Expired50% confidenceReleaseExact time
Waymo released EMMA (End-to-End Multimodal Model for Autonomous Driving) in 2024, which inputs driving scene images and problem descriptions into the Gemini model to directly generate trajectory planning outputs that include reasoning steps.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/21/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/19/2026(expired)
Sources
Related Claims
UnverifiedXLeRobot adopts a hybrid approach: the navigation phase relies on odometry and spatial reasoning, while the object manipulation phase achieves end-to-end mapping through a VLA model.60% similarUnverifiedOmniRoute's Auto mode comprehensively references remaining quota, price, speed, and service status to automatically select a route.58% similarUnverified在确定性高的表单填写场景中，脚本处理高频确定性路径、Agent作为fallback处理边缘情况的混合架构优于纯LLM驱动方案57% similarUnverifiedThe modular approach facilitates single-module upgrades and fault localization, more easily meets the traceability requirements of functional safety standards, and is the core engineering route of mainstream mass-production autonomous driving systems such as Waymo and Baidu Apollo.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/577460API
curl https://kongchang.com/api/v1/knowledge/claims/577460MCP
get_claim(id=577460)