Collaborative Robot Safety & Control Patent Landscape
NEUROMEKA holds the largest position with 17 patent families, and the field is still expanding on a multi-year basis, though annual volume has eased from its 2019 peak and plateaued near that level. The United States and China are the dominant filing jurisdictions, and B25J manipulator technology accounts for the overwhelming share of technical activity.
NEUROMEKA leads a moderately concentrated field with a clear tier gap to challengers
NEUROMEKA ranks first with 17 patent families, ahead of BAE Systems PLC at 11 and Fanuc Ltd at 9, giving the top three a meaningful lead over the rest of the field.
The top five filers together account for 32% of the hundred largest filers’ combined total, indicating moderate concentration: a single dominant player has not locked up the space, but a recognizable first tier has formed.
| # | Applicant | Patent families | Share |
|---|---|---|---|
| 1 | NEUROMEKA | 17 | |
| 2 | BAE Systems PLC | 11 | |
| 3 | Fanuc Ltd | 9 | |
| 4 | Mantis Robotics Inc | 7 | |
| 5 | KUKA Systems GmbH | 7 | |
| 6 | French Alternative Energies and Atomic Energy Commission (CEA) | 6 | |
| 7 | Shenzhen Yuejiang Technology Co Ltd | 5 | |
| 8 | Nachi-Fujikoshi Corp | 5 | |
| 9 | Hanwha Robotics Corp | 4 | |
| 10 | Siasun Co Ltd | 4 |
| # | Applicant | Patent families | Share |
|---|---|---|---|
| 11 | Chengdu CRP Robot Technology Co Ltd | 4 | |
| 12 | Koninklijke Philips NV | 4 | |
| 13 | Shenyang Institute of Automation, Chinese Academy of Sciences | 3 | |
| 14 | Thomson Industries Inc | 3 | |
| 15 | Rethink Robotics Inc | 2 | |
| 16 | Northeastern University (China) | 2 | |
| 17 | Cymechs | 2 | |
| 18 | Shanghai Jieka Robot Technology Co Ltd | 2 | |
| 19 | Digital Surgery Systems Inc | 2 | |
| 20 | Shandong Siasun Industrial Software Research Institute Co Ltd | 2 |
The positions of established industrial robotics players such as Fanuc and KUKA alongside specialist entrants like NEUROMEKA and Mantis Robotics suggest the field attracts both incumbents defending core technology and focused newcomers building differentiated safety and control IP.
The most recent 18–24 months of filings are subject to publication lag and likely under-represent actual activity; conclusions about very recent momentum should be treated with caution. Longer-window growth, applicant concentration, and technology-route coverage are therefore more reliable signals than the latest-year bar alone.
Filing volume has plateaued near its 2019 peak; B25J manipulator IP dominates the technology mix
The annual trend and technology composition charts together reveal a field that surged through 2019, stabilised at a high level, and remains almost entirely anchored in manipulator and motion-control IP.
Annual filing trend
Filings jumped from 7 in 2017 to a first peak of 21 in 2019, dipped to 12 in 2020, then recovered to a second 21-record year in 2022 before easing to 20 in 2023 and 15 in 2024. The 2025–2026 figures are incomplete due to publication lag and should not be read as a decline.
↗ Hover for values · click a bar to ask EurekaTechnology composition
B25J (Manipulators & robots) is the dominant class by a wide margin, reflecting the core hardware and motion-control focus of the field. G05B (Control & regulating systems) is the only other class with meaningful presence; all remaining branches — including force sensing, AI models, and surgical applications — hold single-digit counts, pointing to adjacent areas with limited current coverage.
↗ Hover for values · click a bar to ask EurekaHighly cited patent families surfaced by the query
Citation-heavy patent families returned by the query. Use this section as citation context, not as a curated list of the most topic-specific patents.
Collaborative robot having collision detection fun…
The present invention provides a collaborative robot comprising: a main body robot; an additional shaft robot that moves the main body robot along the additional shaft; and a processor unit that transmits and receives signals to and from the main body robot and the additional shaft robot, wherein the processor unit comprises: a receiving unit that obtains a… (excerpt from the patent abstract)
| # | Patent | Citations |
|---|---|---|
| 1 | 一种协作机器人模块化串联关节 | 50 |
| 2 | 一种协作机器人手眼关系自动标定装置及方法 | 42 |
| 3 | Human-collaborative robot system | 42 |
| 4 | 一种双臂自碰撞检测方法和计算机可读存储介质 | 37 |
| 5 | Robot system | 33 |
| 6 | 一种用于协作机器人关节的柔顺控制方法 | 22 |
| 7 | 一种具有力感知功能的协作机器人关节 | 20 |
| 8 | 协作机器人、碰撞检测系统和方法、存储介质、操作系统 | 19 |
Ranked by total forward citations. Citation counts favour older and broadly cited patent families, and broad or adjacent patents may appear when they match the search scope. Treat this section as citation context, not as a curated list of the most topic-specific patents. Some patent titles may be shown in their original, non-English language where an accurate translation could not be guaranteed.
What the patent structure means for R&D investment decisions
The combination of a plateaued filing trend, moderate concentration, and a dominant-but-narrow technology class creates both risks and entry points for new R&D programs.
Field at plateau: established in core areas, open at edges
Annual filings have plateaued near their peak level rather than continuing to climb, signalling that the core B25J manipulator-safety space is maturing. Fundamentally new filings in mainstream collision detection and torque-based safety are increasingly likely to face prior-art density. R&D investment is better directed at adjacent branches where coverage remains sparse.
Lifecycle: PlateauModerate concentration leaves room for focused challengers
With the top five filers holding 32% of the hundred largest filers’ combined total, no single entity has achieved lock-in. The gap between NEUROMEKA at 17 patent families and the next tier (BAE Systems at 11, Fanuc at 9) is real but not prohibitive. A targeted filing program in an under-served branch could establish a defensible position without directly competing with the leaders’ core portfolios.
Moderate concentrationNo co-applicant activity detected in this corpus
The collaboration evidence for this topic is pending — no co-applicant pairs were identified in the current dataset. This absence may indicate that players are protecting safety and control IP independently rather than through joint ventures or research consortia, or it may reflect the relatively small total corpus size. Either way, there is no established collaborative ecosystem to leverage or compete against.
Solo filing patternUS and China dominate; Europe and PCT channels are secondary
The United States leads at 48 patent records, followed closely by China at 47, and Europe (EPO) at 22. WIPO PCT filings total 11, with South Korea at 8 and India at 4. The near-parity between the US and China suggests competitive pressure from Chinese robotics firms alongside Western incumbents. Applicants seeking broad protection should prioritise US, CN, and EP validation.
US/CN parityGo beyond the landscape: Eureka’s TRIZ Solution agent breaks down an R&D problem and returns patented concept solutions, each with a technical approach and cited patent & literature evidence.
Co-filing pairs, ranked by the number of jointly-filed patent families.
NEUROMEKA and BAE Systems lead; new entrants are accelerating
The top two players differ in technology emphasis: NEUROMEKA is concentrated in manipulator kinematics and safety monitoring, while BAE Systems extends its portfolio into active control systems. Several applicants identified as new entrants in the momentum data are already among the top five by family count.
NEUROMEKA
NEUROMEKA holds 17 patent families — the largest portfolio in this corpus — concentrated across B25J 9 (manipulator programming and control), B25J 5 (mobile or reconfigurable manipulators), and B25J 19 (safety and sensing attachments). Its momentum is flagged as a new entrant trajectory, meaning its current position was built rapidly from a small prior base rather than through decades of incremental accumulation.
families: 17BAE Systems PLC
BAE Systems PLC ranks second with 11 patent families, emphasising B25J 9 manipulator control, B25J 13 (hand and end-effector control), and G05B 19 (programmable control systems) — the only top-two player with meaningful coverage in G05B. This broader control-systems footprint positions BAE as the strongest challenger in safety-critical programmatic control, reflecting its defence and aerospace application context.
families: 11| Applicant | Recent (3 yrs) | Trend |
|---|---|---|
| NEUROMEKA | 8 | ▲ new entrant |
| Mantis Robotics Inc | 5 | ▲ new entrant |
| Shenzhen Yuejiang Technology Co Ltd | 5 | ▲ new entrant |
| Nachi-Fujikoshi Corp | 4 | ▲ new entrant |
Force sensing, AI inference, and surgical robotics are under-served adjacent branches
Beyond the dominant B25J class, several branches hold single-digit patent-record counts despite clear technical relevance to cobot safety — pointing to areas where early filing could establish a differentiated position.
G01L · Force & pressure measurement
With only 8 patent records, force and pressure measurement is the largest adjacent branch yet one of the thinnest relative to its technical importance: tactile and torque-sensing is fundamental to human-robot collision avoidance and compliant control. Existing activity comes mostly from filings that also cover B25J, meaning dedicated G01L-primary sensing IP is genuinely sparse. Teams developing novel force-sensor architectures or skin-based distributed sensing could file here with limited prior-art competition.
Search this in Eureka →G06N · Computing based on AI models
Only 4 patent records sit in G06N, despite growing industry interest in learned safety policies, uncertainty-aware motion planning, and reinforcement-learning-based speed and separation monitoring. The scarcity is notable given that AI-driven cobot control is a stated R&D direction for several top players. Organisations with capability in embedded inference or on-robot learning models face a relatively open landscape if they can tie claims directly to safety-critical cobot control rather than general robotics AI.
Search this in Eureka →How leading applicants differ across technology routes
Route coverage across the main technology branches in the current evidence set.
| Player | B25J 9 · Manipulators & robots | B25J 13 · Manipulators & robots | B25J 19 · Manipulators & robots | G05B 19 · Control & regulating systems | B25J 17 · Manipulators & robots |
|---|---|---|---|---|---|
| NEUROMEKA | Strong · 16 | Absent | Moderate · 7 | Absent | Absent |
| BAE Systems PLC | Strong · 11 | Strong · 6 | Emerging · 1 | Moderate · 5 | Absent |
| Mantis Robotics Inc | Strong · 7 | Strong · 7 | Strong · 4 | Absent | Absent |
| Fanuc Ltd | Strong · 7 | Strong · 5 | Moderate · 2 | Moderate · 2 | Absent |
| Shenzhen Yuejiang Technology Co Ltd | Strong · 5 | Strong · 5 | Absent | Absent | Strong · 5 |
| KUKA Systems GmbH | Strong · 7 | Moderate · 2 | Strong · 5 | Absent | Absent |
| French Alternative Energies and Atomic Energy Commission (CEA) | Strong · 6 | Moderate · 3 | Absent | Absent | Absent |
Frequently asked questions
The current corpus contains 135 patent families in scope. The United States leads as the primary filing office with 48 patent records, followed closely by China at 47.
NEUROMEKA holds the largest portfolio with 17 patent families, ahead of BAE Systems PLC at 11 and Fanuc Ltd at 9. NEUROMEKA built this position rapidly — its momentum is characterised as a new entrant trajectory from a small prior base.
On a multi-year basis the field has expanded, with a 12% recent-window growth figure. However, annual filing volume has plateaued near its 2019 peak rather than continuing to climb. The 2025–2026 data points are incomplete due to publication lag and should not be interpreted as a decline.
B25J (Manipulators & robots) is the dominant class by a wide margin, accounting for the large majority of patent records. G05B (Control & regulating systems) is the next most active class, but at a substantially lower level.
Yes. G01L (Force & pressure measurement) has only 8 patent records despite being technically central to collision avoidance. G06N (AI models) has only 4 records, and A61B (surgical applications) has 5 — all sparse relative to their relevance. These are adjacent branches where early, targeted filing faces limited prior-art density.
No co-applicant pairs were identified in the current dataset. Applicants appear to be protecting safety and control IP independently, with no established co-filing consortium or joint-venture filing pattern evident in this corpus.
Map your own collaborative robot safety landscape in minutes
Join 18,000+ innovators using PatSnap Eureka to map any technology landscape: search 2B+ patents and papers, surface key assignees, and generate a report like this in minutes.
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.