Mobile Manipulator Patents: Who Leads, Where the Gaps Are 2026
- Filing activity peaked in 2022 at 29 families and has not returned to that level since, suggesting the core base-arm coordination claim space is largely staked out rather than still expanding.
- The most-cited family draws 619 citations for a piece-picking and put-away mobile manipulation architecture, five times the next-most-cited record — a strong signal of where downstream designers keep having to work around prior art.
- Filings concentrate in the United States (33 of the tracked records) with PCT, EPO, Australian and Canadian filings trailing well behind, which matters for anyone deciding where freedom-to-operate risk is actually concentrated.
What the mobile manipulator patent record shows
Mobile manipulators combine a mobile base with an articulated arm, and the patent claims that matter most are the ones governing how the two are coordinated — base-arm coordination, whole-body motion and mobile grasping rather than the base or arm hardware alone. This landscape covers 70 patent families published between 2015 and mid-2026, filtered to records whose claims or descriptions explicitly address coordinated mobile manipulation under the core manipulator and motion-control IPC classes.
The dataset is dominated by warehouse and logistics use cases — piece-picking, put-away and bin storage retrieval recur among the most-cited families — which shapes what 'mobile manipulator' has come to mean in claim language: a robot that moves to a location and then manipulates an object there, under a single integrated controller.
Let an AI agent run this analysis on your own technology
Pick a task. Every answer cites the patents behind it.
Filing trends and technology composition
Two views of the same 70 families: how filing activity has moved year over year, and which IPC subclasses the claims actually sit in.
Filings rose sharply into 2022, then plateaued
Annual filings climbed from 4 in 2017 to a peak of 29 in 2022. Since then, activity has flattened rather than continued growing — a pattern more consistent with an established claim space than an emerging one. Remember that the most recent year is always undercounted, since publication typically lags filing by around 18 months.
B25J dominates; control and logistics classes trail
Every record in this set touches B25J (manipulators and robots), as expected given the search scope. The next-largest classes — G05D (non-electric control), B65G (conveying and material handling) and B60P (load-handling vehicles) — show that most of the surrounding claim activity is about integrating the manipulator into a material-handling workflow rather than about the arm mechanism itself. G06Q's presence (11 records) reflects fleet and task-scheduling logic layered on top of the physical system.
Shares are the percentage of the 70 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on Mobile Manipulator Technology Landscape with Eureka
This page is one run against one query. Ask Eureka your own question about mobile manipulator technology landscape and every answer comes back with the patent numbers behind it.
Try EurekaThe most-cited families and a recent representative filing
Control system and method for a mobile manipulation robot (EP4717415A1)
The filing describes a control architecture for a mobile manipulation robot built from a locomotion control module, an integrated control module, a trajectory planning module, a trajectory decomposing and calculating module, an inverse kinematics model, and a decoupling and calculating module. The integrated control module coordinates locomotion and arm motion under a single mode rather than treating base movement and manipulation as separate control loops.Filed by Shanghai Sage Intelligent Technology Co., Ltd., published 2026-04-01.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US20150032252A1 | System and method for piece-picking or put-away with a mobile manipulation robot | 619 |
| 2 | US20150332213A1 | Autonomous mobile bin storage and retrieval system | 182 |
| 3 | US20200242544A1 | System and method for piece picking or put-away with a mobile manipulation robot | 124 |
| 4 | US9519882B2 | Autonomous mobile bin storage and retrieval system | 109 |
| 5 | US9785911B2 | System and method for piece-picking or put-away with a mobile manipulation robot | 108 |
| 6 | US20180104829A1 | Field replaceable battery pack and lift counterbalance for a mobile manipulation robot | 105 |
| 7 | WO2016014917A1 | Autonomous mobile bin storage and retrieval system | 77 |
| 8 | US20180032949A1 | System and method for piece picking or put-away with a mobile manipulation robot | 74 |
| 9 | US10147069B2 | System and method for piece picking or put-away with a mobile manipulation robot | 40 |
| 10 | US9940604B2 | System and method for piece picking or put-away with a mobile manipulation robot | 28 |
Citation counts are a signal of influence within the searched corpus, not of current commercial importance — older families accumulate citations simply by being available longer.
Each row carries its publication number; clicking a row searches Eureka by that number.
Put your own technology through the same analysis
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 →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 →What the numbers mean for a filing or design decision
Three patterns stand out once the raw counts are set against each other.
One architecture dominates the citation graph
The leading family, covering piece-picking and put-away with a mobile manipulation robot, is cited more than five times as often as the second-ranked record. Any new filing in warehouse-facing mobile manipulation should be checked against this family and its continuations before claims are drafted.
Filing risk is concentrated in the United States
Nearly half of the tracked records were filed at the USPTO, with PCT, EPO, Australian and Canadian offices each accounting for a smaller share. Freedom-to-operate work should weight US prior art most heavily, then check PCT applications for jurisdictions not yet nationalised.
Growth has flattened since the 2022 peak
Filings rose from 4 in 2017 to 29 in 2022 but have not exceeded that level since. Combined with a co-assignee network of only 9 pairs, this suggests the field has moved from an initial land-grab phase into narrower, more defensive filing by established players.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to mobile manipulator technology landscape, with the prior art for and against each one.
Who is filing, and where the claim space is still open
Recent-year momentum has dropped to near zero across the assignees tracked here, which is as informative as the historical rankings themselves.
Piece-picking and bin-retrieval originator
The assignee behind the most-cited piece-picking and bin storage/retrieval families set much of the vocabulary this landscape's claims still use, but shows 0 filings in the latest tracked year.
A tight inventor network behind the top family
Galluzzo Thomas and Altman Vladimir co-appear on 10 filings, with a secondary link to Valois Jean Sebastien on 4 each — a small, tightly connected inventor group rather than a broad multi-team effort.
Momentum has largely stalled across tracked assignees
Nearly every assignee tracked, including Boston Dynamics (-100% YoY) and ABB, shows zero filings in the most recent year. Only one entrant, a university filer, registers a single latest-year filing — consistent with the broader plateau since 2022.
| Assignee | Recent year | YoY |
|---|---|---|
| Northwestern University | 1 | — |
| Boston Dynamics | 0 | -100% |
| IAM ROBOTICS | 0 | — |
| GALLUZZO THOMAS | 0 | — |
| ALTMAN VLADIMIR | 0 | — |
| ABB (Switzerland) Ltd. | 0 | — |
| VALOIS JEAN SEBASTIEN | 0 | — |
| Shandong University | 0 | — |
Where to take this
The plateau since 2022 and the thin recent-year momentum both point to the same next step: check specific claim language before committing to a filing direction.
Run a freedom-to-operate check against the top-cited family
Before drafting claims on any piece-picking, put-away or bin-retrieval architecture, check independent claim scope on the 619-citation family and its continuations.
Analyse this family in EurekaMap the under-claimed branches to your own architecture
Whole-body trajectory decoupling and vision-guided inverse kinematics show thinner filing density than the logistics core — worth a targeted search before assuming the space is open.
Explore white space in EurekaCommon questions about mobile manipulator patents
In this landscape, a mobile manipulator patent is one whose claims or description explicitly address coordinating a mobile base and an articulated arm as a single system — covering base-arm coordination, whole-body motion, or mobile grasping, rather than a mobile base and an arm claimed as separate inventions. The search here also required core manipulator and motion-control IPC classes (B25J, G05D and related) to be present. This excludes patents on stationary robotic arms or wheeled bases filed without a manipulation claim.
The most-cited families in this dataset trace back to an assignee behind piece-picking, put-away and bin storage/retrieval architectures, whose top family carries 619 citations. However, recent-year filing activity across almost every assignee tracked, including that historical leader and Boston Dynamics, has dropped to zero, so citation leadership and current filing activity are not the same thing here.
Filing activity rose from 4 families in 2017 to a peak of 29 in 2022, then flattened rather than continuing to climb. That plateau, combined with a small and tightly connected co-assignee network of only 9 pairs, suggests the field has moved past its initial expansion phase into narrower, more defensive filing. The most recent year's count is still partial because publication typically lags filing by about 18 months.
Nearly half of the tracked records, 33 of 70, were filed at the USPTO, making the United States the highest-density jurisdiction for prior art in this space. PCT filings account for 12 records and may still be entering national phase in other jurisdictions, so a PCT-application search is worth running alongside a granted-patent search. Europe, Australia and Canada show meaningfully lower filing density in this dataset.
EP4717415A1 is a 2026 filing from Shanghai Sage Intelligent Technology describing a control system for a mobile manipulation robot built from separate locomotion, integrated control, trajectory planning, trajectory decomposition and inverse-kinematics modules. Its distinguishing feature is coordinating base locomotion and arm motion through a single integrated control mode rather than two independent control loops. Anyone building a comparable unified controller architecture should review its specific module boundaries and claim language before assuming their design falls outside it.
Research Mobile Manipulator Technology Landscape in depth with Eureka
Go past this page: query the whole mobile manipulator technology landscape 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.