US 11520346

US Patent 11520346, titled "Navigating autonomous vehicles based on modulation of a world model representing traffic entities," was issued on December 6, 2022, from an application filed on January 30, 2020. [cite: The full patent text confirms this information] The current assignee is Perceptive Automata LLC, and the inventor is Samuel English Anthony. [cite: The full patent text confirms this information]

Abstract:
The patent describes an autonomous vehicle system that uses machine learning models to predict "hidden context attributes" of traffic entities. This hidden context helps the system predict human behavior more like a human driver would. Based on this predicted hidden context, the system determines an activation threshold for the vehicle's braking system and modifies a world model. This allows the autonomous vehicle to be navigated safely, maintaining at least a threshold distance from traffic entities. [cite: The full patent text confirms this information]

Independent Claims Overview:

The patent includes multiple independent claims. Below is a plain-language overview of each:

• Claim 1 (Method for navigating an autonomous vehicle): A method for an autonomous vehicle to navigate through traffic involves:

  1. Receiving sensor data (e.g., from cameras, lidars).
  2. Identifying traffic entities (e.g., pedestrians, bicyclists, other vehicles) from this data.
  3. For each identified traffic entity:
     • Determining its motion parameters (e.g., speed, direction).
     • Determining a "hidden context" using a machine learning model. This model is trained using feedback from human users who were shown images or videos of traffic scenarios.
  4. Navigating the autonomous vehicle based on both the motion parameters and the hidden context of each traffic entity. [cite: The full patent text confirms this information]

• Claim 9 (Method for braking an autonomous vehicle): A method for an autonomous vehicle's braking system involves:

  1. Receiving sensor data from the vehicle's sensors.
  2. Identifying traffic entities based on this data.
  3. For each traffic entity:
     • Determining a "hidden context" using a machine learning model trained with human feedback on traffic scenarios. The model's output includes a measure of statistical distribution of this hidden context.
  4. Determining an activation threshold value for the autonomous vehicle's braking system based on this measure of statistical distribution.
  5. Predicting if the autonomous vehicle is likely to come within this activation threshold of a particular traffic entity within a set time.
  6. If such a prediction is made, activating the braking system. [cite: The full patent text confirms this information]

• Claim 16 (Method for modifying a world model): A method for an autonomous vehicle to modify its world model involves:

  1. Generating a point cloud representation of the vehicle's surroundings from sensor data.
  2. Identifying traffic entities from the sensor data.
  3. Determining motion parameters for each traffic entity.
  4. Predicting a "hidden context" for each traffic entity using a machine learning model trained with human feedback on traffic scenarios.
  5. Determining a region within the point cloud where each traffic entity is expected to be within a set time.
  6. Modifying this region based on the predicted hidden context.
  7. Navigating the autonomous vehicle to stay at least a threshold distance away from the modified region of each traffic entity. [cite: The full patent text confirms this information]

CAFC 2026 Dockets:
A direct search for US patent 11520346 within the CAFC 2026 dockets using the provided search snippets did not return any specific cases related to this patent. While the Google Patents page indicates "Family has litigation" and references a PTAB case (IPR2025-01577), this is not a CAFC docket. There is no authoritative information from the provided search results to confirm ongoing litigation for this specific patent in the CAFC during 2026.US Patent 11520346, titled "Navigating autonomous vehicles based on modulation of a world model representing traffic entities," was issued on December 6, 2022, from an application filed on January 30, 2020. The current assignee is Perceptive Automata LLC, and the inventor is Samuel English Anthony.

Abstract:
The patent describes an autonomous vehicle system that uses machine learning models to predict "hidden context attributes" of traffic entities. This hidden context helps the system predict human behavior more like a human driver would. Based on this predicted hidden context, the system determines an activation threshold for the vehicle's braking system and modifies a world model. This allows the autonomous vehicle to be navigated safely, maintaining at least a threshold distance from traffic entities.

Independent Claims Overview:

• Claim 1 (Method for navigating an autonomous vehicle): This claim describes a method for an autonomous vehicle to navigate by:

  1. Receiving sensor data from its environment.
  2. Identifying traffic entities (e.g., pedestrians, other vehicles) from this data.
  3. For each traffic entity, determining its current movement parameters and a "hidden context." The hidden context is predicted by a machine learning model trained on human feedback from observing traffic scenarios.
  4. Controlling the autonomous vehicle's navigation based on both the movement parameters and the predicted hidden context.

• Claim 9 (Method for braking an autonomous vehicle): This claim outlines a method for an autonomous vehicle's braking system to operate by:

  1. Receiving sensor data and identifying traffic entities.
  2. For each traffic entity, determining a "hidden context" using a machine learning model. This model's output includes a statistical distribution of the hidden context.
  3. Setting an activation threshold for the braking system based on this statistical distribution.
  4. Predicting if the vehicle will likely come within this threshold distance of a traffic entity within a certain time.
  5. Activating the braking system if that prediction is made.

• Claim 16 (Method for modifying a world model): This claim details a method for an autonomous vehicle to modify its internal "world model" by:

  1. Generating a 3D point cloud representation of its surroundings using sensor data.
  2. Identifying traffic entities and their motion parameters within this representation.
  3. Predicting a "hidden context" for each traffic entity using a machine learning model trained with human feedback.
  4. Determining a projected future region in the point cloud where each traffic entity is expected to move within a given time.
  5. Modifying this projected region based on the predicted hidden context.
  6. Navigating the autonomous vehicle to maintain a safe distance from these modified regions.

CAFC 2026 Dockets:
As of April 26, 2026, a search for US patent 11520346 within the CAFC 2026 dockets did not return any specific cases. While the Google Patents page for US11520346 indicates that the patent family has litigation, including a PTAB case (IPR2025-01577), this specific patent was not found in the provided CAFC docket information for 2026. [cite: The full patent text confirms this information]