Our colleague Vladimir Osipov equipped the SO-ARM100 parallel gripper with FSR402 force sensors to enable delicate object handling with real-time grip force feedback. The sensor detects forces as low as 0.2N, while the target grip force is tuned per object — around 5N for a cherry tomato — to account for the limited torque precision of STS3215 servos and prevent slipping. This allows the gripper to grasp soft objects gently, detect slippage, and automatically retry the grip.
We stress-test the FEETECH STS3215: real backlash (0.87° measured vs spec), repeatability, speed accuracy, stall torque above rating, and thermal overload behavior under continuous load. Practical implications for robot arms and grippers.
Robonine (Educational Robotics) completed a structural optimization of our 6-DOF robotic manipulator after a structural optimization study. By increasing structural rigidity through topology optimization and design refinement, we reduced end-effector deflection by over 60% (from ~1.05 mm to ~0.41 mm) and improved motion stability. The final configuration delivers higher precision and reliability for industrial applications.
Our engineer Alan from https://robonine.com/ (Educational Robotics) integrated Feetech STS3250 and STS3215 servo motors into the prototype and completed the first test run of a 6-DOF semi-SCARA manipulator.
During motion, the structure demonstrates high stiffness with no visible backlash or mechanical play. The kinematic chain remains stable throughout the test trajectory, confirming the rigidity of the mechanical design and joint assembly.
The next stage includes full assembly with all actuators operating in backlash compensation mode, followed by quantitative measurement of positioning accuracy and repeatability.
Our engineer Alan from https://robonine.com team has assembled the mechanical frame of our 6-DoF manipulator prototype - without servo motors for now. At this stage we are evaluating how easy the structure is to assemble, checking for any mechanical play, and validating the kinematics.
Good news: the structure feels solid and Alan reports no detectable backlash so far.
We tested the maximum dynamic payload of the SO-ARM101 with our parallel gripper and a base servo replaced by a Feetech STS3250. The maximum load before failure was 630 g, at which point the Feetech STS3215 in joint 3 failed — its large brass output gear was completely worn down.
The Feetech STS3250 in the base with a metal gear train withstood a significantly higher load.
Next week, we will release full documentation for the SO ARM 101 with a parallel gripper, featuring leader and follower arms and support for widely used stereo cameras.
Update: Our engineer Alan has received a batch of components for the manipulator assemblies — including clamps and metal bracket parts. Prototype assembly is planned for the beginning of next year.
Publishing our research on dual-motor backlash compensation for STS3215 servos. To complete our arXiv submission, we need a quick endorsement from someone who has published in robotics (cs.RO/eess.SY).
If you can help, here’s the code: L64QM3 Thank you!
• Together, we applied advanced topology optimization to redesign critical brackets of the manipulator, achieving a 57–76% reduction in structural deflection.
• Our updated model also demonstrated a major stress decrease — from 93 MPa down to 25 MPa — all while staying within the allowed weight increase.
• Although we didn’t fully reach the target tip deviation of 0.3 mm (best achieved: 0.41 mm), the project gave us valuable insights and a solid foundation for the next design iteration.
We tested the mechanical backlash of the Feetech STS3250 servo. Using an 86 mm lever arm, we measured a tip displacement of 0.64 mm, which corresponds to an angular backlash of approximately 0.43°.
According to the datasheet, the maximum allowable backlash is 0.5°, so our measured value of 0.43° falls within the specified limit.
Robonine are starting work on the next version of the SO ARM 102 manipulator. The version will be open source and agreed upon with @therobotbuilder the creator of the original manipulator.
We are planning to:
- increase positioning accuracy by approximately 2x using Feetech STS 3250 motors - increase working payload from 200g to 300g - increase rigidity using parametric design optimization and stiffer plastic - increase length to 550 mm - increase folding angles - use ISO 9409-1-50-4-M6 mounting standard for the gripper - use a parallel gripper in the default version - update the mounting plate for different camera types, M3 grid with 12.5 mm pitch - add table mounting standard 80x80 M8
The number of degrees of freedom and basic kinematics will remain the same.
Are there other things missing for working with SO ARM 100?
- Any standard inputs/outputs, for example? - Status indicators? - Perhaps some types of mounting for third-party grippers are more preferable? - Anything else?
FEETECH STS3250 Stall Torque and Repeatability Tests
We recently tested the FEETECH STS3250 servo, comparing actual performance with the official specifications. While the datasheet lists a stall torque of 50 kg·cm at 12 V, our real-world measurements showed:
- 25 kg·cm sustained torque after protection activation - Up to 48 kg·cm peak torque for a split second
Although the built-in protection limits continuous stall torque, the servo demonstrated excellent stability and control precision.
Precision and Repeatability: - Repeatability tolerance: ±0.02 mm at the end of a 95 mm arm - Smooth motion response with PID control and 12-bit (4096-step) magnetic encoder - Reliable performance for high-accuracy robotics and automation applications
Load test conducted on the Feetech STS3250 servo motor.
With a 2 kg load on a 100 mm arm, the motor operated near its limit. At higher acceleration settings, lifting performance decreased noticeably. The temperature increased from 40 °C to 70 °C within 8 minutes. The test highlights the torque and thermal constraints under sustained load conditions.
Robonine, we applied topology optimization to enhance the stiffness and efficiency of a robotic manipulator. Using HyperMesh with the OptiStruct solver, we defined the design space where each element had a pseudo-density coefficient (0–1) controlling stiffness. This allowed the algorithm to continuously redistribute material toward regions with higher strain energy — much like how a fluid naturally flows to balance pressure.
Results: - Aluminum bracket: displacement reduced by 0.16 mm - Steel bracket: displacement reduced from 1.05 mm → 0.63 mm - Steel clamp: displacement reduced by 0.14 mm - Final structure: optimized geometry with improved load distribution and reduced deformation
This project highlights how advanced structural optimization can significantly improve performance while minimizing material usage — shaping the next generation of robotic design.
Robonine team we recently verified the rotational speed of the Feetech STS3250 servo motor (12 V, 50 kg·cm torque, magnetic encoder) to compare measured performance with the official specification.
According to the datasheet: - Rated speed: 0.133 s per 60°
Calculation: - 0.133 s × 6 = 0.798 s per full rotation - 1 / 0.798 = 1.253 revolutions per second - 1.253 × 60 = 75.2 RPM
This confirms the official specification of approximately 75 RPM at 12 V under no load.
Our measurement: - Encoder output: 5,300 values per second - Encoder resolution: 4,096 counts per revolution
Result: The measured value differs by only about 2–3% from the datasheet specification, confirming that the STS3250 performs very close to its rated no-load speed. This close agreement validates both the servo’s performance and our measurement approach.
Robonine team created a HEX mesh and started analyzing our 6DOF robotic arm model's stiffness. Our goal is to achieve a maximum displacement of 0.3 mm under full load!
We’re preparing an in-depth review of the Feetech STS-3250 servo motor — exploring its performance, features. One of the top serial bus servo for hobby robotics compatible with SO-ARM 100 manipulator.
