The literature is used to list questions, not to borrow success rates. Questions related to the two-finger parallel gripper RMG22-65 are: whether the action space equals the publicly stated degrees of freedom of the follower or leader, whether the observation equals the cameras on the checklist, whether the chassis moves, whether end-effector open/close is in the vector, and whether timestamps are agreed separately.
Document Location
ALOHA discusses dual-arm master-slave control and action chunking, Mobile ALOHA discusses mobile dual-arm, Diffusion Policy discusses imitation-learned visuomotor policies, UMI discusses a handheld gripper rather than a full platform, and Open X-Embodiment discusses pooling across robots, where the embodiment must be labeled. These sentences can be written into the "source of questions" section of a proposal. Do not copy the authors' success rates, sample counts, or costs.
The two-finger parallel gripper RMG22-65 can only answer the parts already written on the product page: this is an end gripper, not an articulated arm. The public table does not give the gripper an integer "degrees of freedom"; do not invent one to align with other bodies. Communication interface: 6-pin aviation connector. Communication protocol: RS485 / Modbus-RTU. Operating environment: 0–50 °C, relative humidity ≤85%. There is no camera on the page. It is itself the end effector. Whether it directly matches the body's flange, wiring harness, and protocol must be confirmed on the configuration sheet; the page states that plug-and-play is not the default. All other questions remain unanswered until a written configuration is provided.
Do not write "using the system from the above papers." TOBI does not have the equipment list from those experiments, and the two-finger parallel gripper RMG22-65 is not the robot in those papers.

How to Use This Page in This Version
The literature section of the proposal uses a question list, not a scorecard. The list has five questions: Is the action space equal to the degrees of freedom or master-slave columns published for the two-finger parallel gripper RMG22-65? Is the observation equal to the camera in the list? Is the chassis included in the action? Is the end-effector opening / closing listed separately? Is the timestamp handled separately? For the five questions that can be answered from the product page, the answer must be the original sentence. This is an end gripper, not an articulated arm. The public table does not give the gripper an integer "degrees of freedom"; do not invent one to align with other bodies. Communication interface: 6-pin aviation connector. Communication protocol: RS485 / Modbus-RTU. Operating environment: 0–50 °C, relative humidity ≤85%. There is no camera on the page. It is itself the end effector. Whether it directly matches the body's flange, wiring harness, and protocol must be confirmed on the configuration sheet; the page states that plug-and-play is not the default. Opening / closing time 2 s. Positional repeatability ±0.05 mm. The 2 seconds is the opening or closing time specification, not the control frequency.
For anything that cannot be answered, write "not disclosed." Do not fill in gaps with the experimental setups of ALOHA, Mobile ALOHA, Diffusion Policy, UMI, or Open X-Embodiment. Those works use their own robots and their own success definitions. TOBI is not the author of those experiments, and the two-finger parallel gripper RMG22-65 is not the platform used in those papers.
The only connections that can be written are methodological: leader-follower teleoperation requires the leader and follower to share the same action space; mobile manipulation requires recording the chassis; the handheld gripper route is deliberately not a whole-machine; cross-robot aggregation requires annotating embodiment differences. These are research questions derived from reading the literature, not performance guarantees.
The last sentence of the literature section is fixed as: success rate, data duration, and cost are per the original paper and are not transcribed to this product. Then send the reader back to /product-gripper-2f.html, not to an external PDF as if it were a specification sheet.
Line-by-Line Verification
Degrees of freedom. This is an end gripper, not an articulated arm. The public table does not give the gripper an integer "degrees of freedom"; do not invent one to align with other bodies. This line only states the number and locations of joints that have been made public. It does not evaluate intelligence, and it does not automatically include waist, legs, neck, or a whole-machine total that are not named on the page. When writing into the action vector, create channels only for the body parts listed in this row; body parts not listed remain blank. Do not write blank as 0, because 0 would be treated by training scripts as a real angle. Do not fill in the degrees-of-freedom integer of another device after this row to make the numbers add up. If the master-slave joint order is not given on the page, mark it as pending written configuration confirmation; do not number it yourself. For the action space in the literature questions, answer using this row, not using the joint count of the paper's robot. The action vector creates channels only for the body parts named in this row; unnamed body parts remain blank, not filled with 0.
Load and mass. Maximum envelope grasp load 5 kg. Recommended maximum friction load 2 kg. Maximum clamping force 130 N. These three numbers must not be written as the same 5. Every number on this line must be read with its subject: rated, self-weight, full-machine mass, envelope, friction, or clamping force. If the subjects differ, they must not be merged into one number, nor converted using any conversion not given on the page. If the object in the field is heavier, the specification cannot be revised retroactively; a larger specification does not prove that every grasp type reaches that limit. The tool mass is undetermined; do not write the arm's rated value as the graspable object mass. The acceptance table retains the original units. Object weights from papers cannot be written as already verified by this row. During acceptance, read the subject first, then the number; if the subjects differ, split into two rows.
Dimensions and scale. Full-machine dimensions 112 × 60 × 167 mm. Stroke 65 mm. Finger height 80 mm. Body weight 745 g. This line is for external or structural dimensions, used to check doorways, elevators, tabletops, or transport; it is not operating height, nor is it arm reach. Do not add it to the vertical range. If the figure shows protrusions, antennas, or a person's standing position not present in this line, note separately that they are not part of the specification. If weight appears in an adjacent row, do not write it into the dimension sentence. The dimensions of the paper's platform cannot replace this line. Doorways, elevators, and transport are checked only against external dimensions; do not treat this line as operating height.
Operating range. Stroke 65 mm is the finger opening distance, not the robotic arm's reach, nor the body's vertical working range. This line describes the range the hand or lift can reach; the definition must follow the original sentence: vertical working range, reach, motion radius, or stroke — these cannot be added together or renamed. If "excluding end effector" is written, it must remain in the figure caption. When the original text does not specify units, retain the note "units not specified"; do not delete it for tidiness. The workspace definition from the paper cannot replace this line's definition. The figure caption retains the range definition from the original sentence, as well as the terms "excluding end" or "units not specified."
Motion. Open/close time 2 s. Positional repeatability ±0.05 mm. The 2 seconds is the open-or-close time specification, not the control frequency. This row describes how the ground or main arm moves. Four-wheel four-drive, differential drive, in-place turning radius, and rotational speed are terms for different mechanisms and cannot be substituted for one another. The published speed is a capability, not a recommended teaching speed; teaching can be slower, but the slower speed is recorded in the experimental conditions and is not written back into the specification. Do not borrow slope-climbing or positioning figures from another page for a page that does not list them. Whether mobile manipulation applies is determined by whether this row includes ground locomotion, not by whether the paper used a mobile base. The teaching speed can be lower, but the lower speed is recorded in the conditions and does not change the published capability in this row.
Power. Rated voltage 24 V. Rated / maximum current 1.9 / 5.7 A. Rated / maximum power 45.6 / 136.8 W. No battery capacity, no runtime hours. This row retains only the electrical terms that appear on the page: voltage, capacity, runtime, charging, current, or power. If there are no "hours", write runtime as not provided — do not fill in hours from a neighboring page. Do not rename charging time as runtime. Rated and maximum must be listed in separate columns. Keep "approx." for approximate values. Amp-hours from multiple devices must not be summed and presented as one device's battery. The paper does not provide runtime for this row. Hours, charging, or current that do not appear remain as not provided and must not be copied in from other pages.
Perception and computing. Communication interface: 6-pin aviation connector. Communication protocol: RS485 / Modbus-RTU. Operating environment: 0–50 °C, relative humidity ≤85%. There is no camera on the page. This line inventories the items already specified in sensors, computing, or communication, and retains the terms standard, included, optional, and optional-order. Optional items that are not checked do not count. If the cover conflicts with the list, cite the list while not pretending the cover's statement does not exist. Headsets and gloves do not enter this line. Processors, hard-drive capacity, or camera channel counts that are not written out must not be drawn into the system diagram. The number of cameras in the paper is not the channel count for this line. Optional sensors that were not purchased do not enter this data dictionary.
End effector. It is itself the end effector. Whether it directly matches the body's flange, wiring harness, and protocol must be confirmed on the configuration sheet; the page states that plug-and-play is not the default. This line describes which end contact or gripping occurs at. Quick-change, compatible, and recommended are not models already included in the box. The finger-ring fixture on the main arm is not a distal gripper. Force, stroke, and load remain as written in their respective rows; they are not merged into a single system metric because they are mounted on a particular body. Flange and protocol mappings that are not given should be written as "to be confirmed," not as plug-and-play. The gripper from the paper is not the end effector delivered by this row. "Supports" or "compatible" without a model number cannot be treated as delivered.
Boundary. The standard quantity table for the lift model does not include this gripper. The folding model states quick-change capability, not that RMG22-65 is already in the box. The recommended item CTAG2F90-D is also not this model. This row is a boundary deliberately separated on the page: another model, another column, another product page, or an interface that still requires project confirmation after modularization. The boundary is not a defect note; it is to prevent verbally buying two pages as one. When writing the proposal, copy the boundary into "not included in this order." If equipment not included is added later, open a new configuration sheet instead of retroactively changing the robotic platform name in old samples. Embodied differences are exactly the boundary to preserve; do not delete them for the sake of "unification." Equipment within the boundary must be ordered separately; do not rename old samples to imply it is already included.
Configuration column. The order must specify model RMG22-65, along with which robotic platform it is mounted on, the quantity, and whether it replaces other gripper models listed in that platform's recommended column. This row distinguishes standard, recommended, and optional. Recommended and optional items are not delivered unless checked. If the standard row and the parameter table row are inconsistent, keep both rows and use "locked for this order" to indicate which one is actually delivered, rather than striking out one row in the order without signing off. Prices and lead times are not included in the paraphrase of this row. Unchecked configurations cannot be described as the same system as in the paper. Unchecked recommended and optional items must be written as not delivered on the order.
May be excerpted. Copy into the attachment line by line: envelope 5 kg; recommended friction load 2 kg; maximum gripping force 130 N; stroke 65 mm; finger height 80 mm; 745 g; opening/closing 2 s; repeatability ±0.05 mm; 24 V; 1.9/5.7 A; 45.6/136.8 W; RS485 / Modbus-RTU. This is the type of line that can be pasted into the attachment: it has a subject, has units, and can be traced back to the original sentence on the product page. When pasting, retain words such as "approximately", "excluding", "not specified", "optional", and "recommended". Do not convert and keep only the result. If the same number has different meanings on two pages, write it as two separate lines in the attachment. Do not mix test protocols into the specification excerpt. A proposal may state the source of a problem, but must not state a paper's success rate. When pasting into the attachment, paste the words "approximately", "excluding", and "optional" along with the numbers.
Do not write. Do not convert 130 N to 5 kg and delete the original line. Do not write ±0.05 mm as the repeatability of the connected robotic arm. Do not write battery life. This line is a negative sentence for review purposes. It does not describe what the device can do; it only prevents hours, degrees of freedom, load subjects, or cover slogans from adjacent pages from being written in. If a negative sentence is matched, revert to the original sentence on the product page; do not interpret it as "approximately". Success rates from external papers and total hours not published on this site must likewise not be written in. Sentences such as "using the system from that paper" are prohibited. If a manuscript search matches a negative sentence, revert to the original sentence on the product page.
| Projects | Public-Facing Positioning of This Page |
|---|---|
| Degrees of Freedom | This is an end-effector gripper, not a multi-joint arm. The public table does not give the gripper a "degree of freedom" integer; do not fabricate one to align with other platforms. |
| Load and Mass | Maximum envelope grasp payload 5 kg. Recommended maximum friction payload 2 kg. Maximum clamping force 130 N. These three numbers cannot all be written as the same 5. |
| Form Factor and Scale | Overall dimensions 112 × 60 × 167 mm. Stroke 65 mm. Finger height 80 mm. Body weight 745 g. |
| Operating Range | The 65 mm stroke is the finger opening distance, not the robotic arm reach, nor the platform's vertical working range. |
| Motion | Open / close time 2 s. Positional repeatability ±0.05 mm. The 2 seconds is the specification for the open or close time, not the control frequency. |
| Power | Rated voltage 24 V. Rated / maximum current 1.9 / 5.7 A. Rated / maximum power 45.6 / 136.8 W. No battery capacity, no battery life in hours. |
| Perception & Compute | Communication interface: 6-pin aviation connector. Communication protocol: RS485 / Modbus-RTU. Operating environment: 0–50 °C, relative humidity ≤85%. There is no camera on the page. |
| End Effector | It is itself the end-effector. Whether it directly matches the flange, wiring harness, and protocols of the platform must be confirmed on the configuration sheet; the page states that plug-and-play is not the default. |
| Boundary | The standard quantity table for the lift model does not include this gripper. The folding model lists quick-change capability, not that the RMG22-65 is already in the box. The recommended item CTAG2F90-D is also not this model. |
| Configuration Panel | The order should specify model RMG22-65, and state which platform it is mounted on, the quantity, and whether it replaces other gripper models listed in that platform's recommended column. |
| Excerptable | Attachment specifications listed line by line: envelope 5 kg; recommended friction 2 kg; maximum gripping force 130 N; stroke 65 mm; finger height 80 mm; 745 g; open/close time 2 s; repeatability ±0.05 mm; 24 V; 1.9/5.7 A; 45.6/136.8 W; RS485 / Modbus-RTU. |
| Do not write | Do not convert 130 N to 5 kg and then delete the original row. Do not write ±0.05 mm as the repeatability of the attached robotic arm. Do not state battery life. |

Relationship to Public Methods and Adjacent Pages
Placing the product in the literature is to illustrate what data capture problems look like, not to borrow the paper's experimental conclusions. Public works that can be explicitly cited include: dual-arm master-slave teleoperation and action-chunked imitation learning as represented by ALOHA; mobile dual-arm demonstration as represented by Mobile ALOHA; learning visuomotor policies from demonstrations as represented by Diffusion Policy; handheld gripper capture as represented by UMI, which is deliberately not a full robot; and cross-robot data aggregation as represented by Open X-Embodiment, provided the embodiment is labeled.
These works each use their own robots, tasks, and success definitions. TOBI did not participate in those experiments. This article does not transcribe their success rates, number of data records, or dollar costs. When readers need those figures, they should read the original papers.
What is useful for this product is only the checklist: whether the action space matches the slave end, which camera the observation comes from, whether the chassis moves, whether end-effector open/close is in the action vector, whether timestamps are aligned, and whether the robot unit identifier is written into the samples. Items on the checklist that the product page does not answer remain unanswered.
This article uses the literature to lay out the questions, then answers the ones that can be answered using the product's public specifications.
Before handing off to a colleague
When finalizing the literature section, delete all percentages and hours unless the sentence explicitly states "the following figures belong to the original paper and are not measured values of this product", and do not place the figures next to this product's specifications. Only the question list is retained. Questions that can be answered from the product page have their answers rewritten as the original sentences; questions that cannot be answered are left blank. Check the last sentence for an erroneous statement such as "the system adopted from that paper". If such a sentence exists, delete the section rather than adding a footnote to justify it. The literature section is limited to one page. Exceeding one page usually means experiment details have started to be restated. Delete the experiment details and keep only the questions. Questions are answered with original sentences from the product page or left blank. The footer is fixed with one sentence: the success rates, data scale, and costs of external papers belong to the original authors, are not measured values of this company, and do not constitute a test of the equipment in this document. A literature section without this footer sentence is not published.
First, the literature section should not exceed the question list.
Second, do not copy success rates.
Third, use the original sentence when it can answer the question.
Fourth, leave blank what cannot be answered.
Fifth, delete "adopts the system from that paper."
Sixth, the footer states that the figures belong to the original authors.
Continue Reading
- 01 Task Boundaries
- 02 Specification Standards
- 03 Degrees of Freedom
- 04 Payload & Self-Weight
- 05 Workspace
- 06 Locomotion Method
- 07 Perception and Computing
- 08 Power Specifications
- 09 Data Recording
- 10 Time Alignment
- 11 End-Effector Boundaries
- 12 Site Constraints
- 13 Configuration Sheet
- 14 Three-Way Comparison
- 15 Literature References
- 16 Master-Slave Workstation
- 17 Acceptable Deliverable Statements
- 18 Prohibited Conflations
- 19 On-Site Deployment
- 20 Evaluation Path
Back to Product Center View this product page
This article was written on October 3, 2026, for selection and specification verification purposes. Device parameters are subject to the product page tables and do not constitute a supply commitment. External papers only illustrate how problems are framed in the industry; their success rates and data scales belong to the original authors' experiments and are not TOBI's measured results. Phone: +86 137 5502 0164.