Onboard Charger AI Patents: Who Leads, Where the Gaps Are 2026
- Filing has plateaued, not accelerated. the trend rises from zero in 2017 to a peak of 14 families in 2024, but the 2022 midpoint of 13 shows growth has flattened rather than compounded.
- Vehicle propulsion claims dominate over power-electronics claims. B60L accounts for 26 of the underlying IPC counts, more than double H02J's 13, meaning most filers frame onboard charger intelligence as a vehicle-control problem, not a grid-interface one.
- The strongest applicant relationship is a co-filing pair, not a lone leader. Hyundai Motor Company and Kia together account for the single strongest co-assignee pairing in the dataset, at 5 shared families.
What this patent landscape covers
This landscape tracks patent families where onboard charger hardware is claimed together with a machine-learning control layer, a fault-diagnosis routine, or an adaptive charging-optimisation method. The search spans 2015 to mid-2026 and returns 60 published families, a small enough set that individual filings move the ranking, and large enough to show where claim density has actually formed. Most records sit at the intersection of vehicle propulsion control and power electronics, rather than in a standalone AI subclass.
Because publication lags filing by roughly eighteen months, the 2025 and 2026 counts in any trend chart are undercounts of what has actually been filed; treat the most recent one or two bars as a floor, not a ceiling.
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 60-family dataset: how filing volume has moved year over year, and which IPC subclasses carry the claim weight.
A plateau, not a ramp
Filings climbed from zero in 2017 to a peak of 14 in 2024. The 2022 midpoint of 13 sits close to that peak, which means the growth curve flattened well before the most recent data cut-off rather than accelerating into it.
Vehicle control claims outweigh power-electronics claims
B60L (electric vehicle propulsion) leads with 26 of the IPC counts, ahead of H02J (power supply and grid systems) at 13 and B60W (hybrid/joint vehicle control) at 11. H05K, G01R and G05B each sit at 8-9, showing that measurement, control-loop and packaging claims are present but thinner than the propulsion-control core.
Shares are the percentage of the 60 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on Onboard Charger AI and Machine Learning with Eureka
This page is one run against one query. Ask Eureka your own question about onboard charger ai and machine learning and every answer comes back with the patent numbers behind it.
Try EurekaThe records that anchor this landscape
Charging control method and system for battery of vehicle — US20200180603A1
A charging control method for a battery of a vehicle charges a high-voltage battery even when a current sensor fails in the eco-friendly vehicle. The method includes performing a fault diagnosis of a current sensor before starting to charge the battery and determining whether the current sensor has failed from the fault diagnosis result. Constant current (CC) charging control is then performed with a constant current in response to determining that the current sensor has failed.Filed by Hyundai Motor Company, published 2020-06-11.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US20220089237A1 | Robotic production environment for vehicles | 90 |
| 2 | WO2021255445A2 | Robotic production environment for vehicles | 11 |
| 3 | US20190248242A1 | Fault diagnosis system of power converter for electric vehicle | 9 |
| 4 | US20200180603A1 | Charging control method and system for battery of vehicle | 5 |
| 5 | US20230075541A1 | Terminal transport vehicle | 3 |
| 6 | US20190308506A1 | Vehicle activation system | 2 |
| 7 | KR101459923B1 | Fault diagnosis system and method for collant switching device for vehicle | 2 |
| 8 | US20260029360A1 | Electrified vehicle battery combination electrical/ fluid connector | 1 |
| 9 | US20250062620A1 | On-board charger for electric vehicle, relay control method thereof, and bidirectional charging system for el… | 1 |
| 10 | US20240278869A1 | Vehicle With Distinctly Activated Controllers | 1 |
Citation counts favour older filings that have had more time to accumulate references; treat them as a signal of influence within this searched corpus, not as a ranking of current technical importance.
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
Reading the trend, the IPC split and the office data together points to a field that is claim-dense in vehicle-control terms but has not moved decisively into grid-side or measurement-side AI claims.
Growth has flattened, not stalled
The corpus grew from zero filings in 2017 to a peak of 14 in 2024, but the near-identical 2022 count of 13 shows the growth curve levelled off two years before the peak rather than climbing steadily into it. Any 2025-2026 figures are undercounts given publication lag, so the true recent trajectory may look flatter still or slightly higher once later filings publish.
Onboard charger AI is framed as a vehicle problem
B60L (vehicle propulsion) carries roughly double the IPC weight of H02J (power supply and grid systems). Filers are predominantly claiming charger intelligence as part of the vehicle's control architecture rather than as a grid-facing power-electronics innovation, which shapes where prior art will actually collide with a new filing.
US filings lead by a wide margin
United States receiving-office counts nearly double the next-largest office (EPO). India and Germany each sit in single digits, and Australia trails at 3, indicating that defensive and enforcement filing strategy in this niche is still concentrated in US and European offices rather than spread evenly across major EV markets.
Group-level filing, not solo dominance
The single strongest co-assignee relationship in the dataset belongs to an affiliated pair rather than one company filing alone, pointing to shared R&D and joint patent strategy within an automotive group rather than a single standout innovator.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to onboard charger ai and machine learning, with the prior art for and against each one.
| Assignee | Co-assignee | Shared families |
|---|---|---|
| Hyundai Motor Company | Kia Corporation | 5 |
The strongest co-assignee pairing in the dataset links two companies under common corporate ownership, which is typical of automotive groups that centralise R&D across sister brands before splitting filings by entity.
The assignee landscape
Filing activity spans established automakers and their technology arms, with no single company showing sustained year-over-year growth in the latest reported period.
No assignee is currently accelerating
Every assignee tracked for recent-year momentum, including the automotive groups with the deepest filing history in this set, shows zero families in the latest reported year, and one shows a -100% year-over-year drop. Given the roughly eighteen-month publication lag, this likely understates true recent activity rather than confirming a genuine pullback.
Affiliated brands file jointly
The strongest co-assignee pairing in the corpus sits between two affiliated Korean automakers, consistent with shared engineering teams producing charger fault-diagnosis and control filings that get assigned to both entities.
A compact, still-forming field
With 60 total families spread across eight IPC subclasses, no single assignee or subclass has run away with the space. That leaves room for a newly filed claim to land in a genuinely uncrowded corner if it targets the thinner subclasses rather than the dense B60L core.
| Assignee | Recent year | YoY |
|---|---|---|
| BYD Company Limited | 0 | — |
| Hyundai Motor Company | 0 | — |
| Mitsubishi Motors Corporation | 0 | — |
| Kia Corporation | 0 | — |
| Ford Global Technologies, LLC | 0 | -100% |
| Rivian Automotive, Inc. | 0 | — |
| Yinwang Intelligent Technology Co., Ltd. | 0 | -100% |
| Huawei Digital Power Technologies Co., Ltd. | 0 | -100% |
Where to take this analysis
The dataset points to a field that has plateaued in volume but is still open in specific technical corners. The next steps depend on whether the goal is freedom-to-operate, portfolio strategy, or spotting a filing gap.
Check freedom-to-operate against the propulsion-control core
With B60L carrying the heaviest IPC weight, any new onboard charger AI filing that touches vehicle-side control logic should be checked against that dense cluster before drafting claims.
Run a freedom-to-operate check in EurekaMap the affiliated-filer pattern before assuming a single owner
The strongest co-assignee pairing in this set belongs to two affiliated automakers, so ownership and licensing questions may need to trace corporate group structure rather than a single assignee record.
Trace assignee relationships in EurekaDraft toward the thinner subclasses
G01R, G05B and H01M each sit well below B60L in filing count, suggesting more room for a first claim in measurement, control-loop, or battery-interface framing of onboard charger intelligence.
Explore white space in EurekaCommon questions about onboard charger AI patents
This dataset tracks 60 published patent families filed between 2015 and mid-2026 that combine onboard charger hardware with machine-learning control, fault diagnosis, or adaptive charging-optimisation claims. That is a modest, still-forming field rather than a saturated one. Because publication typically lags filing by around eighteen months, the true current total is likely somewhat higher than what has been published and indexed so far.
Filing in this space is led by established automakers and their in-house technology arms rather than a single dominant player. The strongest documented relationship is a co-assignee pairing between two affiliated Korean automakers, Hyundai Motor Company and Kia, who share five families, pointing to centralised group-level R&D rather than one company running away with the category. No assignee tracked in the recent-year momentum data shows growth in the latest reported year, though this should be read against the publication lag rather than as a genuine slowdown.
The filing trend rose from zero in 2017 to a peak of 14 families in 2024, but the 2022 midpoint already sat at 13, just one below the eventual peak. That pattern shows the growth curve flattened two years before the peak rather than climbing steadily toward it, which is closer to a plateau than an acceleration. Given the roughly eighteen-month gap between filing and publication, the 2025 and 2026 figures almost certainly understate real activity and should not be read as a decline.
US20200180603A1, assigned to Hyundai Motor Company and published 2020-06-11, covers a charging control method that keeps charging a vehicle's high-voltage battery even when the current sensor used for charge control has failed. It works by running a fault-diagnosis check on the current sensor before charging starts, then switching to constant-current charging control if that sensor is found to have failed. Anyone designing a charging-control system that includes current-sensor fault detection paired with a fallback constant-current charging mode should review this claim scope closely, since it sits directly on that combination.
Within this dataset, the heaviest claim density sits in B60L (vehicle propulsion, 26 of the IPC counts) and H02J (power supply and grid systems, 13). Subclasses tied to measurement (G01R, 8), control-loop regulation (G05B, 8), and battery-cell interfacing (H01M, 5) carry noticeably fewer filings. That gap suggests more room for new claims framed around current-sensor prediction, PCB-level fault sensing, or grid-side adaptive optimisation than around vehicle-control logic generally, where B60L filings are already dense.
Research Onboard Charger AI and Machine Learning in depth with Eureka
Go past this page: query the whole onboard charger ai and machine learning 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.