Cut-In Vehicle Trajectory Prediction Patents: Top Companies & Trends 2026
Filing growth compares 2021 (26 records) with 2024 (28) — a three-year span. 2024 is the most recent year we treat as complete: publication lags filing by roughly 18 months, so 2025 onwards are still filling in and any growth rate that ends there would understate the field. Top-5 share is the combined record count of the five largest assignees divided by all 211 records in scope (CR5), not by the ranked leaders only.
What this landscape covers
This landscape maps 211 published patent records at the intersection of cut-in prediction, lane-change prediction, surrounding-vehicle prediction and vehicle trajectory prediction within autonomous and self-driving vehicle systems. The search string requires both a prediction-method term and an autonomous-driving framing term, so records here are specifically about anticipating another vehicle’s motion as an input to a self-driving control stack, not trajectory prediction in the abstract.
Coverage runs from 2015 through the 2026-07-31 data cut-off. Because publication typically lags filing by roughly 18 months, the 2025 and 2026 counts in the trend chart are understated and should not be read as a slowdown.
Let an AI agent run this analysis on your own technology
Pick a task. Every answer cites the patents behind it.
Filing trend and technology composition
Two views of the same 211-record dataset: how filing activity has moved year over year, and which IPC subclasses carry the claim weight.
Filing trend, 2017-2026
Annual filings rose from 11 in 2017 to a peak of 47 in 2023. The 2021-to-2024 window shows +8% growth (26 to 28 records) — the most recent span that can be treated as complete given publication lag. 2025 and 2026 figures will continue to fill in as later filings publish.
IPC subclass distribution
B60W (hybrid/joint vehicle control) covers 65.4% of the 211 records, confirming that most filings frame trajectory prediction as a control-system function rather than a pure perception or computing problem. G06N (AI-model computing) sits second at 42.7%, with G08G (traffic control systems), G06V (image/video recognition) and G05D (non-electric variable control) each present in a meaningful minority of records. Because a single record can carry several IPC classes, these shares sum to well over 100% of the record total.
Shares are the percentage of the 211 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on Autonomous Driving — Cut-In Vehicle Trajectory Prediction Patent Landscape with Eureka
This page is one run against one query. Ask Eureka your own question about autonomous driving — cut-in vehicle trajectory prediction patent landscape and every answer comes back with the patent numbers behind it.
Try EurekaMost-cited records and a representative filing
Vehicle trajectory prediction near or at traffic signal
A system and method for determining a predicted trajectory of a human-driven host vehicle as it approaches a traffic signal, using host vehicle-to-signal distance, longitudinal vehicle speed, signal phase, signal timing and time of day as inputs to the prediction.Filed by The Regents of the University of Michigan; published 2021-09-09 as US20210276594A1.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US20210056713A1 | Surround vehicle tracking and motion prediction | 104 |
| 2 | US20200172093A1 | Lane-based probabilistic motion prediction of surrounding vehicles and predictive longitudinal control method… | 102 |
| 3 | US20200089246A1 | Systems and methods for controlling the operation of a vehicle | 74 |
| 4 | US20190077398A1 | System and method for vehicle lane change prediction using structural recurrent neural networks | 71 |
| 5 | WO2019136479A1 | Surround vehicle tracking and motion prediction | 61 |
| 6 | US11004000B1 | Predicting trajectory intersection by another road user | 48 |
| 7 | US20210201504A1 | Vehicle trajectory prediction model with semantic map and lstm | 46 |
| 8 | US20220306152A1 | Task-Motion Planning for Safe and Efficient Urban Driving | 37 |
| 9 | US20220114885A1 | Coordinated control for automated driving on connected automated highways | 32 |
| 10 | US20210276594A1 | Vehicle trajectory prediction near or at traffic signal | 32 |
Citation counts reflect influence within the searched corpus and skew toward older records; treat them as a signal of prior-art density, not of current commercial relevance.
Each row carries its publication number; clicking a row searches Eureka by that number.
Put your own technology through the same analysis
Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →MCP server & REST API
When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →What the filing pattern signals
Three read-throughs from the assignee, class and citation data that matter for freedom-to-operate and roadmap decisions.
Leadership is real but not exclusive
The leading assignee holds 21 records and fifth place holds 9, so the gap from first to fifth is wide but not a monopoly. The top 10 combined reach 43.6% of all records, leaving more than half the field to a long tail of single- and low-count filers.
Control-layer framing dominates over pure AI-model claims
Most filings anchor their claims in vehicle control (B60W) even when a prediction model (G06N) is part of the system. Claims that isolate the AI model itself, independent of the control action taken on its output, are comparatively rarer.
Steady growth, not a filing rush
The three-year growth figure of +8% from 2021 to 2024, against a 2023 peak of 47 filings, describes measured expansion rather than a land-grab. Several previously active assignees show no filings in the latest tracked year, which is consistent with publication lag rather than withdrawal from the space.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to autonomous driving — cut-in vehicle trajectory prediction patent landscape, with the prior art for and against each one.
Where to take this next
The dataset points to specific follow-up questions rather than a single conclusion.
Check freedom-to-operate against the leader's claim scope
With 21 records concentrated in one assignee, any new filing on core trajectory-prediction control logic should be checked against that portfolio first, not just the most-cited records.
Explore assignee claims in Eureka →Watch the 2025-2026 numbers fill in
Because publication lags filing by roughly 18 months, the apparent tail-off after 2023 is an artefact of the data cut-off, not a real decline. Revisit the trend once later filings publish.
Track filing trends in Eureka →Probe the under-claimed branches directly
Standalone AI-model claims and traffic-signal-conditioned prediction show thinner coverage than the control-layer mainstream. A narrowly drafted claim there may face less prior art.
Search white space in Eureka →Common questions on this landscape
The dataset ranks 76 companies by record count, with the leading assignee holding 21 records and fifth place holding 9. The top 5 assignees combined account for 28.9% of all 211 records in scope, and the top 10 combined reach 43.6%. That leaves more than half the field spread across a long tail of lower-volume filers, so a single company does not control the space outright.
Filings grew from 11 in 2017 to a peak of 47 in 2023, and the most recent complete three-year window shows +8% growth from 2021 (26 records) to 2024 (28 records). Counts for 2025 and 2026 appear lower, but that reflects publication lag of roughly 18 months rather than an actual drop in filing activity. Treat any apparent recent decline as incomplete data, not a trend.
B60W, the hybrid and joint vehicle control classification, appears in 65.4% of the 211 records, making it the dominant class by a wide margin. G06N, covering AI-model computing, follows at 42.7%, with G08G traffic control systems, G06V image recognition and G05D non-electric variable control each covering smaller but notable shares. Because records can carry multiple IPC classes, these percentages overlap rather than sum to 100%.
Based on the IPC composition, claims that isolate a prediction model on its own, independent of the control action it feeds into, are less common than control-layer claims under B60W. Traffic-signal-conditioned trajectory prediction and cut-in intent classification from image input alone also show thinner representation relative to the mainstream control-and-prediction combination claims. These are starting points for scoping, not a guarantee of allowability — a full prior-art search is still required.
The United States leads by a wide margin with 122 filings among the tracked receiving offices, ahead of the European Patent Office at 27 and WIPO/PCT at 21. China, Germany and India each show single-digit-to-low-double-digit counts by comparison. This distribution suggests the US is the primary jurisdiction where competitive claim scope is being contested for cut-in and trajectory prediction technology.
Research Autonomous Driving — Cut-In Vehicle Trajectory Prediction Patent Landscape in depth with Eureka
Go past this page: query the whole autonomous driving — cut-in vehicle trajectory prediction patent landscape corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company’s registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.