Cobot Force & Tactile Sensing Patent Landscape 2026
Neuromeka holds the dominant position in cobot force and tactile sensing, with the top five filers together accounting for 41% of the hundred largest filers’ combined output. Filing volume reached its peak around 2022 and has since plateaued, signalling a maturing but still active competitive field.
Neuromeka leads a moderately concentrated field with a clear tier gap
Neuromeka sits at the top of the applicant ranking with 16 patent families, followed by BAE Systems with 11 and Fanuc with 9. The top three alone represent a substantial share of the most active filers, establishing a clear leading tier.
The top five filers — Neuromeka, BAE Systems, Fanuc, Shenzhen Yuejiang Technology, and Hanwha Robotics — together account for 41% of the hundred largest filers’ combined total. Below that tier, activity disperses rapidly across a long tail of single- and two-family filers spanning industrial robotics firms, university labs, and defence integrators.
| # | Applicant | Patent families | Share |
|---|---|---|---|
| 1 | Neuromeka | 16 | |
| 2 | BAE Systems PLC | 11 | |
| 3 | Fanuc Corporation | 9 | |
| 4 | Shenzhen Yuejiang Technology Co., Ltd. | 5 | |
| 5 | Hanwha Robotics Corporation | 4 | |
| 6 | Nachi-Fujikoshi Corp. | 4 | |
| 7 | Koninklijke Philips N.V. | 4 | |
| 8 | Chengdu CRP Robot Technology Co., Ltd. | 3 | |
| 9 | Thomson Industries, Inc. | 3 | |
| 10 | Rethink Robotics, Inc. | 2 |
| # | Applicant | Patent families | Share |
|---|---|---|---|
| 11 | Northeastern University (China) | 2 | |
| 12 | Cymechs | 2 | |
| 13 | Siasun Robot & Automation Co., Ltd. | 2 | |
| 14 | Digital Surgery Systems, Inc. | 2 | |
| 15 | Shenyang Institute of Automation, Chinese Academy of Sciences | 2 | |
| 16 | Zhejiang University | 2 | |
| 17 | CEA (Commissariat à l’Energie Atomique et aux Energies Alternatives) | 2 | |
| 18 | Wipro Limited | 2 | |
| 19 | Ajinextek Co., Ltd. | 1 | |
| 20 | Jiayi Xiaoan (Shanghai) Robot Technology Co., Ltd. | 1 |
Neuromeka’s lead, combined with the new-entrant momentum signals for Shenzhen Yuejiang Technology and Nachi Fujikoshi, suggests the leading tier is not yet static — challengers with focused portfolios are closing the gap, and the identity of the top five could shift within the next filing cycle.
The most recent 18–24 months of filings are subject to publication lag and are likely under-counted; trend readings for 2024–2026 should be treated as provisional. Longer-window growth, applicant concentration, and technology-route coverage are therefore more reliable signals than the latest-year bar alone.
Activity plateaued near the 2022 peak; manipulator mechanics dominate the technology mix
Two charts together capture where this field stands: the annual filing trend reveals a field that built momentum through 2022 and has since held near that level, while the IPC composition shows how heavily patenting concentrates in robotic mechanics versus adjacent sensing and control disciplines.
Annual filing trend
Filings grew steadily from 2017 through a 2022 peak of 15 families, then eased to 14 in 2023 and 12 in 2024. The 2025 and 2026 counts are materially under-counted due to publication lag and should not be read as decline. The multi-year window still shows a 14% recent growth figure, consistent with a field that is maturing rather than contracting.
↗ Hover for values · click a bar to ask EurekaTechnology composition
B25J (Manipulators & robots) accounts for the large majority of records, reflecting that most applicants integrate force and tactile sensing directly into robot arm and joint design. G05B (Control & regulating systems) is the next largest branch, followed by G01L (Force & pressure measurement) and A61B (Diagnosis & surgery) — both materially smaller, indicating that stand-alone sensing instrumentation and medical-robotics sub-fields remain under-served relative to the core manipulator branch.
↗ 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 | Human-collaborative robot system | 42 |
| 2 | 一种双臂自碰撞检测方法和计算机可读存储介质 | 38 |
| 3 | Robot system | 33 |
| 4 | 一种具有力感知功能的协作机器人关节 | 20 |
| 5 | 协作机器人、碰撞检测系统和方法、存储介质、操作系统 | 19 |
| 6 | 基于力矩传感器的协作机器人驱控一体化控制系统 | 17 |
| 7 | Apparatus and Method for Collision Detection for C… | 17 |
| 8 | 一种七自由度协作机器人动力学建模与辨识方法 | 14 |
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 structure means for R&D investment decisions
The combination of a maturing filing curve, moderate concentration, absent formal co-development networks, and a US–China–EPO filing split defines both the risk profile and the entry opportunities in this space.
Field is plateauing near its 2022 peak
Annual filing volume peaked around 2022 and has since held near that level rather than accelerating further. The multi-year window still shows positive recent growth of 14%, so the field has not entered decline, but the era of rapid annual expansion has passed. New entrants should expect to compete against an established body of prior art concentrated in B25J manipulator mechanics.
Lifecycle: MaturityModerate concentration with an active challenger tier
The top five filers hold 41% of the hundred largest filers’ combined output, placing this field in a moderately concentrated zone — dominated but not monopolised. Applicants ranked sixth through twentieth each hold two to four patent families, indicating that a focused R&D programme can reach the second tier without requiring a massive filing budget. The tail of single-family filers, including universities and start-ups, adds competitive unpredictability.
Concentration: ModerateNo formal co-applicant relationships detected
Evidence of co-filing partnerships is absent from the current corpus. All identified applicants appear to be filing independently, which means no established consortium or cross-licensing alliance is visibly shaping the field. This represents both a risk (no clear standard-setting coalition) and an opportunity for a well-positioned player to initiate collaborative filings that could anchor an emerging standard.
Collaboration: None detectedUS and China are co-leading jurisdictions; EPO is the key third market
The United States leads with 35 records, followed closely by China with 33, and Europe (EPO) with 19. South Korea contributes 8 records, reflecting Hanwha Robotics and domestic activity. WIPO PCT filings total 6, indicating selective global prosecution strategies. A patent programme that omits any of the three leading jurisdictions leaves meaningful commercial coverage gaps, particularly given the geographic spread of the top applicants.
Geography: US · CN · EPOGo 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 leads on manipulator integration; BAE Systems anchors the defence and control route
The top two filers differ markedly in sectoral emphasis: Neuromeka concentrates entirely within B25J manipulator subclasses, while BAE Systems extends meaningfully into G05B control systems, reflecting a defence-oriented systems-integration approach.
Neuromeka
Neuromeka holds 16 patent families — the largest portfolio in the corpus — with all activity concentrated in B25J manipulator and robot subclasses, particularly B25J 9, B25J 5, and B25J 19. Momentum data flags Neuromeka as a new entrant that has rapidly accumulated its position, suggesting a compressed but intensive filing campaign rather than a long-term incumbent trajectory. This makes the portfolio worth watching for continuation and divisional activity.
families: 16BAE Systems
BAE Systems holds 11 patent families and is the only top-two applicant with meaningful coverage in G05B 19 (Control & regulating systems) alongside its B25J 9 and B25J 13 manipulator filings. This dual-branch positioning reflects a systems-integration emphasis consistent with defence and industrial automation applications. BAE Systems’ presence signals that cobot force sensing is being pursued in safety-critical, regulated environments beyond conventional industrial robotics.
families: 11| Applicant | Recent (3 yrs) | Trend |
|---|---|---|
| Neuromeka | 7 | ▲ new entrant |
| Shenzhen Yuejiang Technology Co., Ltd. | 5 | ▲ new entrant |
| Nachi-Fujikoshi Corp. | 4 | ▲ new entrant |
| Thomson Industries, Inc. | 3 | ▲ new entrant |
Under-served branches adjacent to the dominant manipulator core
Four IPC branches sit at materially lower coverage relative to B25J, each representing an area where the patent record is sparse but the technical connection to cobot force and tactile sensing is direct. These are observations of relative sparsity; whether they constitute viable entry points depends on business context and freedom-to-operate analysis.
G01L · Force & pressure measurement
Only 7 records fall under G01L despite force and pressure measurement being foundational to the sensing stack described in the corpus. This sparsity suggests that most applicants are protecting sensing capability through the mechanical integration claim (B25J) rather than at the transducer or measurement-instrument level. For a sensing-component supplier or a firm developing standalone torque sensors for cobot joints, this branch offers relatively uncontested claim space with a clear technical rationale — provided freedom-to-operate analysis is conducted against the denser B25J prior art.
Search this in Eureka →G06N · AI-based computing models
Only 3 records appear under G06N, despite the growing use of machine-learning models for contact detection, impedance estimation, and tactile signal interpretation in collaborative robots. Top-cited works in the corpus reference collision detection and dynamics identification — both domains where AI inference is increasingly applied. The low G06N count suggests that applicants are either not claiming the AI layer explicitly or are bundling it within B25J system claims, leaving the algorithmic sensing layer as a relatively sparse branch for a software or AI-focused filer to address directly.
Search this in Eureka →How leading applicants differ by IPC technology route
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 | Emerging · 1 | Moderate · 6 | Absent | Absent |
| BAE Systems PLC | Strong · 11 | Strong · 6 | Emerging · 1 | Moderate · 5 | Absent |
| Fanuc Corporation | Strong · 7 | Strong · 5 | Moderate · 2 | Moderate · 2 | Absent |
| Shenzhen Yuejiang Technology Co., Ltd. | Strong · 5 | Strong · 5 | Absent | Absent | Strong · 5 |
| Hanwha Robotics Corporation | Strong · 4 | Moderate · 2 | Moderate · 2 | Absent | Absent |
| Koninklijke Philips N.V. | Strong · 4 | Absent | Absent | Strong · 3 | Absent |
| Chengdu CRP Robot Technology Co., Ltd. | Absent | Strong · 3 | Absent | Absent | Strong · 3 |
Frequently asked questions
Neuromeka leads with 16 patent families, ahead of BAE Systems with 11 and Fanuc with 9. Neuromeka’s portfolio is concentrated entirely in B25J manipulator and robot subclasses.
Annual filings peaked around 2022 at 15 families and have since held near that level. The most recent 18–24 months are subject to publication lag, so 2025 and 2026 counts should be treated as provisional rather than evidence of decline. The multi-year window shows a recent growth figure of 14%.
The United States leads with 35 records, followed by China with 33 and Europe (EPO) with 19. South Korea contributes 8 records. A comprehensive filing strategy should cover all three leading jurisdictions to match the geographic spread of the main applicants.
No co-applicant relationships are detected in the current corpus. All identified filers appear to be filing independently, meaning no visible standard-setting alliance or formal co-development programme is currently shaping the landscape.
G01L (Force & pressure measurement) has only 7 records, G06N (AI-based computing models) has 3, H02K (Electric motors & generators) has 3, and A61B (Diagnosis & surgery) has 5 — all materially smaller than the dominant B25J branch. These represent areas of relative sparsity rather than confirmed opportunities.
Momentum data flags Neuromeka, Shenzhen Yuejiang Technology, Nachi Fujikoshi, and Thomson Industries as new entrants with recent filing activity, each accumulating their positions rapidly rather than through long-term incremental growth. A very large momentum jump from a small prior base should be interpreted accordingly.
Map your own cobot sensing patent 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.