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 →This landscape tracks patent families at the intersection of mobile robot bases and manipulator arms, filtered specifically to whole-body or coupled base-arm motion planning rather than mobile robotics or robotic arms in general. The search combines title/abstract language on mobile manipulation with claims-level language on collision-free and coupled planning, restricted to the core manipulator and control IPC classes (B25J9/16, G05B19/4155, B25J5). The result is a small, tightly-scoped corpus of 19 patent families published between 2015 and mid-2026.
Because publication typically lags filing by around 18 months, the 2026 figure of zero filings understates real activity; the more reliable read is the 2019 peak and the flat 2022 midpoint, which together suggest the field has stopped accelerating rather than that it has gone quiet.
Pick a task. Every answer cites the patents behind it.
Two views of the same 19-family dataset: how filing activity has moved year over year, and how those filings split across IPC subclasses.
Filings rose from 2 in 2017 to a peak of 4 in 2019, then held at 4 again at the 2022 midpoint before tapering toward the (still-understated) 2026 figure of 0. There is no sustained growth phase visible in this data — activity rose once and has not built on it since.
All 19 records touch B25J (manipulators and robots), the class the search was built around. Welding and brazing (B23K) appears in 2 records, and general control classes G05B and G05D each appear once — signalling that motion-planning claims here are being written as manipulator claims first, with control-theory framing a minor secondary layer rather than a parallel filing strategy.
Shares are the percentage of the 19 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
This page is one run against one query. Ask Eureka your own question about mobile manipulator motion planning and every answer comes back with the patent numbers behind it.
Try EurekaProvided is a teaching device for a mobile manipulator based on a mobile robot and a collaborative robot. The teaching device includes a communication unit that transmits/receives data to and from the mobile manipulator, a memory that stores a program providing an interface for performing a task of the mobile manipulator, and a processor that operates a teaching program that performs map creation and autonomous setting for the mobile robot, and setting necessary for robot manipulation for the collaborative robot on the same interface.Filed by Electronics and Telecommunications Research Institute (ETRI), published 2024-08-29 — one of the most recent records in the set and a useful marker of where teaching-interface claims currently sit.


| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | CN107414832A | 一种基于机器视觉的移动机械臂抓取控制系统及方法 | 53 |
| 2 | US20200398433A1 | Method of calibrating a mobile manipulator | 19 |
| 3 | CN105563490A | 一种移动机械臂障碍物躲避的容错运动规划方法 | 18 |
| 4 | US9862090B2 | Surrogate: a body-dexterous mobile manipulation robot with a tracked base | 14 |
| 5 | CN114800528A | 非凸抗噪型归零神经网络的移动机械臂重复运动规划 | 7 |
| 6 | CN207206429U | 一种基于机器视觉的移动机械臂抓取控制系统 | 7 |
| 7 | CN119871459A | 面向移动机械臂全身运动规划的优化方法 | 4 |
| 8 | CN119927897A | 一种基于改进NSGA-III的移动机械臂时空轨迹综合性能优化方法 | 3 |
| 9 | CN115781669A | 一种轮式移动机械臂加速度层重复运动规划方法 | 2 |
| 10 | WO2019165561A1 | Method of calibrating a mobile manipulator | 2 |
Citation counts favour older filings simply because they have had more time to accumulate references inside this corpus — read them as a marker of influence on subsequent filers, not as a signal of which claims matter most today.
Patent titles are shown in the language they were filed in, not translated, so that each record stays verifiable against the original filing — a translated title will not match in Eureka or in any national register. Each row carries its publication number; clicking a row searches Eureka by that number.
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 →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 →Three findings that change how a team should approach this space, drawn directly from the filing and citation data above.
A single peak year followed by a flat midpoint and a near-empty latest year is not the signature of an emerging field — it reads as a technology where the obvious claims were staked out early and few new entrants have shown up since. Teams evaluating entry should weigh whether the plateau reflects a saturated claim space or simply thin overall filing volume in a niche.
With 10 of 19 records filed through the China receiving office versus 6 through the United States and only single digits elsewhere (Canada, Japan, WIPO/PCT), any freedom-to-operate review for products destined for the Chinese market needs to start with this corpus, not treat it as a secondary jurisdiction.
Only two co-assignee pairings appear across the whole set, and the strongest is a two-filing individual pairing rather than an institutional alliance. There is no visible cluster of firms cross-licensing or co-developing here — each assignee is filing largely alone.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to mobile manipulator motion planning, with the prior art for and against each one.
The assignee base spans Chinese universities, a Korean government research institute and individual inventors, but no single player holds a commanding share of the 19 families, and none show filing activity in the most recent tracked year.
Every named assignee in the recent-momentum data — from Toronto's university council to Hainan University and South China University of Technology — shows zero filings in the latest tracked year, several with a full -100% year-on-year drop. This is a field-wide pause rather than one company losing ground to another.
The most-cited record in the set is a 2017-era Chinese filing on vision-based grasping control for mobile manipulators, cited 53 times — far ahead of the next most-cited record. That gap reflects age and corpus composition as much as ongoing relevance.
Zhejiang University paired once with Yuyao Robotics Research Center, and two individual inventors, Zhang Mingfeng and Yuan Xing, co-filed twice — the only two collaborative links in the entire dataset. New entrants should not expect to find an established consortium to partner into.
| Assignee | Recent year | YoY |
|---|---|---|
| The Governing Council of the University of Toronto | 0 | — |
| Electronics and Telecommunications Research Institute (ETRI) | 0 | — |
| Hainan University | 0 | -100% |
| South China University of Technology | 0 | — |
| ZHANG MINGFENG | 0 | — |
| YUAN XING | 0 | — |
| Changchun University of Technology | 0 | — |
| Suzhou Ronghui Special Robot Co., Ltd. | 0 | — |
This landscape identifies the filing pattern and the gaps; deciding whether to file, license, or design around requires going claim by claim.
Run your specific base-arm coupling method or planning algorithm against the highest-cited families identified here to see which claim elements actually overlap with your design.
Explore in EurekaBecause every tracked assignee currently shows zero recent filings, a fresh filing from any of them would be a meaningful signal worth monitoring going forward.
Set up monitoring in EurekaThe under-claimed branches flagged here are based on filing density, not a full claim-language review — confirm the gap holds before committing a first claim to any of them.
Review claim language in EurekaThis dataset tracks 19 patent families published between 2015 and mid-2026 that specifically combine mobile manipulator or arm-on-base robot terminology with whole-body or coupled base-arm motion planning language, within the core manipulator and control IPC classes. That is a narrow, purpose-built corpus rather than a count of every mobile robotics patent — broader searches on mobile manipulation alone would return a much larger number. Filing activity peaked at 4 families in 2019 and has not exceeded that since, through the 2022 midpoint of 4 and a near-empty most recent year, though the latest year is understated due to normal publication lag.
No single company holds a commanding share of this 19-family corpus; the assignee base includes Chinese universities such as Zhejiang University, South China University of Technology and Hainan University, Canada's University of Toronto, South Korea's Electronics and Telecommunications Research Institute, and several individual inventors. Every one of these assignees shows zero filings in the most recent tracked year, so leadership here is better read as historical concentration than current momentum. The most-cited single record, a 2017-era Chinese filing on vision-based grasping control, still anchors the citation graph but that reflects its age as much as ongoing influence.
Mobile manipulation broadly covers any robot combining a mobile base with a manipulator arm, including perception, grasping and task planning. Motion planning patents within that space, which is what this dataset isolates, specifically claim methods for computing collision-free or coupled base-and-arm trajectories — the algorithmic layer that decides how the robot moves, not what it perceives or grasps. This distinction matters for freedom-to-operate work because a product could clear mobile-manipulation prior art broadly while still infringing a narrowly drafted whole-body planning claim, or vice versa.
The receiving-office data shows China accounts for 10 of the 19 tracked families, with the United States at 6 and Canada, Japan and the WIPO/PCT route each appearing once. That concentration means the densest existing claim coverage — and the highest infringement risk for products sold or manufactured in China — sits in the Chinese filings. A team evaluating entry should prioritise a China-focused claim chart before assuming clearer freedom to operate in other jurisdictions, since the US and other regions currently carry lighter documented coverage in this specific niche.
The trend data suggests filing has plateaued rather than grown: activity rose to a peak of 4 families in 2019, held at 4 again by the 2022 midpoint, and shows no filings yet in the most recent tracked year. Because publication lags filing by roughly 18 months, that final-year zero is likely understated rather than a true stop. Still, the absence of a clear upward trend across nearly a decade, combined with only two co-assignee pairs across all 19 families, points to a niche with modest and fragmented ongoing investment rather than an accelerating one.
Go past this page: query the whole mobile manipulator motion planning corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
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.