Company patents

Five AI Limited

Five AI Limited's patent strategy reveals a strong, but recently decelerating, focus on core autonomous vehicle technologies, with Vehicle Control Systems (37.5% of portfolio) and Computer Vision (34.8%) being dominant. While Machine Learning & AI saw explosive growth in 2024 (+450.0% YoY), the significant year-over-year declines across nearly all categories in 2025 and so far in 2026 suggest a potential shift in R&D priorities or a maturation of their initial patenting surge.

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.

112 US filings (since 2023) · 12 categories · 14 themes

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.

Image ProcessingTraffic Control SystemsIndustrial & Autonomous Control
Who else files here? →
54since 2023
-23.8%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? →
35since 2023
0.0%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? →
18since 2023
+25.0%YoY
Autonomous Fleet & Task Managementfiltered

Systems for coordinating and controlling fleets of autonomous vehicles or machines, including task allocation, route optimization, and monitoring their operational status and progress.

Time / Attendance / Access Control
Who else files here? →
16since 2023
+75.0%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 Vision
Who else files here? →
16since 2023
-75.0%YoY
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? →
14since 2023
+50.0%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.

Computer VisionPattern Recognition & ML Models
Who else files here? →
8since 2023
-20.0%YoY
Vehicle Telematics & Diagnostics

Technologies for monitoring vehicle performance, detecting faults, collecting operational data, and providing remote assistance or automated control based on sensor inputs and network connectivity.

Time / Attendance / Access Control
Who else files here? →
6since 2023
0.0%YoY
Automated Visual Inspection

Systems that employ imaging and image processing to automatically detect defects, verify states, or ensure quality control in manufactured goods, printed materials, or industrial processes.

Pictorial / Video Communications
Who else files here? →
6since 2023
n/a
Damage Detection & Structural Assessment

Automated systems using image processing and artificial intelligence to identify, classify, and assess the extent of damage to structures or objects, supporting maintenance or insurance claims.

Image Processing
Who else files here? →
5since 2023
+200.0%YoY
Generative AI for Images

Techniques utilizing deep learning models like Generative Adversarial Networks (GANs) or diffusion models to create new images, modify existing ones, or generate synthetic data based on various inputs or conditions.

Computer Vision
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
3D Reconstruction & Modeling

Processes for creating or manipulating three-dimensional digital representations of objects or environments, including mesh generation, surface fitting, and depth estimation from multiple views.

Image Processing
Who else files here? →
1since 2023
n/a
Video Enhancement & Object Tracking

Methods and systems for improving the quality of video streams, generating intermediate frames, or continuously locating and following objects within a sequence of images, even under occlusion.

Image Processing
Who else files here? →
1since 2023
n/a

Patents

Page 2 of 2
US 20240144745 A1APPLICATION
G07C5/08

PERFORMANCE TESTING FOR AUTONOMOUS VEHICLES

Filed:2022-02-25Pub:2024-05-02
Applicant:Five Al Limited

A computer system for testing the performance of a stack for planning ego vehicle trajectories in real or simulated driving scenarios, the computer system comprising: at least a first input configured to receive (i) scenario ground truth and (ii) internal state data of the stack, the scenario ground truth and internal state data generated using the stack to control an ego agent responsive to at least one other agent in the simulated driving scenario; at least a second input configured to receive a defined operational design domain (ODD); a test oracle configured to apply one or more driving rules to the scenario ground truth for evaluating the performance of the stack in the scenario, and provide an output for each of the driving rules indicating whether that driving rule has been complied with; wherein the one or more driving rules include at least one ODD-based response rule, the test oracle configured to apply the ODD-based response rule by: processing the scenario ground truth over multiple time steps, to determine whether or not the scenario is within the defined ODD at each time step, and thereby detecting a change in the scenario that takes the scenario outside of the defined ODD, and processing the internal state data, to determine whether a required state change occurred within the stack, within a required time interval, the output for the at least one ODD-based response rule indicating whether or not the required state change occurred within the required time interval.

US 20230081921 A1APPLICATION
B60W30/09

PLANNING IN MOBILE ROBOTS

Filed:2021-01-28Pub:2023-03-16
Applicant:Five AI Limited

A computer-implemented method of determining control actions for controlling a mobile robot comprises: receiving a set of scenario description parameters describing a scenario and a desired goal for the mobile robot therein; in a first constrained optimization stage, applying a first optimizer to determine a first series of control actions that substantially globally optimizes a preliminary cost function for the scenario, the preliminary cost function based on a first computed trajectory of the mobile robot, as computed by applying a preliminary robot dynamics model to the first series of control actions, and in a second constrained optimization stage, applying a second optimizer to determine a second series of control actions that substantially globally optimizes a full cost function for the scenario, the full cost function based on a second computed trajectory of the mobile robot, as computed by applying a full robot dynamics model to the second series of control actions; wherein initialization data of at least one of the first computed trajectory and the first series of control actions is used to initialize the second optimizer for determining the second series of control actions, and wherein the preliminary robot dynamic model approximates the full robot dynamics model, the cost functions embody similar objectives to each encourage achievement of the desired goal, and both are optimized with respect to similar hard constraints, such that the initialization data guides the second optimizer to the substantially globally-optimal second series of control actions.