Digital Twin and Robot Simulation Patents: Leaders, Trends & Gaps 2026
- Filing peaked in 2020 at 21 families, then flattened toward the midpoint year rather than continuing to climb — this is not a technology still accelerating on paper.
- G06F dominates at 80 of 100 records, while B25J (manipulators & robots) sits at just 16 — a lot of this art is data-processing scaffolding around simulation, not robot mechanics itself.
- No single assignee shows filings in the latest year, including the most active historical filers — a signal that the recorded activity is aging faster than new entrants are replacing it.
What this patent set actually covers
This landscape covers 100 patent families filed between 2015 and 2026 at the intersection of digital twin platforms, robot simulation and virtual commissioning, narrowed to filings that explicitly claim technical mechanisms such as physics engines, sim-to-real transfer, model fidelity or real-time synchronization. The IPC scope spans G05B17 (control/regulating system models), G06F30 (computer-aided design and simulation) and B25J9 (manipulator control), which is why the composition below leans toward general-purpose digital simulation infrastructure rather than robot hardware.
Filing activity is concentrated in the United States and Europe, with India and WIPO PCT filings also present, pointing to a field still being fought over primarily through national and regional filing strategy rather than settled global standards.
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
The two views below show when this field was built out and which parts of the IPC map carry the claim density — read together, they show a field that grew in a burst and then plateaued, concentrated in software-side simulation rather than mechanical robotics.
A 2020 peak, then a flattening curve
Filings rose from zero in 2017 to a peak of 21 in 2020, then eased to 12 at the 2022 midpoint. Because publication typically lags filing by roughly 18 months, the final one or two years in this chart will always look thinner than they eventually turn out to be — but the shape from 2020 to 2022 already shows deceleration, not just a reporting artefact.
Software simulation infrastructure outweighs robot mechanics
G06F (electric digital data processing) appears in 80 of 100 records and G05B (control & regulating systems) in 36, while B25J (manipulators & robots) appears in only 16. Healthcare informatics, business data processing and image recognition each register at 6 — thin but present, suggesting digital twin techniques are being pulled into adjacent domains rather than staying confined to industrial robotics.
Go deeper on Digital Twin and Robot Simulation with Eureka
This page is one run against one query. Ask Eureka your own question about digital twin and robot simulation and every answer comes back with the patent numbers behind it.
Try EurekaThe families other filers had to cite
Digital twin based method for monitoring behavior of passenger on escalator (US20240176933A1)
Filed by China Jiliang University, this 2024 filing constructs a digital twin virtual scene of an escalator, generates risky passenger behaviors inside a physics engine, and pairs that with a VGG19-based human pose recognition pipeline to classify passenger behavior in real time.It is a useful marker of where the field is heading: physics-engine-driven synthetic behavior generation paired with vision-based recognition, applied to a narrow public-safety use case rather than industrial robotics.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US20200285788A1 | Systems and methods for providing digital twin-enabled applications | 126 |
| 2 | US20210138651A1 | Robotic digital twin control with industrial context simulation | 62 |
| 3 | KR102297468B1 | Digital twin modeling apparatus and modeling method using the same | 54 |
| 4 | WO2020190272A1 | Creation of digital twin of the interaction among parts of the physical system | 25 |
| 5 | US20220156433A1 | Industrial network communication emulation | 23 |
| 6 | US20200276708A1 | Robot simulation engine architecture | 23 |
| 7 | US20220171907A1 | Creation of digital twin of the interaction among parts of the physical system | 23 |
| 8 | US20220075918A1 | Industrial automation process simulation for fluid flow | 20 |
| 9 | US20240176933A1 | Digital twin based method for monitoring behavior of passenger on escalator | 15 |
| 10 | US20230131458A1 | Probe sensor | 15 |
Citation counts here reflect influence within this searched corpus and skew toward older filings — a young, uncited family can still cover ground nobody else has claimed.
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 numbers imply for filing strategy
Three patterns in the data matter more than the raw counts: where filing volume sits by geography, how concentrated the technology composition is, and how thin the collaboration signal is between assignees.
The US is the primary battleground
Over half of all records in this set were filed at the USPTO, with Europe a distant second at 18 and India at 10. A freedom-to-operate check that skips the US misses the majority of the enforceable art here.
Claims cluster in data processing, not mechanics
Digital twin filings in this set are five times more likely to sit in general computing (G06F) than in manipulator/robot classes (B25J). Robot-hardware-specific simulation claims are comparatively rare and may be easier ground to stake out.
Almost no joint filing
The strongest co-assignee pairing in the dataset appears only twice, between Siemens entities. Beyond that, this is a field of solo filers rather than joint ventures or consortium-style IP.
The historical leaders have gone quiet
None of the most active named assignees show a filing in the most recent year captured. Given the ~18-month publication lag, some of this is reporting delay — but a full stop across every top filer simultaneously is still notable.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to digital twin and robot simulation, with the prior art for and against each one.
Who holds the ground, and what is still open
Filing activity is spread across industrial automation incumbents and a scatter of single-filing entrants, with no dominant joint-filing cluster to speak of.
Industrial automation names anchor the set
Names associated with industrial control and automation appear repeatedly across the ranking, filing primarily through the USPTO and, to a lesser extent, the EPO. Their filings tend to sit in the G05B and G06F overlap — control-system digital twins rather than pure robotics.
Simulation-native firms are a distinct cohort
Alongside legacy automation and electronics filers, at least one simulation-focused robotics company appears in the tracked set, distinct from the diversified industrial incumbents. Their presence signals that dedicated simulation vendors, not just automation conglomerates, are staking claims here.
Universities are filing narrow, applied claims
The representative 2024 filing on escalator passenger monitoring shows academic filers entering with tightly scoped, application-specific digital twin claims rather than broad platform claims — a different filing strategy from the industrial incumbents.
| Assignee | Recent year | YoY |
|---|---|---|
| Rockwell Automation Technologies, Inc. | 0 | — |
| Siemens AG | 0 | — |
| Dell Products L.P. | 0 | — |
| Watlow Electric Manufacturing Company | 0 | — |
| DUALITY ROBOTICS INC | 0 | — |
| Fujitsu Limited | 0 | — |
| TIMELIKE SYST INC | 0 | -100% |
| SIEMENS CORP | 0 | — |
Where to take this next
The dataset points to a field that grew fast, plateaued, and now has some clearly thinner branches next to a dense core — the next steps depend on whether you're clearing a product or hunting for filing room.
Run a freedom-to-operate check against the G06F/G05B core
Before shipping a digital twin or simulation product touching control systems, check claim scope against the densest cluster in this dataset rather than assuming robotics-specific classes are the only risk.
Explore this in EurekaModel the thinner branches for filing opportunity
B25J, G06Q, G06V, G16H and H04L all register at 16 or fewer records — worth a closer look if you have a claim that touches robot mechanics, healthcare or networked twins specifically.
Explore this in EurekaCommon questions about this landscape
The ranking in this dataset is led by a mix of industrial automation incumbents and diversified electronics firms, filing predominantly through the USPTO and EPO. No single assignee holds a dominant share of the 100 tracked families, and the strongest co-assignee link in the set — between Siemens entities — appears only twice, so this is a fragmented field rather than one controlled by a handful of firms. Newer entrants focused specifically on simulation software also appear in the recent-momentum data, alongside the legacy automation names.
Not on the evidence here: filings rose from zero in 2017 to a peak of 21 in 2020, then declined to 12 by the 2022 midpoint. Publication lag of roughly 18 months means the very latest years will always look artificially thin, but the drop-off between 2020 and 2022 predates that lag window and reflects a genuine slowdown. None of the top-ranked assignees show a filing in the most recent year tracked.
In practice the two overlap heavily in this dataset: filings tagged for digital twins frequently cite physics-engine and sim-to-real mechanisms that are identical to those in robot simulation filings, and both sit under the same IPC codes (G05B17, G06F30, B25J9). The clearer technical split is by IPC class rather than by label — G06F-heavy filings tend toward general computational simulation infrastructure, while the smaller B25J cluster is where claims specifically address manipulator or robot control.
Relative to the dense G06F and G05B core, sub-areas like manipulator-specific simulation (B25J, 16 records), healthcare-informatics-linked twins (G16H, 6 records) and networked/communication-layer synchronization (H04L, 6 records) show far thinner coverage. That doesn't guarantee those areas are technically easy, but it does mean fewer prior filings stand between a new claim and grant in those specific branches, based on this corpus.
Patent applications typically publish about 18 months after filing, so any year close to the data cut-off will understate true filing activity — it simply hasn't finished publishing yet. In this dataset the 2026 figure of 2 records should be read as a placeholder, not a real signal of decline; the more reliable read on momentum is the 2020-to-2022 drop, which is old enough to have fully published.
Research Digital Twin and Robot Simulation in depth with Eureka
Go past this page: query the whole digital twin and robot simulation 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.