What are the features of this technology?

The technology is characterized by its ability to lightweight search vector databases through re-learning of embedded models, maintaining search accuracy even in in-vehicle SoC environments.

What applications are envisioned?

Applications include dialogue assistants for setting destinations, information search, and vehicle function control, among other in-vehicle HMI functions.

What are the evaluation results of this technology?

Evaluation using public datasets confirmed that it reduces memory capacity by 30-60% while maintaining high accuracy compared to existing models.

What are the future plans?

We plan to collaborate with automakers and partner companies to contribute to the development of mobility society.

What is the background of this technology's development?

To address the challenge of generative AI alone not being able to handle the latest information or vehicle/user-specific information, we aimed to implement RAG technology on in-vehicle edge devices.

Developing Generative AI Technology for Low-Memory RAG Execution on In-Vehicle Edge Devices

Key facts

Developing Generative AI Technology for Low-Memory RAG Execution on In-Vehicle Edge Devices
Denso Ten has developed generative AI technology that enables low-memory RAG execution on in-vehicle edge devices, aiming to provide a natural and reassuring dialogue experience tailored to drivers and passengers.
Source: PR TIMES
Date: Tue Jun 16 2026 23:00:01 GMT+0900 (Japan Standard Time)

Direct answer

Denso Ten has developed generative AI technology that enables low-memory RAG execution on in-vehicle edge devices, aiming to provide a natural and reassuring dialogue experience tailored to drivers and passengers.

Citation: Developing Generative AI Technology for Low-Memory RAG Execution on In-Vehicle Edge Devices (Tue Jun 16 2026 23:00:01 GMT+0900 (Japan Standard Time)), PR TIMES
Source: PR TIMES
Date: Tue Jun 16 2026 23:00:01 GMT+0900 (Japan Standard Time)

AI Summary (NQ-processed)

Denso Ten has developed generative AI technology that enables low-memory RAG execution on in-vehicle edge devices, aiming to provide a natural and reassuring dialogue experience tailored to drivers and passengers.

AI Analysis

Frequently Asked Questions

Q: What are the features of this technology?: A: The technology is characterized by its ability to lightweight search vector databases through re-learning of embedded models, maintaining search accuracy even in in-vehicle SoC environments.
Q: What applications are envisioned?: A: Applications include dialogue assistants for setting destinations, information search, and vehicle function control, among other in-vehicle HMI functions.
Q: What are the evaluation results of this technology?: A: Evaluation using public datasets confirmed that it reduces memory capacity by 30-60% while maintaining high accuracy compared to existing models.
Q: What are the future plans?: A: We plan to collaborate with automakers and partner companies to contribute to the development of mobility society.
Q: What is the background of this technology's development?: A: To address the challenge of generative AI alone not being able to handle the latest information or vehicle/user-specific information, we aimed to implement RAG technology on in-vehicle edge devices.