UnfoldIP

Company patents

Pony AI Inc.

Pony AI Inc. appears to be significantly shifting its patent strategy, as evidenced by a broad decline across nearly all categories since 2023. Surprisingly, despite its core focus on autonomous driving, categories like Radar / Sonar / Lidar (31.2% of portfolio) and Vehicle Control Systems (25.8%) have seen substantial year-over-year declines, with Radar / Sonar / Lidar dropping by 66.7% in 2024, 25.0% in 2025, and 66.7% so far in 2026, while Industrial & Autonomous Control has seen a dramatic -100.0% decline in 2026 after significant drops in prior years. The only exception to this trend is Image Processing, which shows an emerging focus with a +100.0% growth in 2026 (so far), suggesting a potential pivot towards visual data processing within its broader technology portfolio.

Patent Trend by Technology Area

Yearly patent publications since 2023

Product themes

Product-level themes inferred from filings since 2023, with category chips showing where each theme appears. Select a theme to filter the patents below.

128 US filings (since 2023) · 12 categories · 18 themes

ADAS Perception & Display

Systems utilizing various sensors (e.g., cameras, radar, sonar) to perceive the vehicle's surrounding environment, detect objects, and process/display relevant information to the driver for enhanced awareness, assistance in maneuvers, or safety.

Vehicle Body Fittings
Who else files here? →
40since 2023
-54.5%YoY
Sensor-based Environment Perception

Techniques and hardware for autonomous systems to gather and interpret data about their surroundings, including obstacle detection, object recognition, and depth estimation, to inform control decisions.

Computer VisionIndustrial & Autonomous Control
Who else files here? →
36since 2023
-55.6%YoY
Multi-modal Sensor Fusion

Techniques for combining data from disparate sensor types (e.g., cameras, radar, mobile device signals) to achieve a more robust and comprehensive understanding of an environment or subject, often leveraging machine learning for interpretation and correlation.

Radar / Sonar / LidarComputer VisionPattern Recognition & ML Models
Who else files here? →
17since 2023
-50.0%YoY
Autonomous System Redundancy & Validation

Techniques and architectures for ensuring the reliability, fault tolerance, and performance validation of autonomous driving systems, including redundant computing platforms and perception system monitoring.

Vehicle Control Systems
Who else files here? →
15since 2023
0.0%YoY
Lane-Level Mapping & Localization

Techniques for generating, updating, and utilizing highly detailed digital maps that include lane-specific information, and for precisely determining a vehicle's position within these lanes, often using sensor data.

Navigation & Geodesy
Who else files here? →
8since 2023
-66.7%YoY
Sensor Calibration & Compensation

Systems and methods designed to improve the accuracy, reliability, or operational range of sensors and electronic components by measuring temperature and applying corrections or adjustments.

Measurement (Non-specific)
Who else files here? →
6since 2023
-75.0%YoY
Cooperative Driving & Maneuver Planning

Algorithms and systems for planning and executing complex vehicle maneuvers, often involving cooperation with other vehicles or infrastructure, to optimize traffic flow, avoid collisions, or navigate challenging scenarios. This includes lane changes, cut-ins, and traffic congestion.

Vehicle Control Systems
Who else files here? →
5since 2023
new
Multi-Sensor Positioning Systemsfiltered

Integration and processing of data from diverse sensors (e.g., magnetometers, odometers, IMUs, vision sensors) to achieve robust and accurate positioning, especially in environments where GPS is unreliable or unavailable.

Navigation & Geodesy
Who else files here? →
5since 2023
+100.0%YoY
In-Vehicle Electronics & Power

Integration and control of electronic components within the vehicle, including power distribution, thermal management for integrated circuits, and advanced user interfaces such as voice assistants, often involving specialized housings or trim.

Vehicle Body Fittings
Who else files here? →
5since 2023
n/a
Advanced Radar/Lidar Hardware

Innovations in the physical components and architectures of radar, lidar, and sonar systems, including antenna design, RF signal generation, beam steering mechanisms, and optical elements for improved performance.

Radar / Sonar / Lidar
Who else files here? →
4since 2023
new
Smart Parking Systems

Integrated systems for managing parking facilities, guiding vehicles to available spots, and providing notifications, often leveraging sensors, communication, and remote control.

Vehicle Control Systems
Who else files here? →
4since 2023
n/a
Autonomous Path Planning

Algorithms and systems for generating, optimizing, and executing trajectories for autonomous vehicles or robots to move through an environment, often involving obstacle avoidance, route validation, and goal reaching.

Navigation & GeodesyIndustrial & Autonomous Control
Who else files here? →
3since 2023
new
VRU Protection & Localization

Systems and methods for enhancing the safety of vulnerable road users (pedestrians, cyclists) by improving their detection, prediction, and precise localization relative to the vehicle, often leveraging communication technologies and specialized markers.

Vehicle Control Systems
Who else files here? →
3since 2023
n/a
Driver State Monitoring

Systems that monitor a vehicle operator's physiological state, attentiveness, or behavior using in-cabin sensors and machine learning to enhance safety or personalize vehicle functions.

Vehicle Control Systems
Who else files here? →
2since 2023
0.0%YoY
Multi-Agent System Coordination

Methods and systems for managing the interaction, communication, and collaborative tasks among multiple autonomous entities, or between autonomous entities and a central control system or users.

Industrial & Autonomous Control
Who else files here? →
2since 2023
n/a
Precise Positioning & Localization

Methods and systems for accurately determining the absolute or relative position of an object or device, often integrating satellite navigation (GNSS), inertial measurement units (IMU), and local ranging or wireless communication technologies.

Radar / Sonar / Lidar
Who else files here? →
1since 2023
n/a
Braking & Stationary Vehicle Control

Control systems for managing vehicle braking and maintaining a stationary state, including brake pedal actuation sensing, automatic brake hold functions, and coordination with parking brakes.

Vehicle Control Systems
Who else files here? →
1since 2023
n/a
Vision-Based Object & Pose Estimation

Methods and apparatus for detecting objects and determining their three-dimensional position and orientation (pose) using imagery or point cloud data, often for navigation, surveying, or environmental understanding.

Computer Vision
Who else files here? →
1since 2023
n/a

Patents

Showing 1-10 of 10

Multi-Sensor Positioning Systems
Page 1 of 1
US 12436246 B2GRANTED
G01S7/497

Sensor triggering to synchronize sensor data

Filed:2021-05-19Pub:2025-10-07
Applicant:Pony AI Inc.

A computing device triggers a sensor operation. The computing device includes one or more processors and instructions or logic that, when executed by the one or more processors, implements computing functions. The computing device performs receiving timestamps from a sensor, simulating an operation of the sensor, the simulation including predicting orientations of the sensor at different times based on the received timestamps, comparing a latest timestamp of the computing device to a latest timestamp of the sensor, and based on the comparison, triggering a second sensor to perform an operation.

US 12314184 B2GRANTED
G06F12/1009

Efficient retrieval of sensor data while ensuring atomicity

Filed:2021-05-19Pub:2025-05-27
Applicant:Pony AI Inc.

A computing device performs initial processing of sensor data. The computing device performs obtaining sensor data, writing the sensor data to first addresses of a dynamically allocated buffer associated with the computing device, encoding the sensor data, writing the encoded sensor data to second addresses of the dynamically allocated buffer, in response to completing the writing of the encoded sensor data, indicating that the writing of the encoded sensor data has been completed, receiving, from a computing resource, a polling request to read the encoded sensor data, transmitting, to the computing resource, a status that the writing of the encoded sensor data to the second addresses has been completed, reading, to a memory of the computing resource, the encoded sensor data, receiving, from the computing resource, a second status that the encoded sensor data has been read, and removing, from the dynamically allocated buffer, the encoded sensor data.

US 12086213 B2GRANTED
G06F18/25

Generating fused sensor data through metadata association

Filed:2023-06-30Pub:2024-09-10
Applicant:Pony AI Inc.

Described herein are systems, methods, and non-transitory computer readable media for generating fused sensor data through metadata association. First sensor data captured by a first vehicle sensor and second sensor data captured by a second vehicle sensor are associated with first metadata and second metadata, respectively, to obtain labeled first sensor data and labeled second sensor data. A frame synchronization is performed between the first sensor data and the second sensor data to obtain a set of synchronized frames, where each synchronized frame includes a portion of the first sensor data and a corresponding portion of the second sensor data. For each frame in the set of synchronized frames, a metadata association algorithm is executed on the labeled first sensor data and the labeled second sensor data to generate fused sensor data that identifies associations between the first metadata and the second metadata.

US 20230350979 A1APPLICATION
G06F18/25

GENERATING FUSED SENSOR DATA THROUGH METADATA ASSOCIATION

Filed:2023-06-30Pub:2023-11-02
Applicant:Pony AI Inc.

Described herein are systems, methods, and non-transitory computer readable media for generating fused sensor data through metadata association. First sensor data captured by a first vehicle sensor and second sensor data captured by a second vehicle sensor are associated with first metadata and second metadata, respectively, to obtain labeled first sensor data and labeled second sensor data. A frame synchronization is performed between the first sensor data and the second sensor data to obtain a set of synchronized frames, where each synchronized frame includes a portion of the first sensor data and a corresponding portion of the second sensor data. For each frame in the set of synchronized frames, a metadata association algorithm is executed on the labeled first sensor data and the labeled second sensor data to generate fused sensor data that identifies associations between the first metadata and the second metadata.

US 11693927 B2GRANTED
G06F18/25

Generating fused sensor data through metadata association

Filed:2020-07-24Pub:2023-07-04
Applicant:Pony AI Inc.

Described herein are systems, methods, and non-transitory computer readable media for generating fused sensor data through metadata association. First sensor data captured by a first vehicle sensor and second sensor data captured by a second vehicle sensor are associated with first metadata and second metadata, respectively, to obtain labeled first sensor data and labeled second sensor data. A frame synchronization is performed between the first sensor data and the second sensor data to obtain a set of synchronized frames, where each synchronized frame includes a portion of the first sensor data and a corresponding portion of the second sensor data. For each frame in the set of synchronized frames, a metadata association algorithm is executed on the labeled first sensor data and the labeled second sensor data to generate fused sensor data that identifies associations between the first metadata and the second metadata.

US 20220374366 A1APPLICATION
G06F12/1009

EFFICIENT RETRIEVAL OF SENSOR DATA WHILE ENSURING ATOMICITY

Filed:2021-05-19Pub:2022-11-24
Applicant:Pony AI Inc.

A computing device performs initial processing of sensor data. The computing device performs obtaining sensor data, writing the sensor data to first addresses of a dynamically allocated buffer associated with the computing device, encoding the sensor data, writing the encoded sensor data to second addresses of the dynamically allocated buffer, in response to completing the writing of the encoded sensor data, indicating that the writing of the encoded sensor data has been completed, receiving, from a computing resource, a polling request to read the encoded sensor data, transmitting, to the computing resource, a status that the writing of the encoded sensor data to the second addresses has been completed, reading, to a memory of the computing resource, the encoded sensor data, receiving, from the computing resource, a second status that the encoded sensor data has been read, and removing, from the dynamically allocated buffer, the encoded sensor data.

US 11480434 B2GRANTED
G01C21/28

Initial localization

Filed:2020-02-04Pub:2022-10-25
Applicant:Pony AI Inc.

Provided herein is a system comprising: one or more processors; and a memory storing instructions that, when executed by the one or more processors, causes the system to perform: obtaining a previous pose of a vehicle; acquiring one or more previous readings corresponding to one or more wheel encoders during the previous pose; acquiring one or more readings corresponding to one or more wheel encoders acquired after the previous pose; and adjusting the previous pose based on the one or more readings to obtain a current pose.

US 11287269 B2GRANTED
G01C21/32

Map coordinate distortion compensation

Filed:2019-12-10Pub:2022-03-29
Applicant:Pony AI Inc.

Provided herein is a system comprising: one or more processors; and a memory storing instructions that, when executed by the one or more processors, causes the system to perform: generating a projection of a map having an origin; determining distortion factors of the map relative to distances from the origin; determining a distance from a vehicle to the origin; determining a reading from a sensor of the vehicle; and adjusting the reading to coordinates of the map based on a distortion factor corresponding to the distance.

US 20220027684 A1APPLICATION
G06K9/62

GENERATING FUSED SENSOR DATA THROUGH METADATA ASSOCIATION

Filed:2020-07-24Pub:2022-01-27
Applicant:Pony AI Inc.

Described herein are systems, methods, and non-transitory computer readable media for generating fused sensor data through metadata association. First sensor data captured by a first vehicle sensor and second sensor data captured by a second vehicle sensor are associated with first metadata and second metadata, respectively, to obtain labeled first sensor data and labeled second sensor data. A frame synchronization is performed between the first sensor data and the second sensor data to obtain a set of synchronized frames, where each synchronized frame includes a portion of the first sensor data and a corresponding portion of the second sensor data. For each frame in the set of synchronized frames, a metadata association algorithm is executed on the labeled first sensor data and the labeled second sensor data to generate fused sensor data that identifies associations between the first metadata and the second metadata.

US 20210239471 A1APPLICATION
G01C21/28

INITIAL LOCALIZATION

Filed:2020-02-04Pub:2021-08-05
Applicant:Pony AI Inc.

Provided herein is a system comprising: one or more processors; and a memory storing instructions that, when executed by the one or more processors, causes the system to perform: obtaining a previous pose of a vehicle; acquiring one or more previous readings corresponding to one or more wheel encoders during the previous pose; acquiring one or more readings corresponding to one or more wheel encoders acquired after the previous pose; and adjusting the previous pose based on the one or more readings to obtain a current pose.

1