Force-Torque Sensing Patent Landscape 2026
Force-Torque Sensing Patent Landscape in 2026
Force-torque sensing is in a growth phase, with filings expanding significantly on a multi-year basis, though annual volume has eased from its 2023 peak. The field is lightly concentrated with Dextrous Robotics Inc leading among a broad set of emerging entrants, and robotic manipulation (B25J) dominates the technology mix.
Dextrous Robotics leads a fragmented, early-stage field
Dextrous Robotics Inc holds the top position in the applicant ranking, followed by a cluster of filers each holding smaller shares — including Lu Bang Technology, Ocado Innovation, GM Global Technology Operations, and the Board of Trustees of the Leland Stanford Junior University.
The top five filers together account for 55% of the combined patent records held by the hundred largest filers, indicating moderate concentration at the top but a long tail of single-record participants — universities, startups, and industrial players — suggesting the field has not yet consolidated around a dominant incumbent.
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 1 | Dextrous Robotics Inc | 4 | |
| 2 | Lu Bang Technology Authorization Co., Ltd. | 2 | |
| 3 | Ocado Innovation Ltd | 2 | |
| 4 | GM Global Technology Operations LLC | 2 | |
| 5 | The Board of Trustees of the Leland Stanford Junior University | 2 | |
| 6 | Indian Institute of Technology Mandi | 1 | |
| 7 | Figure AI Inc | 1 | |
| 8 | Intrinsic Innovation LLC | 1 |
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 9 | Wisconsin Alumni Research Foundation | 1 | |
| 10 | Howmedica Osteonics Corp | 1 | |
| 11 | G PULLAIAH COLLEGE OF ENG & TECH | 1 | |
| 12 | Sony Group Corporation | 1 | |
| 13 | Trilobio Inc | 1 | |
| 14 | Cosmic Robotics Inc | 1 | |
| 15 | Worcester Polytechnic Institute | 1 |
Dextrous Robotics Inc’s position as sole leader, ahead of a tier of equal-sized challengers, implies the field is still open to displacement; no single organization has yet established the scale advantage that typically signals a locked-in technology standard.
The most recent one to two years of filing data are likely under-represented due to standard patent publication lag, so apparent slowdowns in 2024–2025 should not be read as a real decline in activity. Longer-window growth, applicant concentration, and technology-route coverage are therefore more reliable signals than the latest-year bar alone.
Multi-year growth, robot manipulation dominates the technology mix
Annual filing volume and the IPC technology breakdown together reveal a field that has accelerated since 2020 while remaining anchored in robotic manipulation hardware. Understanding both dimensions helps identify where activity is deepening and where adjacent branches remain sparse.
Annual filing trend
Filings were negligible through 2018–2022, then rose sharply in 2023 before easing slightly in 2024; 2025 shows a meaningful count but is likely understated by publication lag. The three-year recent window sits 300% above the prior three-year window, confirming genuine multi-year expansion even if annual volume has eased from its 2023 peak. Do not read the 2025–2026 figures as a decline.
↗ Hover for values · click a bar to ask EurekaTechnology composition
B25J (Manipulators and robots) is overwhelmingly dominant in the IPC mix, with G05B (Control and regulating systems) a secondary cluster and G01L (Force and pressure measurement), G06F (Electric digital data processing), and G06N (AI models) each represented by only a handful of records — flagging these as under-served adjacent branches relative to the hardware manipulation core.
↗ 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.
Robotic dense packing
A dynamic robotic packaging approach places a set of objects in a containment or shipping container based on dynamic, or real time evaluation and imaging of the set of objects for placement. Predefined object dimensions need not be provided, as an RGB-D or similar imaging provides a representation of each object in a set of objects for packaging. A sensed… (excerpt from the patent abstract)
| # | Patent | Citations |
|---|---|---|
| 1 | Force display master interface device for teleoper… | 126 |
| 2 | A system for controlling the position and orientat… | 65 |
| 3 | Rapid robotic imitation learning of force-torque t… | 55 |
| 4 | A system for controlling the position and orientat… | 21 |
| 5 | A system for controlling the position and orientat… | 20 |
| 6 | Capacitive force/torque sensor | 19 |
| 7 | Rapid robotic imitation learning of force-torque t… | 11 |
| 8 | Device and method for controlling joint mechanism,… | 7 |
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 competitive structure means for R&D investment decisions
Four structural dimensions — maturity, concentration, collaboration, and geography — shape how an entrant or incumbent should position a force-torque sensing R&D program. Each is read directly from the filing evidence.
Growth phase, past its 2023 annual peak
The field carries a Growth lifecycle label: the recent three-year filing window is 300% above the prior three-year window, confirming genuine expansion on a multi-year basis. Annual volume eased from its 2023 peak, and the most recent years are further understated by publication lag. This profile — broad participation, no dominant incumbent, rising overall volume — is consistent with a technology still in active formative competition rather than consolidation.
Lifecycle: GrowthModerate at the top, fragmented beneath
The top five filers hold 55% of the patent records among the hundred largest filers, with Dextrous Robotics Inc alone at the front. The remaining applicants — spanning robotics startups, automotive OEMs, academic institutions, and medtech firms — each hold one or two records. This fragmentation means no single organization controls a blocking position across the full technology scope, and a focused filing program could rapidly alter the competitive balance.
Fragmented fieldOne active co-filing pair identified: Brogardh Torgny and ABB
The only documented co-applicant relationship in evidence is between inventor Brogardh Torgny and ABB (Swedish entity), who share two co-filed records. No other multi-party co-filing clusters are evident. The near-absence of cross-organization collaboration suggests the ecosystem has not yet formed the research consortia or licensing partnerships that typically appear in more mature fields; this represents both a risk (no shared infrastructure) and an opportunity (partnerships could deliver outsized positioning).
Limited co-filingUS-centric, with PCT filings signaling global ambitions
The United States is the lead jurisdiction by patent records, followed by WIPO PCT filings — indicating that the most active filers are actively seeking international protection beyond the US home market. Europe (EPO), China, and India each have a smaller presence, and Germany appears with a single record. For a new entrant, the US is the primary battleground, but PCT coverage by existing filers means that defensive freedom-to-operate analysis should extend to Europe and, increasingly, Asia.
US-led, PCT-enabledGo 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.
| Applicant | Collaborator | Co-filings |
|---|---|---|
| BROGARDH TORGNY | ABB | 2 |
Co-filing pairs, ranked by the number of jointly-filed patent families.
Dextrous Robotics leads; Ocado and Trilobio are new entrants to watch
The applicant ranking is led by a robotics-focused startup, with the next tier split across a logistics-tech firm, an automotive OEM, and an academic institution. Momentum data shows all tracked entrants are new to this space, reinforcing the field’s formative character.
Dextrous Robotics Inc
Dextrous Robotics Inc holds 4 patent records — the highest count in the ranking — concentrated in B25J 9 (robotic manipulator systems) and B25J 15 (robot end effectors), with one record in B65G 61 (conveying and material handling), reflecting a focus on manipulation for logistics or industrial pick-and-place tasks. Their momentum is flagged as a new entrant, meaning all their records are recent; the entire portfolio has been built in the current growth window.
patent records: 4Ocado Innovation Ltd
Ocado Innovation Ltd holds 2 patent records, focused on B25J 17 (robot joint mechanisms), consistent with their automated grocery-fulfillment platform requiring precise articulated-arm control. Their momentum is also flagged as a new entrant — activity is entirely recent. As a well-capitalized logistics-robotics player, Ocado’s entry into force-torque sensing filings is a signal that sensing capability is becoming integral to next-generation warehouse automation.
patent records: 2| Applicant | Recent (3 yrs) | Trend |
|---|---|---|
| Dextrous Robotics Inc | 4 | ▲ new entrant |
| Ocado Innovation Ltd | 1 | ▲ new entrant |
| Trilobio Inc | 1 | ▲ new entrant |
Under-served branches adjacent to the dominant robotics core
Several IPC classes appear in the corpus at low counts relative to the dominant B25J cluster. These are observations of relative sparsity; technical value and entry-path plausibility are assessed below for those branches where a case can be made.
G06N · AI-driven force-torque inference
With only 2 patent records in G06N (Computing based on AI models), the intersection of machine-learning inference and force-torque sensing is notably sparse despite being cited in foundational works (the top-cited ‘rapid robotic imitation learning of force-torque tasks’ document appears twice in the cited-prior-art record). The technical value is high — learned compliance policies can outperform hard-coded control — and the entry path is accessible to organizations already active in robot learning or tactile AI, making this a plausible focus for a differentiated filing strategy.
Search this in Eureka →A61B · Surgical and diagnostic force sensing
A61B (Diagnosis and surgery) appears with only 1 patent record in this corpus, held by Howmedica Osteonics Corp (orthopedic implants). Surgical robotics requires precise force-torque feedback for safe tissue interaction, and the regulatory and clinical differentiation potential is substantial. The sparse filing count suggests that medtech-focused force-torque sensing remains largely unpublished here or is being filed under different classification strategies — either scenario represents an observation worth deeper investigation for medtech robotics R&D teams.
Search this in Eureka →How leaders differ by technology route
Strength of each leader across the main technology routes.
| Player | B25J 9 · Manipulators & robots | B25J 13 · Manipulators & robots | G05B 19 · Control & regulating systems | B25J 17 · Manipulators & robots | G01L 1 · Force & pressure measurement |
|---|---|---|---|---|---|
| Dextrous Robotics Inc | Strong · 4 | Absent | Absent | Absent | Absent |
| The Board of Trustees of the Leland Stanford Junior University | Absent | Strong · 2 | Absent | Absent | Strong · 2 |
| GM Global Technology Operations LLC | Strong · 2 | Absent | Moderate · 1 | Absent | Absent |
| Lu Bang Technology Authorization Co., Ltd. | Strong · 2 | Absent | Absent | Absent | Absent |
| G Pullaiah College of Engineering and Technology | Strong · 1 | Absent | Strong · 1 | Absent | Absent |
Frequently asked questions
There are 18 patent families in scope. The applicant ranking and IPC branch counts are measured at the patent-record level, so those figures can exceed 18 when a family is filed across multiple jurisdictions or classified under multiple IPC codes.
Dextrous Robotics Inc leads with 4 patent records, ahead of a cluster of filers — including Lu Bang Technology, Ocado Innovation Ltd, GM Global Technology Operations LLC, and the Board of Trustees of the Leland Stanford Junior University — each holding 2 records.
Yes, on a multi-year basis. The lifecycle stage is Growth, with the recent three-year filing window sitting 300% above the prior three-year window. Annual volume eased from a 2023 peak, and the most recent years are further understated by publication lag, so the overall trend remains expansionary.
B25J (Manipulators and robots) is the dominant IPC class by a wide margin. G05B (Control and regulating systems) is the next largest cluster, followed by much smaller counts in G01L (Force and pressure measurement), G06F (Digital data processing), and G06N (AI models).
The United States is the lead jurisdiction, followed by WIPO PCT filings. Europe (EPO), China, and India each have smaller but present filings. Germany appears with a single record. The PCT presence indicates that leading filers are pursuing multi-jurisdiction protection beyond the US.
One co-applicant pair is identified in evidence: inventor Brogardh Torgny and ABB, who share 2 co-filed records. No other multi-organization collaboration clusters are evident, suggesting the ecosystem has not yet developed significant cross-institutional research partnerships.
Map your own force-torque sensing patent landscape
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.