Harvesting Robot & Manipulator Patent Landscape 2026
Chinese agricultural universities and a handful of industrial automation firms dominate the harvesting robot and manipulator patent space, with Northwest A&F University holding the top position. Annual filing volume peaked in 2021 and has since plateaued, signaling a maturing field where differentiation through vision, sorting, and AI integration remains sparse.
Chinese academic institutions lead a moderately concentrated field
Northwest. A&F University holds the leading position among the top-ranked filers, followed closely by Four Growers Inc. and Jiangsu University. The top five filers collectively account for 24% of the combined total among the hundred largest filers, indicating moderate concentration rather than a winner-take-all dynamic.
A clear two-tier structure exists: the top three applicants — Northwest. A&F University, Four Growers Inc., and Jiangsu University — are separated from the remaining ranked filers by a meaningful gap. ABB (Schweiz) AG is the only established industrial automation multinational in the upper tier, sitting fourth.
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 1 | NORTHWEST A & F UNIV | 10 | |
| 2 | Four Growers Inc. | 8 | |
| 3 | Jiangsu University | 8 | |
| 4 | ABB (Schweiz) AG | 5 | |
| 5 | China Agricultural University | 4 | |
| 6 | Nanjing Institute of Technology | 4 | |
| 7 | Shandong Guoxing Smartech Co., Ltd. | 4 | |
| 8 | Shandong Agricultural University | 4 | |
| 9 | ISEKI & CO LTD | 3 | |
| 10 | Central South University of Forestry and Technology | 3 |
| # | Applicant | Patent records | Share |
|---|---|---|---|
| 11 | Henan Polytechnic University | 3 | |
| 12 | Zhengzhou University | 2 | |
| 13 | Muxing Intelligent Industrial Technology (Shanghai) Co., Ltd. | 2 | |
| 14 | Sudarmani R. | 2 | |
| 15 | Sharmeela R. | 2 | |
| 16 | Nanchang University | 2 | |
| 17 | Nanjing Agricultural University | 2 | |
| 18 | Huai’an Qingjiangpu District Market Supervision Comprehensive Service Center | 2 | |
| 19 | AVINASHILINGAM INST FOR HOME SCI & HIGHER EDUCATIO… | 2 | |
| 20 | Zhejiang University | 2 |
The dominance of academic applicants implies that foundational end-effector and manipulator designs are well-established in the literature but not yet fully industrialized. This creates an opportunity for firms that can translate university-generated IP into commercially deployable systems.
The most recent 18–24 months of filings are subject to publication lag and should be treated as under-counted; apparent softness in 2024–2025 data does not necessarily reflect a real decline in inventive activity. Longer-window growth, applicant concentration, and technology-route coverage are therefore more reliable signals than the latest-year bar alone.
Filing activity has plateaued and technology mix is concentrated in core harvesting mechanics
The annual trend chart tracks filing volume from 2017 onward, while the technology composition chart reveals how IPC classes are distributed across the corpus. Together they show a field that ramped sharply into 2021 and has since leveled off, with most activity still anchored in core harvesting and manipulation classes.
Annual filing trend
Filings grew rapidly from 2017 to a peak in 2021, then stabilized in the 12–15 range annually through 2023. The 2024 and 2025 bars appear softer but reflect publication lag and should not be read as a confirmed downturn. The 3% recent-window growth figure confirms the field is not contracting on a multi-year basis.
↗ Hover for values · click a bar to ask EurekaTechnology composition
A01D (Harvesting & mowing) dominates the technology mix by a wide margin, followed by B25J (Manipulators & robots). Vision and recognition branches — G06V, G06T — and sorting-related B07C appear at much lower volumes, underscoring where coverage thins relative to the core mechanical classes.
↗ 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.
Fruit Picking Robot and End Effector Therefore
An end effector for a fruit picking robot has a distal portion comprising tools for seizing and detaching a fruit from its mother plant, a proximal portion comprising an interface for mounting the end effector to a robot arm, and a storage bay for picked fruit. The storage bay is elongate in a longitudinal direction and has a discharge port extending along… (excerpt from the patent abstract)
| # | Patent | Citations |
|---|---|---|
| 1 | Robot mechanical picker system and method | 263 |
| 2 | Agricultural robot system and method | 119 |
| 3 | 一种苹果采摘机器人的末端执行器 | 79 |
| 4 | 球状果实采摘机器人末端执行器 | 78 |
| 5 | Fruit controlling and harvesting robot | 53 |
| 6 | 一种苹果采摘机器人 | 47 |
| 7 | 一种油茶果采摘机器人及其油茶果采摘方法 | 41 |
| 8 | 水果采摘机器人的机械臂和末端执行器及水果采摘方法 | 38 |
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
China, and a plateauing filing rate shapes where incremental patent value can still be created. The four dimensions below translate the structural evidence into actionable read-outs.
Field has plateaued near its 2021 peak
The lifecycle evidence places this field at the Maturity stage: annual filings peaked in 2021 and have since plateaued rather than continuing to grow. The multi-year window still shows modest positive growth at 3%, so the field is not in decline, but the rapid expansion phase has passed. New entrants should expect a crowded core and will need to differentiate in adjacent technology branches to secure defensible IP.
Lifecycle: MaturityModerate concentration with a clear academic-vs-industry divide
The top five filers hold 24% of the hundred largest filers’ combined total — concentrated enough to indicate clear leaders but not so dominant as to foreclose entry. Northwest A&F University and Jiangsu University anchor the academic cluster, while Four Growers Inc. and ABB (Schweiz) AG represent commercial applicants. The tier gap between the top three and the rest is meaningful; challengers in ranks 4–10 each hold four or fewer patent records.
Concentration: ModerateNo co-applicant activity detected in this corpus
The collaboration evidence shows no recorded co-applicant filings within the analyzed corpus. This is consistent with a landscape dominated by individual universities and single-entity commercial filers working independently. The absence of visible consortia or cross-institutional joint filings suggests that partnering or licensing arrangements — if they exist — are not yet reflected in jointly filed patents.
Collaboration: Evidence pendingChina-dominant filing with limited international coverage
China accounts for the largest single jurisdiction by a substantial margin, with India and the United States each recording only 6 patent records, followed by the European Patent Office with 5. PCT (WIPO) filings number only 3, suggesting that most filers have not yet pursued broad international protection. This leaves non-Chinese jurisdictions — particularly the US, Europe, and Japan — relatively open for applicants willing to file internationally.
Geography: China-dominantGo 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.
Northwest A&F University leads on volume; Four Growers Inc. distinguishes itself through vision and sorting integration
The top two filers illustrate two distinct strategic approaches: deep mechanical end-effector development anchored in Chinese academia versus a commercially-oriented system that integrates harvesting mechanics with computer vision and object sorting. Both show recent momentum as new entrants in the analyzed window.
Northwest A&F University
Northwest A&F University leads the ranking with 10 patent records. Its technology emphasis is concentrated in A01D 46 (Harvesting & mowing) with additional coverage in B25J 15 and B25J 13 (Manipulator end-effectors and control). The applicant momentum data shows a ‘new entrant’ trend in the recent window, indicating that its current filing activity represents a newly established position within this specific corpus rather than a long-running portfolio.
10 patent recordsFour Growers Inc.
Four Growers Inc. holds 8 patent records and is the only top-tier applicant with balanced coverage across A01D 46 (Harvesting), B07C 5 (Object sorting), and G06V 10 (Image/video recognition) — each at 8 records. This multi-branch profile is unique among the leaders and reflects a vertically integrated system approach. As a commercial entity operating alongside predominantly academic filers, it represents the clearest industrialization pathway in the current landscape.
8 patent records| Applicant | Recent (3 yrs) | Trend |
|---|---|---|
| Northwest Agriculture and Forestry University | 3 | ▲ new entrant |
| Jiangsu University | 1 | ▲ new entrant |
| China Agricultural University | 1 | ▲ new entrant |
| ABB (Schweiz) AG | 1 | ▲ new entrant |
Vision integration and intelligent sorting are under-served relative to core harvesting mechanics
Compared to the dominant A01D and B25J classes, several adjacent IPC branches show sparse coverage despite clear technical relevance to next-generation harvesting systems. Two branches stand out as observations worth monitoring for potential white-space entry.
G06V · Image/video recognition
With only 14 patent records — representing 6% of the branch total — image and video recognition coverage is thin relative to the core mechanical classes. Yet vision-based fruit detection and localization are prerequisites for autonomous operation. Four Growers Inc. is the primary filer here; most academic applicants have not extended into this branch. An entrant with proprietary vision models or training datasets for agricultural produce could file defensible IP in a space where volume remains low.
Search this in Eureka →G06T · Image data processing & generation
Image data processing (G06T) accounts for only 4 patent records at a 2% share, despite being directly relevant to 3D point-cloud processing, depth estimation, and pose detection for manipulator guidance. Iseki & Co. Ltd. is the only top-ranked applicant with recorded G06T coverage. The combination of sparse filings and high technical relevance to precision end-effector control makes this an adjacent branch worth monitoring, particularly for firms with existing computer vision capabilities.
Search this in Eureka →How the leading applicants differ by technology route
Route coverage across the main technology branches in the current evidence set.
| Player | A01D 46 · Harvesting & mowing | B25J 15 · Manipulators & robots | B25J 11 · Manipulators & robots | B25J 9 · Manipulators & robots | B25J 5 · Manipulators & robots |
|---|---|---|---|---|---|
| Northwest Agriculture and Forestry University | Strong · 10 | Moderate · 3 | Absent | Absent | Absent |
| Four Growers Inc. | Strong · 8 | Moderate · 4 | Absent | Absent | Absent |
| Jiangsu University | Strong · 8 | Absent | Absent | Moderate · 4 | Absent |
| China Agricultural University | Strong · 6 | Moderate · 3 | Absent | Moderate · 2 | Absent |
| Nanjing Institute of Technology | Strong · 6 | Moderate · 3 | Absent | Absent | Absent |
| 井关农机株式会社 | Strong · 3 | Strong · 3 | Moderate · 1 | Absent | Absent |
| ABB (Schweiz) AG | Strong · 5 | Absent | Emerging · 1 | Absent | Absent |
Frequently asked questions
The analysis covers 85 patent families. The leading jurisdiction by patent records is China, reflecting the concentration of filing activity among Chinese academic and industrial applicants.
Northwest A&F University (Northwest Agriculture and Forestry University, China) holds the top position with 10 patent records. It is followed by Four Growers Inc. and Jiangsu University, each with 8 patent records.
The field is in a Maturity stage. Annual filings peaked in 2021 and have since plateaued rather than continuing to rise. The multi-year recent-window growth is positive at 3%, so the field is not declining, but the rapid expansion phase has ended. Recent-year data through 2025 is subject to publication lag and may be under-counted.
A01D (Harvesting & mowing) is the dominant branch by a wide margin, followed by B25J (Manipulators & robots). All other branches — including vision, sorting, and AI — account for substantially fewer patent records, indicating that the core mechanical layer is well-covered while adjacent enabling technologies remain sparse.
G06V (Image/video recognition) and G06T (Image data processing) are the most technically relevant under-served branches, with only 14 and 4 patent records respectively. G06N (AI models) and B07C (Object sorting) also show low coverage relative to their importance for autonomous harvesting systems.
The United States and India each record 6 patent records, the European Patent Office records 5, and Japan records 4 — all substantially below China’s count. PCT (WIPO) filings number only 3, suggesting that most filers have not yet pursued broad international protection. Non-Chinese jurisdictions, particularly the US and Europe, are relatively lightly covered.
Ready to map your own harvesting robot 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.