From ergonomic data
to joint references.
Trace TESOLLO’s published MANUS ROS 2 retargeting example into DG-5F-M joint references. Separate calibration, model selection and code evidence from tested deployment.
DROID RESEARCH · SOURCES CHECKED
MANUS ROS stream → DG-5F-M
TESOLLO publishes a ROS 2 retargeting node that maps MANUS ergonomic data into DG5F joint references. The model-specific package is identified as DG-5F-M by its parent workspace.
Read the pinned example ↗MANUS ergonomic stream→Rule-based retargeting→DG5F joint references→Physical controller
The example does not identify an exact MANUS glove or firmware combination. It is a rule-based mapping with calibration factors, not evidence of a tested production deployment or autonomous task success.
What the example actually establishes
| Boundary | Published evidence | Remaining check |
|---|---|---|
| Input | MANUS ROS messages containing ergonomic values. TESOLLO ↗ | The exact glove, SDK, firmware and license combination is unspecified. |
| Mapping | A heuristic maps 20 ergonomic values to 20 joints and applies calibration factors. TESOLLO ↗ | Operator proportions and task demands can require tuning. Matching vector lengths does not prove matching kinematics. |
| Output | Joint references go to the DG5F controller. The parent workspace identifies that model package as DG-5F-M. TESOLLO ↗ TESOLLO ↗ | Confirm left/right model, physical mode, limits and command-loss behavior. |
| Performance | Code and instructions are published. | No sustained uptime, task-success rate or independent end-to-end latency result is established in this review. |
A versioned interface is the useful deliverable.
- Record the exact glove and hand configuration beside the pinned retargeting commit. The generic MANUS input label must not become a claim that every glove model is compatible.
- Replay a known pose fixture through the mapper without physical motion. Check hand side, joint ordering, zero points, signs, scaling and limits before evaluating the task.
- Measure the whole loop after a supervised bring-up: capture timing, controller response, operator intervention, tracking loss and recovery. A successful retargeting clip is evidence of that demonstration, not autonomous production.
Source record
- MANUS stream to DG5F retargeting ↗TESOLLO · Commit 9e9af12; glove model and firmware unspecified · Checked 2026-11-10
- TESOLLO ROS 2 workspace and architecture limits ↗TESOLLO · Commit 1307f7d; pinned per-model submodules · Checked 2026-11-10
START WITH THE WORKFLOWBring us the task.
Request a project review Bring us the task.
Let’s find the fit.
Share your environment, the job to be done, and the outcome you need to measure.