Book a demo

Service Robots Patents: Top Companies & Filing Trends 2026

Service Robots Patents: Top Companies & Filing Trends 2026
https://www.patsnap.com/resources/blog/rd-blog/service-robots-patent-landscape-patent-landscape/ · Patsnap · data cut-off 2026-08-31 · downloaded from the live page
Patent Landscape · Service Robots
Service robots patent activity: who is filing, and where the claim space is still open
  • Concentrated but not locked up. the top five assignees hold 190 of 646 records in scope (29.4%), and the top ten hold 272 (42.1%) — leaving a long tail of single- and few-filing entrants.
  • Filing has cooled from its peak. activity peaked in 2023 at 94 records, and the complete-year comparison shows 2021's 63 filings falling to 44 by 2024, a 30% decline over that span.
  • Navigation and manipulation dominate the classes. G05D (control of non-electric variables) and B25J (manipulators & robots) appear in 39.6% and 33.6% of records respectively, far ahead of AI-model classes like G06N at 8.7%.
Get a prior-art report on your approach
646
Published Records
29%
Top-5 Share of All Records
-30%
Filing Growth 2021→2024
US
Leading Jurisdiction

Filing growth compares 2021 (63 records) with 2024 (44) — a three-year span. 2024 is the most recent year we treat as complete: publication lags filing by roughly 18 months, so 2025 onwards are still filling in and any growth rate that ends there would understate the field. Top-5 share is the combined record count of the five largest assignees divided by all 646 records in scope (CR5), not by the ranked leaders only.

Published byPatsnap Research··7 min readSourced from Patsnap Eureka
Overview

What this landscape covers

This landscape draws on 646 published patent records filed between 2015 and 2026 that combine service-robot terminology with core enabling functions: position estimation, motion trajectory, environment sensing, actuator control, autonomous navigation and robotic actuation. The search string requires both a service-robot framing and at least one of these technical mechanisms, which narrows the set to records that describe how a robot senses, plans or moves rather than every mention of robotics in general.

Publication naturally lags filing by roughly eighteen months, so the most recent one or two years in any trend line will look smaller than they eventually become once the backlog clears. Family-level counting, used throughout this ranking, reduces the distortion that comes from aggressive continuation filing or filing the same invention across multiple jurisdictions.

Filing activity and technology composition, 2015–2026
  1. 1SEEGRID CORP67
  2. 2GOOGLE LLC53
  3. 3ARISTOCRAT TECHNOLOGIES INC25
  4. 4AI INC23
  5. 5BAR ILAN UNIV22
  6. 6ROBERT BOSCH GMBH21
  7. 7HUAWEI TECH CO LTD18
  8. 8IROBOT CORP16
  9. 9TATA CONSULTANCY SERVICES LTD14
  10. 10YUJIN ROBOT13
Source: Patsnap Eureka. Assignee ranking and totals. Derived from a Patsnap search on Service Robots Patent Landscape covering 2015–2026, data cut-off 2026-08-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
The Data

Filing trend and technology composition

Two views of the same 646 records: how filing volume has moved year over year, and which IPC subclasses carry the claim density.

Filing trend, 2017–2026

Filings rose from 53 in 2017 to a peak of 94 in 2023, then declined across the last complete comparison window — 63 in 2021 down to 44 in 2024, a 30% drop. Treat 2025 and 2026 figures as provisional given publication lag.

Filing trend, 2017–202602550751005320172018201920202021202294202320242025282026Most recent year is partial — publication lag means later filings are not yet visible.

IPC subclass composition

G05D and B25J anchor the field, each appearing in roughly a third or more of records, while G06N (AI-based computing) and G06T (image processing) sit under 10% — evidence that navigation and physical manipulation claims still outweigh AI-model claims in this corpus. Shares are calculated against all 646 records and sum to more than 100% because records can carry multiple classes.

IPC subclass compositionG05D · Control of non-electric variab…25639.6%B25J · Manipulators & robots21733.6%G06F · Electric digital data processi…8913.8%G01C · Distance, navigation & gyrosco…8613.3%G06V · Image/video recognition639.8%H04L · Digital information transmissi…639.8%G06T · Image data processing & genera…578.8%G06N · Computing based on AI models568.7%Other681105.4%

Shares are the percentage of the 646 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.

Source: Patsnap Eureka. Filing trend and technology composition. Derived from a Patsnap search on Service Robots Patent Landscape covering 2015–2026, data cut-off 2026-08-31. Counts reflect published records only and shift as new filings publish.

Go deeper on Service Robots Patent Landscape with Eureka

This page is one run against one query. Ask Eureka your own question about service robots patent landscape and every answer comes back with the patent numbers behind it.

Try Eureka
Key Patents

Representative filing and most-cited records

Representative Record
US20230244239A12023-08-03

Method for Detecting Physical Forbidden Zone and Global Relocating of Service Robot

LONGTO (SUZHOU) CO., LTD

The filing (US20230244239A1, assigned to Longto (Suzhou) Co., Ltd, published 2023-08-03) presets an identification marker at the edge of a physical zone a service robot must not enter, then constantly checks for that marker during operation. On detecting it, the robot confirms its position and heading relative to the marker and adjusts its motion trajectory accordingly — a low-cost approach to boundary enforcement and relocalisation that avoids dependence on a pre-built map.Abstract condensed from the published filing.

US20230244239A1 — patent drawing 1US20230244239A1 — patent drawing 2
View full record →
Most-cited records in this landscape
#Publication no.Patent titleCitations
1US20220066456A1Obstacle recognition method for autonomous robots763
2US20210089040A1Obstacle recognition method for autonomous robots457
3US20160170996A1Crowd-based scores for experiences from measurements of affective response333
4US20160300252A1Collection of Measurements of Affective Response for Generation of Crowd-Based Results320
5US20160224803A1Privacy-guided disclosure of crowd-based scores computed based on measurements of affective response316
6US20160134932A1Camera System API For Third-Party Integrations271
7US20220026920A1Light weight and real time slam for robots267
8US11199853B1Versatile mobile platform252
9US20220187841A1Method of lightweight simultaneous localization and mapping performed on a real-time computing and battery op…206
10US11037320B1Method for estimating distance using point measurement and color depth166

Citation counts reflect influence within this searched corpus and skew toward older filings; they are not a measure of current commercial importance.

Each row carries its publication number; clicking a row searches Eureka by that number.

Source: Patsnap Eureka. Citation counts and representative records. Derived from a Patsnap search on Service Robots Patent Landscape covering 2015–2026, data cut-off 2026-08-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Run it yourself

Put your own technology through the same analysis

 
Where to run it
Fastest

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 →
For builders

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 →
Insights

What the numbers mean for filing strategy

Four patterns stand out once the raw counts are set against each other.

Concentration
29.4% / top 5
share of 646 records

The top of the field is real but not exclusive

The five leading assignees account for 190 of 646 records, and the top ten for 272 — a meaningful concentration, but well short of a closed field. A large share of the remaining assignees appear only once or twice in the ranking.

Top 5: 190 records · Top 10: 272 records
Momentum
94 in 2023
peak filing year

Volume has passed its peak, on the complete-year data

The last fully comparable window shows filings falling from 63 in 2021 to 44 in 2024, a 30% decline. Because publication lags filing by about eighteen months, 2025-2026 figures should not yet be read as a continuation of that decline.

2021: 63 → 2024: 44 (-30%)
Technology mix
39.6% G05D
share of 646 records

Control and manipulation outweigh AI-model claims

G05D (non-electric variable control) and B25J (manipulators & robots) lead the class breakdown, each present in over a third of records. G06N, the AI-model class, trails at 8.7% — claim activity is still concentrated on the mechanical and control layer rather than the learning layer.

G05D 39.6% · B25J 33.6% · G06N 8.7%
Filing geography
271 US filings
of tracked receiving offices

The US and Europe carry most of the volume

The United States (271) and EPO (104) are the largest receiving offices tracked, with India (70), WIPO/PCT (54), China (37) and Germany (27) making up the remainder. This spread suggests most applicants are prioritising US and European protection before broader PCT filing.

US 271 · EPO 104 · India 70
Eureka AI Agent
Looking for what nobody has claimed yet?

Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to service robots patent landscape, with the prior art for and against each one.

Find the white space →
Source: Patsnap Eureka. Co-assignee relationships and derived observations. Derived from a Patsnap search on Service Robots Patent Landscape covering 2015–2026, data cut-off 2026-08-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Players

Who is filing, and where they are pulling back

The assignee ranking covers 100 companies counted in records — the full set the data endpoint returns, not a curated top list. Recent-year momentum data shows several previously active filers, including some of the largest, recording zero filings in the latest tracked year, which is consistent with the publication-lag effect rather than a sudden exit.

Leader
67 records
leading assignee

One assignee leads by a clear margin

The top-ranked assignee holds 67 records, well ahead of fifth place at 22 and tenth place at 13 — a steep drop-off that signals one applicant has built a substantially deeper portfolio than any single competitor.

Leader: 67 · 5th: 22 · 10th: 13
Co-filing
10 pairs
co-assignee pairs

Co-assignment is limited and clustered

Only ten co-assignee pairs appear in the dataset, with the strongest pairing recorded 15 times. This points to a field where most filing is done by single entities rather than joint ventures or cross-licensed development.

Strongest pair: 15 shared records
Momentum
0 in latest year
for several top filers

Several established filers show no recent activity

Multiple assignees that appear high in the historical ranking, including large diversified technology firms, show zero filings in the latest tracked year. Given the roughly eighteen-month publication lag, this likely reflects filings still working through the pipeline rather than a confirmed halt.

Multiple assignees at 0, -100% YoY
🔍
Under-claimed sub-areas worth checking before filing
Class shares below 10% of the 646-record set suggest lighter claim density in these adjacent branches:
multi-robot coordination protocolsaffective/emotion-response sensing integrationAI-model-based (G06N) motion planningimage-data-driven (G06T) scene reconstructiondigital transmission (H04L) for fleet telemetry
Rank all filers by momentum →
Recent-year filing momentum by assignee
AssigneeRecent yearYoY
Seegrid Corp0-100%
Google LLC0
ARISTOCRAT TECHNOLOGIES INC0-100%
EBRAHIMI AFROUZI ALI0-100%
Bar-Ilan University0
Robert Bosch GmbH0
iRobot Corp0
HIGHFILL BRIAN0-100%
Source: Patsnap Eureka. Assignee-level momentum. Derived from a Patsnap search on Service Robots Patent Landscape covering 2015–2026, data cut-off 2026-08-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
What's Next

Where to take this next

The landscape points to specific next steps depending on whether the goal is freedom-to-operate, portfolio benchmarking or identifying a filing gap.

Check freedom-to-operate against the leader's portfolio

With one assignee holding 67 records against a field where fifth place sits at 22, any new filing in navigation or actuator control should be checked specifically against that leader's claim set before drafting.

Explore assignee portfolios in Eureka →

Test claims in the under-10% classes

G06N, G06T and H04L all sit under 10% of the 646 records despite being adjacent to the core G05D and B25J activity — a first claim combining service-robot navigation with one of these lighter-claimed functions is worth drafting and searching before committing.

Run a white-space search in Eureka →
Source: Patsnap Eureka. Forward-looking reading of the same dataset. Derived from a Patsnap search on Service Robots Patent Landscape covering 2015–2026, data cut-off 2026-08-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
FAQ

Common questions about the service robots patent landscape

Answers are grounded in the same dataset. Derived from a Patsnap search on Service Robots Patent Landscape covering 2015–2026, data cut-off 2026-08-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP

Research Service Robots Patent Landscape in depth with Eureka

Go past this page: query the whole service robots patent landscape corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.

Try Eureka

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.

Help us improve this page

Found incorrect or outdated information? Let us know and we'll get it fixed.