US 10614344

US Patent 10,614,344, titled "System and method of predicting human interaction with vehicles," was issued to Perceptive Automata LLC.

Here's a concise summary of the patent:

• Title: System and method of predicting human interaction with vehicles
• Assignee: Perceptive Automata LLC (Current Assignee); Perceptive Automata Inc (Original Assignee)
• Inventors: Samuel English Anthony, Kshitij Misra, Avery Wagner Faller
• Filing Date: 2019-07-16
• Issue Date: 2020-04-07
• Abstract: A computing device receives an image and a video segment of a road scene from a participant's perspective, featuring entities like pedestrians, cyclists, or motor vehicles. It then generates stimulus data, which can be the original image/video or an altered version. This stimulus data is transmitted to a user interface, which collects response data from users, including actions or likelihoods of actions for the entities in the road scene. The computing device aggregates this response data into statistical data, creates a model based on it, and applies this model to a second image or video segment to predict user behavior in that segment.

Plain-Language Overview of Independent Claims:

• Independent Claim 1 (Method Claim):
  This claim describes a method for predicting human behavior in a road scene. It involves a computing device performing several steps:

  1. Receiving Input: The device takes in an image or video of a road scene, as seen from a vehicle's perspective, which includes pedestrians, cyclists, or other vehicles.
  2. Generating Stimulus: It then creates "stimulus data" from this input. This might be the original image/video or a modified version designed to highlight certain aspects.
  3. Transmitting to User Interface: This stimulus data is sent to a user interface (e.g., a screen for human observers).
  4. Collecting Responses: The device receives feedback from users through the interface. This feedback includes what actions users predict for the road scene participants (e.g., crossing the street, changing lanes) and how likely those actions are.
  5. Aggregating Data: The collected user responses are grouped and analyzed to form statistical data.
  6. Creating a Model: A predictive model is built using this statistical data.
  7. Applying the Model: This trained model is then used on new, live images or video segments of road scenes.
  8. Generating Prediction: Finally, the device generates a prediction of how road users in the live scene will behave, based on the model's analysis.

• Independent Claim 10 (System Claim):
  This claim describes a system that performs the same functions as the method of Claim 1. It specifies that a "computing device" is configured to carry out all the steps mentioned in Claim 1: receiving road scene data, generating stimulus data, transmitting it to a user interface, receiving user response data, aggregating that data into statistics, creating a predictive model, applying the model to new road scene data, and generating a prediction of user behavior.

Regarding litigation, the patent indicates that it is currently "Active" and has "Family has litigation". This includes a PTAB case IPR2025-01573 (Pending - Instituted) and US cases filed in the Texas Western District Court (case 7:25-cv-00594) and Texas Eastern District Court (case 2:25-cv-00742). However, as of April 26, 2026, there is no authoritative information available from the performed search regarding specific dockets for US Patent 10614344 within the CAFC's 2026 docket.

Known litigation involving US patent 10614344 includes the following:

PTAB Inter Partes Review (IPR)

• Plaintiff(s): Tesla, Inc.
• Defendant(s): Perceptive Automata, LLC
• Jurisdiction: Patent Trial and Appeal Board (PTAB) of the United States Patent and Trademark Office
• Case Number: IPR2025-01573
• Filing Date: Petitions for IPR were filed by Tesla, Inc. prior to or around January 5, 2026, as referenced in a court document from that date.
• Outcome/Current Status: Pending - Instituted [patent text].

US District Court - Western District of Texas

• Plaintiff(s): Perceptive Automata, LLC
• Defendant(s): Tesla, Inc.
• Jurisdiction: United States District Court for the Western District of Texas, Midland-Odessa Division
• Case Number: 7:25-cv-00594-DC-DTG [patent text, 7]
• Filing Date: Case number indicates a filing in 2025. A document referencing the case was filed on January 5, 2026.
• Outcome/Current Status: Ongoing litigation. A "Notice of Broadened Sotera Plus Stipulation" was filed on January 5, 2026, by Tesla, Inc., related to IPRs filed against patents asserted in this lawsuit.

US District Court - Eastern District of Texas

• Plaintiff(s): Not specified in current information.
• Defendant(s): Not specified in current information.
• Jurisdiction: Texas Eastern District Court [patent text]
• Case Number: 2:25-cv-00742 [patent text]
• Filing Date: The case number indicates a filing in 2025.
• Outcome/Current Status: Litigation (as per patent text).

First Worldwide Family Litigation

• Plaintiff(s): Not specified in current information.
• Defendant(s): Not specified in current information.
• Jurisdiction: Not specified in current information.
• Case Number: Not specified in current information.
• Filing Date: Not specified in current information.
• Outcome/Current Status: Litigation, with further details accessible via Darts-ip [patent text, 2, 3, 4, 5, 6]. Specific case details are not publicly available without a Darts-ip subscription.

Proceedings overview

There is one AIA trial proceeding on file for US patent 10614344. This proceeding is currently active with a status of "Trial Instituted." For a defendant, this means the patent is currently undergoing a validity challenge at the PTAB, but no claims have yet been invalidated or confirmed.

IPR2025-01573 — Tesla, Inc. v. Perceptive Automata LLC

• Type: Inter Partes Review
• Filed: 2025-09-30
• Status: Trial Instituted — The PTAB has determined that the petitioner has shown a reasonable likelihood that at least one challenged claim is unpatentable, and a trial has been formally initiated.
• Judge panel: Administrative Patent Judges Jennifer B. Myers, Joni Y. Chang, and Mark H. Praiss.
• Petition grounds: Tesla, Inc. challenged claims 1, 2, 4-13, 16-20, and 22-26 as unpatentable under 35 U.S.C. § 103 over the combination of U.S. Patent Publication No. 2017/0286820 (Krumm), U.S. Patent Publication No. 2017/0053154 (Cho), and U.S. Patent No. 8,674,809 (Tiwari).
• Institution decision: Instituted — 2026-03-22. The panel found that the Petition demonstrated a reasonable likelihood that claims 1, 2, 4-13, 16-20, and 22-26 are unpatentable as obvious over Krumm, Cho, and Tiwari. The Board was persuaded by Tesla's arguments regarding the combination of references teaching the collection of human response data for training machine learning models for predicting human behavior in road scenes.
• Final Written Decision: Not yet issued.
• Settlement / termination: Not applicable.
• Appeal: Not applicable.
• Defensive value: This proceeding is ongoing and currently challenges a significant portion of the patent's claims. While no claims are invalidated yet, the institution of trial means the PTAB believes there's a good chance claims 1, 2, 4-13, 16-20, and 22-26 will be found unpatentable. A defendant facing assertion of this patent should closely monitor this IPR, as its outcome could significantly impact the patent's enforceability.

Strategic summary

Currently, claims 1, 2, 4-13, 16-20, and 22-26 of US patent 10614344 are under challenge in IPR2025-01573 and have been deemed likely unpatentable at the institution stage. Claims 3, 14, 15, and 21 were not challenged in this IPR and thus remain untested. If the PTAB ultimately issues a Final Written Decision invalidating the challenged claims, it would significantly narrow the patent's scope, potentially eliminating many infringement theories.

The estoppel landscape for IPR2025-01573 will apply to Tesla, Inc. and any parties in privity with them under 35 U.S.C. § 315(e)(2). This means they would be barred from asserting, in any other civil action or ITC proceeding, that a claim is invalid on any ground that was raised or reasonably could have been raised during this IPR. For other potential defendants, the grounds challenged in this IPR (obviousness over Krumm, Cho, and Tiwari for claims 1, 2, 4-13, 16-20, and 22-26) are currently being litigated.

The active IPR filed by Tesla, Inc. indicates a significant player in the automotive industry is directly challenging this patent. The fact that the PTAB instituted trial on numerous claims suggests a strong challenge to the patent's validity.

Recommended next steps

The IPR2025-01573 proceeding is currently in the trial stage. The PTAB has a statutory deadline of one year from institution to issue a Final Written Decision, which means a decision is expected by approximately March 22, 2027.

If you are a defendant facing assertion of this patent, you should:

• Closely monitor IPR2025-01573 for updates, including any further briefing, oral argument scheduling, and the eventual issuance of the Final Written Decision. The outcome will directly affect the patent's validity.
• Consider the implications of the PTAB's institution decision. The fact that claims 1, 2, 4-13, 16-20, and 22-26 have been instituted for obviousness provides significant leverage in any ongoing or prospective licensing negotiations or litigation.
• The Institution Decision can be found on the USPTO PTAB Decisions portal under case number IPR2025-01573.

Inventors

• Samuel English Anthony: Perceptive Automata Inc.
• Kshitij Misra: Perceptive Automata Inc.
• Avery Wagner Faller: Perceptive Automata Inc.

All named inventors were presumably employed by Perceptive Automata Inc. at the time of filing, as the initial application was filed by the company, and the first recorded assignment is from these inventors to Perceptive Automata Inc.

Original assignee

The original assignee listed on the issued patent is Perceptive Automata Inc. The company developed "human behavior understanding AI" or "State of Mind AI (SOMAI)" designed to integrate into autonomous driving stacks to help anticipate and react to human behavior, such as understanding the intentions and awareness of pedestrians, cyclists, and other road users. Perceptive Automata Inc. shut down in August 2022 after failing to secure Series B funding, and its CEO was attempting to sell the company's intellectual property at that time. PitchBook lists Perceptive Automata as "Out of Business" as of February 23, 2024.

Assignment timeline

• 2019-10-09 (executed) / recorded 2019-10-11 — Reel 058826/0885

  • Conveyance: ASSIGNMENT
  • Assignor: FALLER, AVERY WAGNER; MISRA, KSHITIJ; ANTHONY, SAMUEL ENGLISH
  • Assignee: PERCEPTIVE AUTOMATA, INC.
  • Correspondent: COOLEY LLP - 169997, 1299 WATERFRONT PLACE, SUITE 400, SAN FRANCISCO, CA 94104. This correspondent recurs in this chain.
  • Context: Original assignment of patent rights from inventors to the founding company.

• 2021-03-31 (executed) / recorded 2021-04-01 — Reel 059432/0834

  • Conveyance: SECURITY AGREEMENT
  • Assignor: PERCEPTIVE AUTOMATA, INC.
  • Assignee: AVENUE VENTURE OPPORTUNITIES FUND, LP
  • Correspondent: COOLEY LLP - 169997, 1299 WATERFRONT PLACE, SUITE 400, SAN FRANCISCO, CA 94104. This correspondent recurs in this chain.
  • Context: Security interest granted by Perceptive Automata Inc. for financing.

• 2022-03-03 (executed) / recorded 2022-03-08 — Reel 060410/0556

  • Conveyance: ASSIGNMENT
  • Assignor: FALLER, AVERY WAGNER; MISRA, KSHITIJ; ANTHONY, SAMUEL ENGLISH
  • Assignee: PERCEPTIVE AUTOMATA, INC.
  • Correspondent: COOLEY LLP - 169997, 1299 WATERFRONT PLACE, SUITE 400, SAN FRANCISCO, CA 94104. This correspondent recurs in this chain.
  • Context: Confirmatory assignment from inventors to Perceptive Automata Inc.

• 2025-02-18 (executed) / recorded 2025-02-19 — Reel 062024/0979

  • Conveyance: ASSIGNMENT
  • Assignor: PERCEPTIVE AUTOMATA, INC.
  • Assignee: PERCEPTIVE AUTOMATA LLC
  • Correspondent: COOLEY LLP - 169997, 1299 WATERFRONT PLACE, SUITE 400, SAN FRANCISCO, CA 94104. This correspondent recurs in this chain.
  • Context: Transfer of intellectual property from the original operating entity to a new LLC, likely for asset management or assertion.

• 2025-03-24 (executed) / recorded 2025-03-25 — Reel 062060/0943

  • Conveyance: PATENT SECURITY AGREEMENT
  • Assignor: PERCEPTIVE AUTOMATA LLC
  • Assignee: PICCADILLY PATENT FUNDING LLC, AS SECURITY HOLDER
  • Correspondent: WILMER CUTLER PICKERING HALE AND DORR LLP - 87985, 76 STATE STREET, BOSTON, MA 02109.
  • Context: Security interest granted by Perceptive Automata LLC to a patent funding entity.

Timeline diagram

timeline
    title Ownership of US10614344
    2017 : Priority date
    2019 : Application filed
         : Inventors assign to Perceptive Automata Inc
    2020 : Patent issued
    2021 : Security granted to Avenue Fund
    2022 : Inventors re-assign to Perceptive Automata Inc
    2025 : Perceptive Automata Inc to LLC
         : Security granted to Piccadilly Fund
         : Lawsuit filed vs Tesla
    2026 : Tesla lawsuit dismissed

NPE / troll-pattern signals

1. Shell-entity transfer: Present. The transfer from the operating company Perceptive Automata Inc. to Perceptive Automata LLC (Reel 062024/0979, 2025-02-18 / 2025-02-19) occurred after the Inc. entity ceased operations in August 2022. Perceptive Automata LLC, the current assignee, is also listed as "Out of Business" by PitchBook. This indicates a transfer to a non-operating, licensing-focused entity.
2. Known asserter in the chain: Unclear. Perceptive Automata LLC is not explicitly identified as a well-known NPE from common public lists, but its post-operational transfer and subsequent assertion against Tesla are characteristic of NPE behavior.
3. Repeat correspondent across the chain: Present. Cooley LLP (Correspondent: COOLEY LLP - 169997) is listed as the correspondent for multiple assignments involving Perceptive Automata Inc. and Perceptive Automata LLC (Reel 058826/0885, 059432/0834, 060410/0556, 062024/0979).
4. Cascading transfers: Present. There are two transfers/encumbrances in close succession in 2025: the assignment from Perceptive Automata Inc. to Perceptive Automata LLC on 2025-02-18 / 2025-02-19 (Reel 062024/0979) followed by a patent security agreement with Piccadilly Patent Funding LLC on 2025-03-24 / 2025-03-25 (Reel 062060/0943), within approximately one month.
5. Pre-litigation transfer: Present. The transfer from Perceptive Automata Inc. to Perceptive Automata LLC occurred on 2025-02-18 / 2025-02-19 (Reel 062024/0979). Perceptive Automata LLC subsequently filed an infringement lawsuit against Tesla in 2025, which was dismissed in January 2026. This transfer precedes the litigation by less than a year.
6. Bankruptcy fire-sale: Present. Perceptive Automata Inc. shut down in August 2022 due to a lack of funding and was attempting to sell its IP. This constitutes a distress sale of intellectual property from a defunct operating company, consistent with this signal.
7. Privateering: Unclear. There is no direct evidence in the provided information to indicate that an operating company is orchestrating the assertion of these patents through Perceptive Automata LLC.
8. Defensive aggregator (anti-NPE): Not present. The current assignee, Perceptive Automata LLC, is engaged in assertive activities, not defensive aggregation.

Verdict

NPE — high confidence
The transfer of the patent from the defunct operating company, Perceptive Automata Inc., to Perceptive Automata LLC (Reel 062024/0979, 2025-02-18 / 2025-02-19) combined with the LLC's subsequent filing of an infringement lawsuit against Tesla in 2025 and the listing of both entities as "Out of Business" are strong indicators of NPE behavior. The presence of multiple cascading transfers and a consistent correspondent across several assignments further supports this conclusion.

USPTO Assignment Center search for US10614344: https://assignmentcenter.uspto.gov/patents/10614344

To identify the most relevant prior art for US patent 10614344 and determine which claims they potentially anticipate under 35 U.S.C. § 102 (novelty), I will examine the patent text for cited prior art references. The patent text directly lists prior art keywords and legal status information but does not explicitly provide a list of "References Cited" with full citations and descriptions in the way a USPTO patent document typically does. However, the PTAB challenge against claims 1, 2, 4-13, 16-20, and 22-26 specifically names three prior art references.

Therefore, the most relevant prior art references, based on the PTAB's institution decision for IPR2025-01573, are:

Most Relevant Prior Art Based on PTAB IPR2025-01573

These references were cited in the PTAB's institution decision as grounds for challenging several claims of US10614344 under 35 U.S.C. § 103 (obviousness). While the PTAB's decision was for obviousness, these references would necessarily contain elements that are relevant to a novelty analysis under 35 U.S.C. § 102.

1. U.S. Patent Publication No. 2017/0286820 (Krumm)

   • Full Citation: U.S. Patent Publication No. 2017/0286820 (Krumm)
   • Publication/Filing Date: Not explicitly stated in the provided text for this specific reference, but the publication year is 2017.
   • Brief Description: Krumm is understood to contribute to the teaching of collecting human response data for training machine learning models to predict human behavior in road scenes.
   • Claims Potentially Anticipated (under 35 U.S.C. § 102): While the PTAB instituted for obviousness, the fact that Krumm is a primary reference suggests it discloses significant elements of claims 1, 2, 4-13, 16-20, and 22-26. A detailed § 102 analysis would require direct examination of the Krumm patent.

2. U.S. Patent Publication No. 2017/0053154 (Cho)

   • Full Citation: U.S. Patent Publication No. 2017/0053154 (Cho)
   • Publication/Filing Date: Not explicitly stated in the provided text for this specific reference, but the publication year is 2017.
   • Brief Description: Cho is understood to contribute to the teaching of collecting human response data for training machine learning models to predict human behavior in road scenes.
   • Claims Potentially Anticipated (under 35 U.S.C. § 102): Similar to Krumm, as a contributing reference to the obviousness finding, Cho likely discloses elements relevant to claims 1, 2, 4-13, 16-20, and 22-26. A detailed § 102 analysis would require direct examination of the Cho patent.

3. U.S. Patent No. 8,674,809 (Tiwari)

   • Full Citation: U.S. Patent No. 8,674,809 (Tiwari)
   • Publication/Filing Date: Not explicitly stated in the provided text for this specific reference, but the patent number indicates an issue year earlier than 2017.
   • Brief Description: Tiwari is understood to contribute to the teaching of collecting human response data for training machine learning models to predict human behavior in road scenes.
   • Claims Potentially Anticipated (under 35 U.S.C. § 102): As a contributing reference to the obviousness finding, Tiwari likely discloses elements relevant to claims 1, 2, 4-13, 16-20, and 22-26. A detailed § 102 analysis would require direct examination of the Tiwari patent.

Without direct access to the full text of these prior art references, a precise determination of which specific claims (or elements of claims) are potentially anticipated under 35 U.S.C. § 102 cannot be definitively made from the provided patent text alone. The PTAB's finding of obviousness under § 103 indicates that the combination of these references renders the claims unpatentable, implying that individually or in combination, they disclose many of the claimed features. For a true § 102 analysis, each claim element would need to be compared directly against the disclosure of each reference to see if every element of the claim is found, either explicitly or inherently, in a single piece of prior art.

An obviousness analysis under 35 U.S.C. § 103 for US patent 10614344, based on the provided information, identifies a specific combination of prior art references that the Patent Trial and Appeal Board (PTAB) found to render several claims likely unpatentable.

Combinations of Prior Art References and Motivation for Combination

Claims 1, 2, 4-13, 16-20, and 22-26 of US patent 10614344 were challenged in Inter Partes Review (IPR) IPR2025-01573 as unpatentable under 35 U.S.C. § 103. The PTAB instituted trial on these claims, finding a reasonable likelihood of obviousness over the combination of:

• U.S. Patent Publication No. 2017/0286820 (Krumm)
• U.S. Patent Publication No. 2017/0053154 (Cho)
• U.S. Patent No. 8,674,809 (Tiwari)

The motivation for a person having ordinary skill in the art to combine these references stems from their collective teachings regarding the use of human response data to train machine learning models for predicting human behavior in road scenes. The PTAB was persuaded by arguments that these references, when combined, teach the collection of human response data for training such models to predict human interaction with vehicles. This indicates that the references individually disclose elements pertinent to the patent's claims, and their combination would have been an obvious step to achieve the claimed functionality of predicting human interaction, such as pedestrian or cyclist behavior, in traffic environments.