historical dataset of wind tunnel and CFD (Computational Fluid Dynamics) results to train RICOS's proprietary models for higher accuracy in racing-specific conditions.
- •This collaboration is part of a broader TGR-D initiative to integrate 'Digital Twin' technology into their vehicle development cycle to accelerate the iteration speed of aerodynamic components.
📊 Competitor Analysis▸ Show
| Feature | RICOS (AI-CAE) | Altair (ultraFluidX) | Ansys (Discovery) |
|---|---|---|---|
| Core Tech | ML-based surrogate modeling | GPU-accelerated CFD | Real-time simulation/AI |
| Primary Focus | Speed/Prediction | High-fidelity CFD | General engineering |
| Racing Suitability | High (Rapid iteration) | High (Validation) | Medium (Design phase) |
🛠️ Technical Deep Dive
- •RICOS employs a proprietary Graph Neural Network (GNN) architecture capable of handling unstructured mesh data common in automotive CAE.
- •The system utilizes a 'Surrogate Modeling' approach where the AI learns the mapping between geometric parameters and aerodynamic coefficients (Cd, Cl) without solving Navier-Stokes equations in real-time.
- •Integration involves a pre-processing pipeline that converts CAD geometry into a latent space representation, allowing the model to predict pressure distribution maps across the vehicle surface.
🔮 Future ImplicationsAI analysis grounded in cited sources
TGR-D will reduce aerodynamic development cycles by over 50% within two years.
The shift from traditional CFD to AI-based prediction allows engineers to test hundreds of design variations per day rather than a handful.
RICOS will expand its AI-CAE platform to include structural and thermal analysis modules.
The success of the aerodynamics pilot provides a validated framework for applying the same surrogate modeling techniques to other physics domains.
⏳ Timeline
2018-11
RICOS founded in Tokyo, Japan, focusing on AI-driven engineering solutions.
2023-04
RICOS secures significant Series A funding to scale its AI-CAE platform for industrial manufacturing.
2025-09
RICOS announces strategic expansion of its AI-CAE cloud platform for automotive sector clients.
2026-04
Official announcement of the partnership between RICOS and Toyota Gazoo Racing Development.
📰
Weekly AI Recap
Read this week's curated digest of top AI events →
👉Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: ITmedia AI+ (日本) ↗