Microsoft AI Predicts Body Motion, Granted US12608073B2
Summary
The USPTO granted US Patent 12,608,073B2 to Microsoft Technology Licensing, LLC on April 21, 2026. The patent covers an AI motion prediction system using reference joint poses and mask tokens to predict body motion trajectories for articulated entities. The 20-claim patent, filed February 3, 2023, is classified under CPC G06N 3/08 and relates to machine learning applications for motion modeling.
What changed
USPTO issued Patent 12,608,073B2 to Microsoft Technology Licensing, LLC for an AI-based body motion prediction method. The system uses reference joint poses combined with temporally adaptable mask tokens to predict trajectories and poses of articulated entities, handling both observed and unobserved joint conditions. The patent contains 20 claims and covers CPC classifications including G06N 3/08 and G06T 13/40.
Technology companies developing AI motion prediction systems, gesture recognition interfaces, animation systems, or motion capture applications should review this patent to assess potential licensing requirements or design-around considerations for their own products.
Archived snapshot
Apr 21, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
Predicting body motion
Grant US12608073B2 Kind: B2 Apr 21, 2026
Assignee
Microsoft Technology Licensing, LLC.
Inventors
Mohammand Sadegh Ali Akbarian, Fatemehsadat Saleh, Pashmina Jonathan Cameron
Abstract
For each of a plurality of time steps: receive a reference joint pose of an articulated entity and receiving an indication that another joint of the articulated entity is unobserved or observed. Prompt a motion model using the reference joint pose and a mask token. The model predicts body motion comprising a trajectory of the articulated entity and a pose of a plurality of joints of the articulated entity. The mask token represents the other joint and is temporally adaptable by: in response to receiving an indication that the other joint is unobserved, using information about the reference joint pose and a pose of the other joint from a previous time step; and in response to receiving an indication that the other joint is observed, using information about the reference joint pose and a pose of the other joint from the current time step.
CPC Classifications
G06F 3/011 G02B 27/0093 G06N 3/08 G06T 13/40
Filing Date
2023-02-03
Application No.
18164391
Claims
20
Mentioned entities
Related changes
Get daily alerts for USPTO Patent Grants - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Grants - AI & Computing (G06N) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.