Plum picking and grading robot and picking method

Chao Wang, Urumqi City (CN); Dongxu Wang, Urumqi City (CN); Haining Wang, Urumqi City (CN); He Zhang, Urumqi City (CN); Hong Jiang, Urumqi City (CN); Hui Zhang, Urumqi City (CN); Jundong Wang, Urumqi City (CN); Mingming Xiong, Urumqi City (CN); Xiangjun Zou, Urumqi City (CN); Xiaojuan Li, Urumqi City (CN)

USPTO: us-12660754 · published 2026-06-23 · patents · A01D 46/30

Plum picking and grading robot and picking method

Xiaojuan Li, Urumqi City (CN) , Dongxu Wang, Urumqi City (CN) , Xiangjun Zou, Urumqi City (CN) , Hong Jiang, Urumqi City (CN) , Chao Wang, Urumqi City (CN) , Mingming Xiong, Urumqi City (CN) , Hui Zhang, Urumqi City (CN) , Jundong Wang, Urumqi City (CN)

show 2 more authors

Haining Wang, Urumqi City (CN) He Zhang, Urumqi City (CN)

This is my paper

Pith reviewed 2026-06-24 19:32 UTC · model grok-4.3

classification patents A01D 46/30

keywords plum picking robotfruit grading mechanismbinocular camera visionrobotic harvesting armcrawler base mobilitysound and defective fruit separationend effector mechanismautomated storage system

0 comments

The pith

A tracked robot with three binocular cameras picks plums and sorts them into sound and defective boxes via a robotic arm and screening mechanism.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The patent presents a complete mechanical and vision system for automated plum harvesting that combines mobility, picking, quality grading, and storage in one machine. A crawler base carries a robotic arm whose end effector uses a positioning camera, while two additional cameras on the base identify fruit quality for routing into separate collection boxes. The design routes picked plums through a grading screen and storage mechanism to avoid mixing good and bad fruit. A sympathetic reader would care because successful operation would replace manual labor for selective harvesting. The patent describes the arrangement of these components but supplies no performance data.

Core claim

The patent claims a plum picking and grading robot assembled from a base supporting mechanism with chassis, vertical studs, connecting plate, crawler wheels and tracks; a collecting box body containing separate sound-fruit and defective-fruit boxes; a grading and screening mechanism; a picking robotic arm; an end execution mechanism; a storage mechanism connected to both the arm and the screener; and a visual identification system that places one positioning binocular camera on the end effector and two identifying binocular cameras on the base to support the grading step.

What carries the argument

The visual identification system consisting of one positioning binocular camera on the end execution mechanism and two identifying binocular cameras on the base, which together locate plums and classify them for routing into the correct collection box.

If this is right

The crawler base allows the machine to traverse orchard rows while the arm reaches fruit.
The end effector removes plums and passes them to the grading mechanism for separation.
Sound fruit is directed to one box and defective fruit to the other through the storage mechanism.
The three-camera arrangement supplies both positioning data for the arm and quality data for sorting.
All operations occur on a single mobile platform without separate manual grading stations.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same camera-plus-screen layout could be tested on other tree fruits of similar size to check transferability.
Adding a simple weight or color threshold in the identifying cameras might further reduce misrouting rates.
If the crawler tracks prove stable on uneven ground, the base design could support heavier loads for larger harvests.

Load-bearing premise

The listed mechanical, electronic, and vision parts can be integrated to pick, grade, and store plums without damage or frequent misclassification.

What would settle it

A field trial in which more than a small percentage of picked plums show visible damage or are placed in the wrong collection box would show the integration does not work as described.

read the original abstract

1 . A plum picking and grading robot, comprising: a base supporting mechanism, a collecting box body, a grading and screening mechanism, a picking robotic arm, an end execution mechanism, a storage mechanism, and a visual identification system, wherein the collecting box body is disposed at a front end of the base supporting mechanism, and comprises a sound fruit collecting box and a defective fruit collecting box; the grading and screening mechanism and the picking robotic arm are separately disposed on an end surface of the base supporting mechanism; the end execution mechanism is disposed on an end that is of the picking robotic arm and that is away from the base supporting mechanism; the storage mechanism is disposed on the end surface of the base supporting mechanism, and the storage mechanism is separately connected to the end execution mechanism and the grading and screening mechanism; and the visual identification system comprises one positioning binocular camera and two identifying binocular cameras, wherein the one positioning binocular camera is disposed on the end execution mechanism, and the two identifying binocular cameras corresponding to the grading and screening mechanism are disposed on the end surface of the base supporting mechanism; wherein the base supporting mechanism comprises a chassis, a plurality of vertical supporting studs, a connecting plate, crawler wheels, and tracks, wherein the plurality of vertical supporting studs that are uniformly distributed are disposed on an end surface of the chassis, an end that is of each of the plurality of vertical supporting studs and that is away from the chassis is connected to the same connecting plate, two crawler wheels are disposed on a side surface of each of two sides of the chassis, and the two cr

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This is a patent filing that lists a tracked plum-picking robot with dual boxes, robotic arm, and three binocular cameras but supplies no test data or comparisons.

read the letter

This patent describes a robotic system for picking and grading plums using a tracked chassis, a robotic arm with an end effector, separate boxes for sound and defective fruit, a grading mechanism, and a vision system with three binocular cameras. That's the main takeaway: it is a component-level design description without any accompanying test results or performance claims.

The design specifies a base with crawler wheels and tracks for mobility, vertical supports, a connecting plate, collection boxes at the front, the arm mounted on the base, the end effector with one positioning camera, and two identifying cameras on the base for the grading and screening part. The storage mechanism links the picking and grading sections. This level of detail on how the parts fit together is the main contribution of the filing.

It does a solid job outlining the mechanical and visual subsystems in one package tailored to plums. The camera placement—one on the gripper for positioning and two on the base for identification—shows some thought about separating tasks.

The limitation is that nothing is proven. There are no numbers on picking success, fruit damage rates, grading accuracy, or even basic functionality tests. The description stops at listing the parts and their connections. For a patent this is standard, but it leaves the actual effectiveness as an open question.

This kind of document is mainly for people doing patent searches in agricultural automation or companies developing similar hardware who want to see one possible configuration. It is not aimed at researchers who need validated methods or data.

I would not bring this to a reading group or cite it in technical work because it reports no findings. A serious editor should desk reject it if submitted as a research paper since it lacks the empirical or analytical content that referees would evaluate.

Referee Report

0 major / 2 minor

Summary. The manuscript describes a plum picking and grading robot comprising a base supporting mechanism (chassis, vertical supporting studs, connecting plate, crawler wheels, and tracks), a collecting box body with separate sound-fruit and defective-fruit boxes, a grading and screening mechanism, a picking robotic arm, an end execution mechanism, a storage mechanism, and a visual identification system consisting of one positioning binocular camera on the end execution mechanism and two identifying binocular cameras on the base.

Significance. If the described integration of mechanical subsystems, vision components, and storage elements were successfully realized and validated, the design could contribute to agricultural automation by enabling selective harvesting and sorting of plums. The manuscript, however, contains only a high-level component enumeration with no performance data, simulations, error rates, or integration details, so its practical significance cannot be evaluated from the provided text.

minor comments (2)

The abstract text is truncated mid-sentence ('and the two cr').
No section headings, equations, tables, or figures are present to organize the component descriptions.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their review of this patent application. We wish to clarify that the document is a US patent specification (US12660754) whose purpose is to provide an enabling disclosure of the invention for legal protection, rather than to present experimental results as in a research paper.

read point-by-point responses

Referee: The manuscript, however, contains only a high-level component enumeration with no performance data, simulations, error rates, or integration details, so its practical significance cannot be evaluated from the provided text.

Authors: This is a patent document, not a scientific manuscript. Patent law requires a written description that enables a person skilled in the art to make and use the invention, which the provided component descriptions, interconnections, and visual system configuration satisfy. Empirical performance data, simulations, or error rates are not required for patentability and are outside the scope of this filing; such validation would belong in a separate research publication if pursued. revision: no

Circularity Check

0 steps flagged

No significant circularity

full rationale

The document is a patent specification that enumerates mechanical components, vision subsystems, and storage mechanisms for a plum-picking robot. It contains no equations, derivations, fitted parameters, predictions, or load-bearing scientific claims. The text is a pure systems description with no reduction of any result to its own inputs by construction. This is the most common honest finding for non-derivational documents.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, mathematical axioms, or invented scientific entities are present because the document is a mechanical patent specification rather than a theoretical or empirical research paper.

pith-pipeline@v0.9.1-grok · 5912 in / 1131 out tokens · 42465 ms · 2026-06-24T19:32:04.153535+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith.Foundation.RealityFromDistinction reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

A plum picking and grading robot, comprising: a base supporting mechanism, a collecting box body, a grading and screening mechanism, a picking robotic arm, an end execution mechanism, a storage mechanism, and a visual identification system...
IndisputableMonolith.Cost.FunctionalEquation washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

the visual identification system comprises one positioning binocular camera and two identifying binocular cameras

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.