Loading post…
GoogleDavid Mclaughlin, Ajeet MirwaniExplainer
Bridging the Domain Gap: AI Race Coach built with Antigravity and Gemini
Summary
At Sonoma Raceway, Google Developer Experts built an AI-powered race coach to turn vehicle telemetry into split-second driving advice, extending an earlier pilot that handled basic telemetry. The system uses Antigravity for stateful orchestration and ingestion, Python and Jetpack Compose for mobile processing and display, Agent Development Kit for agent coordination, and hybrid Gemma 4 edge reasoning plus Gemini API cloud analysis. A custom USB interface connected a Pixel 10 directly to the vehicle telemetry network, providing a 10 Hz stream from hundreds of sensors, while an activated on-device TPU reached 40 tokens per second for local coaching alerts delivered through text-to-speech. The test identified a throttle application zone in Turn 2 associated with a 0.1-second gain, and the initiative is scheduled to continue at Interlagos, Brazil.
Context
The work addresses the AI trust gap and the domain gap between software expertise and specialized racing knowledge. It follows a pilot that could process basic telemetry and aims to support high-stakes, real-time decisions with physics-grounded architecture and real-time verification.
Approach / What changed
The race coach combines Antigravity orchestration, Python telemetry ingestion, an Agent Development Kit agent collection, Jetpack Compose, Gemma 4 edge reasoning, Gemini API cloud reasoning, and text-to-speech delivery. A custom USB interface connects a Pixel 10 directly to the vehicle telemetry network, while the on-device TPU supports low-latency local coaching.
Takeaways
Antigravity handled stateful orchestration and telemetry ingestion, allowing software engineers to focus on system behavior and coaching methods supplied by racing experts.
A custom USB interface bypassed standard wireless latency and delivered a 10 Hz stream from hundreds of vehicle sensors directly to the Pixel 10.
The architecture uses Gemma 4 as a local fail-safe when connectivity drops, while Gemini API evaluates performance against established driver models in the cloud.
Source and freshness
- Source
- developers.googleblog.com
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.