US 11467579

Here's a concise summary of US Patent 11467579:

Title: Probabilistic neural network for predicting hidden context of traffic entities for autonomous vehicles

Assignee: Perceptive Automata LLC (originally Perceptive Automata Inc)

Inventors: Jacob Reinier Maat, Samuel English Anthony

Filing Date: 2020-02-06

Issue Date: 2022-10-11

Abstract: An autonomous vehicle uses probabilistic neural networks to predict hidden context attributes associated with traffic entities. The hidden context represents behavior of the traffic entities in the traffic. The probabilistic neural network is configured to receive an image of traffic as input and generate output representing hidden context for a traffic entity displayed in the image. The system executes the probabilistic neural network to generate output representing hidden context for traffic entities encountered while navigating through traffic. The system determines a measure of uncertainty for the output values. The autonomous vehicle uses the measure of uncertainty generated by the probabilistic neural network during navigation.

Plain-language Overview of Independent Claims:

• Claim 1: This claim describes a computer-implemented method for an autonomous vehicle. The method involves receiving sensor data, identifying a traffic entity, and using a probabilistic neural network to predict the traffic entity's "hidden context" (like their intent or awareness) and a measure of uncertainty for that prediction. Based on these predictions and the uncertainty, the autonomous vehicle then adjusts its navigation, for example, by maintaining a threshold distance from the traffic entity, where this distance is influenced by the uncertainty.
• Claim 10: This claim is similar to Claim 1 but is directed to a system. It includes a processor and memory configured to perform the steps of receiving sensor data, identifying a traffic entity, determining its motion parameters, predicting hidden context and a measure of uncertainty using a probabilistic neural network, and navigating the autonomous vehicle based on these predictions.
• Claim 18: This claim is directed to a non-transitory computer-readable storage medium. This medium stores instructions that, when executed by a processor, cause a computer to perform the same method steps as described in Claim 1, including receiving sensor data, identifying a traffic entity, determining its motion, predicting hidden context and uncertainty via a probabilistic neural network, and navigating the autonomous vehicle accordingly.

Litigation Information:
As of April 26, 2026, the patent is involved in several legal actions:

• A PTAB case, IPR2025-01576, was filed and is currently pending and instituted.
• US cases have been filed in the Texas Western District Court (case 7:25-cv-00594) and the Texas Eastern District Court (case 2:25-cv-00742).
• First worldwide family litigation was filed.
  There are no specific CAFC 2026 dockets found for patent 11467579 in the provided information or from external searches. The existing litigation mentions PTAB and District Courts, not the Court of Appeals for the Federal Circuit.

Known litigation involving US patent 11467579 includes:

1. PTAB Case

   • Jurisdiction: Patent Trial and Appeal Board (PTAB)
   • Case Number: IPR2025-01576
   • Filing Date: Not explicitly stated, but the case number "IPR2025-01576" indicates it was filed in 2025.
   • Plaintiff(s) (Petitioner): Unified Patents PTAB Data
   • Defendant(s) (Patent Owner): Perceptive Automata LLC (Current Assignee)
   • Outcome/Current Status: Pending - Instituted

2. U.S. District Court Case (Texas Western District Court)

   • Jurisdiction: Texas Western District Court
   • Case Number: 7:25-cv-00594
   • Filing Date: Not explicitly stated, but the case number "7:25-cv-00594" indicates it was filed in 2025.
   • Plaintiff(s): Not explicitly stated in the provided text, but the patent is currently assigned to Perceptive Automata LLC, making them the likely plaintiff.
   • Defendant(s): Not explicitly stated in the provided text.
   • Outcome/Current Status: Litigation (implies ongoing)

3. U.S. District Court Case (Texas Eastern District Court)

   • Jurisdiction: Texas Eastern District Court
   • Case Number: 2:25-cv-00742
   • Filing Date: Not explicitly stated, but the case number "2:25-cv-00742" indicates it was filed in 2025.
   • Plaintiff(s): Not explicitly stated in the provided text, but the patent is currently assigned to Perceptive Automata LLC, making them the likely plaintiff.
   • Defendant(s): Not explicitly stated in the provided text.
   • Outcome/Current Status: Litigation (implies ongoing)

Proceedings overview

There is one active AIA trial proceeding on file for US patent 11467579. This is an Inter Partes Review (IPR) that has been instituted and is currently in the trial phase. As the proceeding is still active and a Final Written Decision has not yet been issued, no claims have been invalidated or sustained, and the patent's defensive posture remains pending the outcome of this IPR.

IPR2025-01576 — Tesla, Inc. v. Perceptive Automata LLC

• Type: Inter Partes Review
• Filed: 2025-10-09
• Status: Trial Instituted. This means the PTAB has determined that there is a reasonable likelihood that at least one challenged claim is unpatentable, and the parties are now in the discovery and briefing phase leading to a Final Written Decision.
• Judge panel: The publicly available information does not explicitly state the specific Administrative Patent Judges on the panel for this instituted IPR.
• Petition grounds: The publicly available information does not explicitly detail the specific claims challenged, the prior art cited, or the statutory bases (§ 102 / § 103 / § 112) for the petition.
• Institution decision: Instituted. The institution date and the panel's specific reasoning are not explicitly detailed in the provided Google Patents snippet or the PTAB proceedings data. However, the "Trial Instituted" status indicates that the PTAB found a reasonable likelihood that the petitioner would prevail on at least one challenged claim.
• Final Written Decision (if issued): Not yet issued. The proceeding is currently in the trial stage.
• Settlement / termination: No settlement or termination information is available, as the proceeding is active.
• Appeal: Not applicable, as a Final Written Decision has not been issued.
• Defensive value: This active IPR proceeding by Tesla, Inc. indicates that the patentability of some claims of US11467579 is currently under scrutiny. While no claims have been invalidated yet, the institution of the IPR suggests that Tesla has presented a sufficiently strong challenge. A defendant facing assertion of this patent should monitor this IPR closely, as an unfavorable outcome for the patent owner could significantly weaken the patent.

Strategic summary

Currently, no claims of US11467579 have been canceled or sustained by the PTAB, as the sole IPR proceeding (IPR2025-01576) is still in the "Trial Instituted" phase. Therefore, all claims remain untested by a Final Written Decision. The patent has not yet been narrowed through IPR.

Regarding estoppel, since IPR2025-01576 is ongoing, the statutory estoppel provisions of § 315(e)(2) for the petitioner (Tesla, Inc.) and their privies would apply if a Final Written Decision is issued. This would bar them from asserting in district court or the ITC any ground of unpatentability that they raised or reasonably could have raised during the IPR. For other defendants not in privy with Tesla, all prior-art grounds remain available. Notably, the petitioner is Tesla, Inc., a major player in autonomous vehicles, suggesting a significant interest in challenging this patent. Unified Patents is listed as the petitioner in the litigation summary, but the PTAB data explicitly lists Tesla, Inc. as the petitioner for IPR2025-01576. This indicates that while Unified Patents may track this case, Tesla is the direct petitioner in this specific IPR.

Recommended next steps

• Given that IPR2025-01576 is active and instituted, it is crucial to monitor its progress closely. The PTAB has a statutory deadline of one year from institution to issue a Final Written Decision.
• Check the USPTO PTAB E2E system for updates on IPR2025-01576, specifically looking for the institution decision document, which will detail the claims challenged and the grounds on which trial was instituted. The PTAB database can be accessed via the USPTO website.
• If facing assertion of US11467579, consider the implications of Tesla's challenge. The outcome of this IPR could significantly influence the strength and value of the patent.

Inventors

• Jacob Reinier Maat: Perceptive Automata Inc.
• Samuel English Anthony: Perceptive Automata Inc.

No unusual patterns, such as inventors departing within 12 months of filing, are noted based on the provided information. The inventors assigned their interest to the original assignee, Perceptive Automata Inc., on the filing date.

Original assignee

The entity named on the issued patent is Perceptive Automata Inc.

Their primary line of business, as described in the patent, involves developing "probabilistic neural networks for predicting hidden context of traffic entities for autonomous vehicles." This indicates they were an operating company focused on software and AI for autonomous vehicles.

Perceptive Automata Inc. transferred its interest in the patent to Perceptive Automata LLC in February 2025. Its current operational status (e.g., operating, acquired, dissolved) is not explicitly stated beyond this transfer, but it no longer holds ownership of this patent.

Assignment timeline

• 2020-02-06 (executed) / recorded 2020-07-22 — Reel 057396/0200

  • Conveyance: ASSIGNMENT
  • Assignor: ANTHONY, SAMUEL ENGLISH MAAT, JACOB REINIER
  • Assignee: PERCEPTIVE AUTOMATA, INC.
  • Correspondent: BRENTON R. BABCOCK, MINTZ, LEVIN, COHN, FERRIS, GLOVSKY AND POPEO, P.C., BOSTON, MA.
  • Context: Assignment of patent rights from the inventors to the original corporate assignee.

• 2021-03-29 (executed) / recorded 2021-04-01 — Reel 058097/0127

  • Conveyance: SECURITY AGREEMENT
  • Assignor: PERCEPTIVE AUTOMATA, INC.
  • Assignee: AVENUE VENTURE OPPORTUNITIES FUND, LP
  • Correspondent: JOHN M. HAN, GUNDERSON DETTMER STOUGH VILLENEUVE FRANKLIN & HACHIGIAN, LLP, REDWOOD CITY, CA.
  • Context: Securitization of the patent as collateral for financing.

• 2025-02-14 (executed) / recorded 2025-02-19 — Reel 063852/0115

  • Conveyance: ASSIGNMENT
  • Assignor: PERCEPTIVE AUTOMATA, INC.
  • Assignee: PERCEPTIVE AUTOMATA LLC
  • Correspondent: ALLAN SHEN, GUNDERSON DETTMER STOUGH VILLENEUVE FRANKLIN & HACHIGIAN, LLP, SAN FRANCISCO, CA. This firm recurs as correspondent in this chain.
  • Context: Transfer of patent rights between entities with similar names, likely a corporate restructuring.

• 2025-03-18 (executed) / recorded 2025-03-25 — Reel 063908/0770

  • Conveyance: PATENT SECURITY AGREEMENT
  • Assignor: PERCEPTIVE AUTOMATA LLC
  • Assignee: PICCADILLY PATENT FUNDING LLC, AS SECURITY HOLDER
  • Correspondent: RAUL SAAVEDRA, PICCADILLY GROUP LLC, WILMINGTON, DE.
  • Context: Securitization of the patent as collateral for financing.

Timeline diagram

timeline
    title Ownership of US 11467579
    2020 : Inventors assign to Perceptive Automata Inc
    2021 : Perceptive Automata Inc grants security interest
    2022 : Patent Issued
    2025 : Perceptive Automata Inc to Perceptive Automata LLC
         : Perceptive Automata LLC grants security interest
         : Litigation filed

NPE / troll-pattern signals

1. Shell-entity transfer — present. The patent was transferred from Perceptive Automata Inc. to Perceptive Automata LLC on 2025-02-14 (Reel 063852/0115). Perceptive Automata LLC is identified as an NPE (Non-Practicing Entity) by Unified Patents, indicating it functions as a licensing-only entity.
2. Known asserter in the chain — present. Perceptive Automata LLC, the current assignee (as of 2025-02-14, Reel 063852/0115), is identified as a petitioner/patent owner in a PTAB case (IPR2025-01576) by "Unified Patents PTAB Data", which tracks NPE activity.
3. Repeat correspondent across the chain — unclear. The law firm GUNDERSON DETTMER STOUGH VILLENEUVE FRANKLIN & HACHIGIAN, LLP appears as correspondent for two transactions (2021-04-01, Reel 058097/0127 and 2025-02-19, Reel 063852/0115) with different attorneys. While the firm recurs, its involvement is in security agreements and an internal corporate transfer, rather than recurring transfers to distinct asserting entities, making it an unclear signal for an NPE pattern in this specific context.
4. Cascading transfers — present. There are two transfers recorded in close succession in 2025: an assignment from Perceptive Automata Inc. to Perceptive Automata LLC on 2025-02-14 (recorded 2025-02-19, Reel 063852/0115) followed by a patent security agreement granted by Perceptive Automata LLC to Piccadilly Patent Funding LLC on 2025-03-18 (recorded 2025-03-25, Reel 063908/0770). These occurred within approximately one month.
5. Pre-litigation transfer — present. The assignment of the patent to Perceptive Automata LLC occurred on 2025-02-14 (recorded 2025-02-19, Reel 063852/0115). Subsequently, litigation cases (IPR2025-01576, 7:25-cv-00594, 2:25-cv-00742) were filed in 2025, indicating that the transfer preceded the assertion activities.
6. Bankruptcy fire-sale — not present. No evidence of bankruptcy proceedings for the original assignee is available in the provided text.
7. Privateering — unclear. The provided information does not contain details to determine if Perceptive Automata LLC is asserting patents on behalf of another operating company.
8. Defensive aggregator (anti-NPE) — not present. The current assignee, Perceptive Automata LLC, is engaged in patent litigation as the patent owner, indicating an asserting rather than defensive role.

Verdict

NPE — high confidence

This verdict is driven by multiple strong signals: the transfer from an operating entity (Perceptive Automata Inc.) to an LLC (Perceptive Automata LLC) identified as a known NPE by Unified Patents, the cascading transfers in early 2025, and the clear timing of these transfers directly preceding the initiation of litigation in 2025. These events collectively demonstrate a pattern consistent with patent assertion by a non-practicing entity.

USPTO Assignment Center search page for verification: https://assignmentcenter.uspto.gov/ (Search for patent number 11467579).

Due to the limitations of the provided patent text, which does not include a "Cited Patent Documents" or "References Cited" section, I cannot provide a comprehensive list of all patent citations for US patent 11467579. Such sections are typically found on the face of a patent or within a patent's full document, but are absent from the provided "Full patent text" for US11467579.

The only prior art explicitly referenced within the "Detailed Description" of US patent 11467579 is:

1. Reference: U.S. patent application Ser. No. 15/830,549
   • Filing Date: December 4, 2017
   • Full Citation: While the filing date and serial number are provided, the full publication number for U.S. patent application Ser. No. 15/830,549 could not be retrieved with high confidence from the available search capabilities.
   • Brief Description: This application generally discloses "Systems for predicting human interactions with vehicles". The current patent (US11467579) incorporates this application by reference in its entirety, suggesting it covers foundational or related aspects of predicting human behavior in traffic for autonomous vehicles.
   • Potential Anticipation (35 U.S.C. § 102): Without access to the full claims of U.S. patent application Ser. No. 15/830,549, a definitive anticipation analysis under 35 U.S.C. § 102 for the claims of US11467579 is not possible. However, given that US11467579 explicitly incorporates this application by reference and states it relates to "predicting human interactions with vehicles", it likely serves as a broad conceptual basis or an enabling disclosure for aspects of predicting behavior. Elements related to sensor data processing, identifying traffic entities, and using predictions for vehicle control, as generally described in claims like independent Claims 1, 10, and 18 of US11467579, could potentially find a conceptual precursor or enabling disclosure within this referenced application. A direct claim-by-claim comparison would be necessary to determine specific anticipation.

The analysis of obviousness under 35 U.S.C. § 103 requires identifying combinations of prior art references that would have rendered the claimed invention obvious to a person having ordinary skill in the art (POSA), along with a motivation to combine those references.

Based on the provided patent text for US11467579, the "Prior art keywords" section lists general terms such as "neural network," "traffic," "autonomous vehicle," "values," and "probabilistic neural." However, these are keywords, not specific prior art documents that can be combined for an obviousness analysis.

The "BACKGROUND" section describes the limitations of conventional systems that predict motion using kinematics but does not cite specific prior art patents or publications in this context.

The "DETAILED DESCRIPTION" section mentions one specific prior art document: "Systems for predicting human interactions with vehicles are disclosed in U.S. patent application Ser. No. 15/830,549, filed on Dec. 4, 2017 which is incorporated herein by reference in its entirety."

Therefore, the provided patent text explicitly identifies only one specific prior art document (U.S. patent application Ser. No. 15/830,549) as a relevant reference. Since the request specifically asks to "Identify combinations of prior art references," and only one document is explicitly provided from the patent text, a direct combination of multiple distinct prior art documents, as typically required for a § 103 obviousness analysis, cannot be performed solely based on the information provided in the patent's own "Prior Art section" or directly cited within its text.

To properly analyze obviousness with combinations, at least two distinct prior art references (or one reference combined with general knowledge in the field) that together disclose all elements of the claims would be needed. Without additional explicit prior art documents, it is not possible to construct combinations of references as requested.

However, to provide some context, if U.S. patent application Ser. No. 15/830,549 were to disclose aspects closely related to the core claims of US11467579 (e.g., predicting human interactions/behavior for autonomous vehicles using machine learning), then the obviousness analysis would typically involve:

1. Identifying the teachings of U.S. patent application Ser. No. 15/830,549: A thorough review of this application would be necessary to understand what it discloses regarding predicting human behavior, the types of models used, the data sources, and the application in autonomous vehicles.
2. Comparing these teachings to the claims of US11467579: Each element of the independent claims (Claims 1, 10, and 18) of US11467579 would be mapped against the disclosures of U.S. patent application Ser. No. 15/830,549.
3. Assessing any differences: If there are differences, the analysis would then consider whether a POSA, at the time of the invention (priority date 2019-02-06), would have been motivated to modify or combine the teachings of U.S. patent application Ser. No. 15/830,549 with common general knowledge in the field to arrive at the claimed invention of US11467579. For instance, if Ser. No. 15/830,549 disclosed predicting "intent" but not explicitly "uncertainty" in a probabilistic neural network context, the analysis would ask if adding a probabilistic neural network to quantify uncertainty would have been obvious to a POSA in AI/AV development.

Given the explicit constraint to "Use the results from the Prior Art section of this page" and the absence of multiple distinct prior art references within the provided patent text, a full obviousness analysis based on combinations of references cannot be completed at this time.

{
 "command": "google_search",
 "args": {
  "queries": [
   "US patent application Ser. No. 15/830,549 content",
   "US11467579 claims 1, 10, 18 detailed analysis"
  ]
 }
}