Waymo and Google secure grants for autonomous vehicle data mining and reinforcement learning.
The filing
Waymo LLC received a US grant on November 10, 2026, for a system that maintains multiple density estimation models to score the rarity of sensor inputs in driving logs (USPTO 12,792,874 (opens in a new tab)). Google LLC also received US grants on the same date for methods that perform reinforcement learning using centralized inference and training across multiple environments, and for techniques to determine the importance of tokens in machine learning models using multi-model stochastic sparsity inducing regularization (USPTO 12,792,905 (opens in a new tab), USPTO 12,792,960 (opens in a new tab)). On November 12, 2026, Google LLC published applications covering full attention mechanisms with sparse computation costs, variational quantization models for efficient content creation, and adaptive large language model architectures that adjust based on system-on-chip temperature and power (USPTO 20260359561A1 (opens in a new tab), USPTO 20260359612A1 (opens in a new tab), USPTO 20260359663A1 (opens in a new tab)), plus an application for the decentralized learning of large machine learning models (USPTO 20260360353A1 (opens in a new tab)).
This filing’s full text wasn’t read for this issue, so its claims and the applicant’s background aren’t shown. Both are in the record, under Sources.