# What is Edge Inference?

Running a machine learning model on the vehicle or local gateway instead of sending raw data to the cloud.

## In real work

Edge inference flags drowsiness locally. Latency target is under 50 ms with no round trip to the cloud.

## Related terms

- [ADAS](https://prompthausapp.com/learn/adas.md)
- [Sensor Fusion](https://prompthausapp.com/learn/sensor-fusion.md)
- [Perception Stack](https://prompthausapp.com/learn/perception-stack.md)
- [Domain Controller](https://prompthausapp.com/learn/domain-controller.md)
- [Driving Automation Level](https://prompthausapp.com/learn/driving-automation-level.md)

## How is this different from Googling it?

Google gives a definition. Prompthaus pairs each term with how it shows up in standups, PRs, prompts, and design reviews—then quizzes you until the word sticks. One term a day on iPhone.

- Category: Automotive
- HTML: https://prompthausapp.com/learn/edge-inference
- App Store: https://apps.apple.com/us/app/prompthaus-ai-vocabulary/id6776314407