Unfolding Robotics: Open-Source Shirt Folding from Data to Deployment
🤖
148
Teach a robot to fold t‑shirts with open‑source code
Nikita Bragin PRO
branikita
AI & ML interests
Founder of Robonine. Robotics for research and education
Recent Activity
liked a Space 4 days ago
lerobot/robot-folding reacted to theirpost with 🔥 10 days ago
SO-ARM 101 vs SO-ARM 102: stiffness
Same rig, same 300 g hanging from the gripper, dial indicator in the same spot.
• SO-ARM 101 — 7.5 mm
• SO-ARM 102 — 3.9 mm
About half the deflection. Both arms are built with printed servo dummies, so this is the structure being compared, not the motors. Parts printed at 25 % infill. posted an update 10 days ago
SO-ARM 101 vs SO-ARM 102: stiffness
Same rig, same 300 g hanging from the gripper, dial indicator in the same spot.
• SO-ARM 101 — 7.5 mm
• SO-ARM 102 — 3.9 mm
About half the deflection. Both arms are built with printed servo dummies, so this is the structure being compared, not the motors. Parts printed at 25 % infill.Organizations
liked a
Space 4 days ago
reacted to their post with 🔥 10 days ago
Post
95
SO-ARM 101 vs SO-ARM 102: stiffness
Same rig, same 300 g hanging from the gripper, dial indicator in the same spot.
• SO-ARM 101 — 7.5 mm
• SO-ARM 102 — 3.9 mm
About half the deflection. Both arms are built with printed servo dummies, so this is the structure being compared, not the motors. Parts printed at 25 % infill.
Same rig, same 300 g hanging from the gripper, dial indicator in the same spot.
• SO-ARM 101 — 7.5 mm
• SO-ARM 102 — 3.9 mm
About half the deflection. Both arms are built with printed servo dummies, so this is the structure being compared, not the motors. Parts printed at 25 % infill.
posted an update 10 days ago
Post
95
SO-ARM 101 vs SO-ARM 102: stiffness
Same rig, same 300 g hanging from the gripper, dial indicator in the same spot.
• SO-ARM 101 — 7.5 mm
• SO-ARM 102 — 3.9 mm
About half the deflection. Both arms are built with printed servo dummies, so this is the structure being compared, not the motors. Parts printed at 25 % infill.
Same rig, same 300 g hanging from the gripper, dial indicator in the same spot.
• SO-ARM 101 — 7.5 mm
• SO-ARM 102 — 3.9 mm
About half the deflection. Both arms are built with printed servo dummies, so this is the structure being compared, not the motors. Parts printed at 25 % infill.
reacted to their post with 🔥 15 days ago
Post
2221
SO-ARM 102 goes open source in the next few weeks.
What's new:
- A parallel gripper: the jaws stay parallel through the whole stroke instead of pivoting around the object as they close.
- PET-CF instead of PLA+ for a much stiffer frame.
- A topology-optimized structure.
- Wider joint rotation and folding range.
- STS3250 servos on the first shoulder joint.
Compared with the SO-ARM 101, that adds up to 2.5x the payload, roughly 2x better positioning accuracy, roughly 1.6x the movement speed, and about 36 mm more reach.
It runs on Hugging Face LeRobot, so the same tooling, training pipeline and tutorials for the SO-ARM 101 work on it from day one.
What's new:
- A parallel gripper: the jaws stay parallel through the whole stroke instead of pivoting around the object as they close.
- PET-CF instead of PLA+ for a much stiffer frame.
- A topology-optimized structure.
- Wider joint rotation and folding range.
- STS3250 servos on the first shoulder joint.
Compared with the SO-ARM 101, that adds up to 2.5x the payload, roughly 2x better positioning accuracy, roughly 1.6x the movement speed, and about 36 mm more reach.
It runs on Hugging Face LeRobot, so the same tooling, training pipeline and tutorials for the SO-ARM 101 work on it from day one.
- 1 reply
posted an update 15 days ago
Post
2221
SO-ARM 102 goes open source in the next few weeks.
What's new:
- A parallel gripper: the jaws stay parallel through the whole stroke instead of pivoting around the object as they close.
- PET-CF instead of PLA+ for a much stiffer frame.
- A topology-optimized structure.
- Wider joint rotation and folding range.
- STS3250 servos on the first shoulder joint.
Compared with the SO-ARM 101, that adds up to 2.5x the payload, roughly 2x better positioning accuracy, roughly 1.6x the movement speed, and about 36 mm more reach.
It runs on Hugging Face LeRobot, so the same tooling, training pipeline and tutorials for the SO-ARM 101 work on it from day one.
What's new:
- A parallel gripper: the jaws stay parallel through the whole stroke instead of pivoting around the object as they close.
- PET-CF instead of PLA+ for a much stiffer frame.
- A topology-optimized structure.
- Wider joint rotation and folding range.
- STS3250 servos on the first shoulder joint.
Compared with the SO-ARM 101, that adds up to 2.5x the payload, roughly 2x better positioning accuracy, roughly 1.6x the movement speed, and about 36 mm more reach.
It runs on Hugging Face LeRobot, so the same tooling, training pipeline and tutorials for the SO-ARM 101 work on it from day one.
- 1 reply
replied to their post 15 days ago
We are still testing it. I think we will be ready to pusblish it within the next few weeks.
reacted to their post with 🚀 5 months ago
Post
226
Hackernoon published our article on how semi-SCARA kinematics and mechanical design choices reduce the cost of a 6DOF manipulator without relying on expensive actuators.
https://hackernoon.com/building-a-budget-robot-arm-with-semi-scara-kinematics
https://hackernoon.com/building-a-budget-robot-arm-with-semi-scara-kinematics
posted an update 5 months ago
Post
226
Hackernoon published our article on how semi-SCARA kinematics and mechanical design choices reduce the cost of a 6DOF manipulator without relying on expensive actuators.
https://hackernoon.com/building-a-budget-robot-arm-with-semi-scara-kinematics
https://hackernoon.com/building-a-budget-robot-arm-with-semi-scara-kinematics
reacted to their post with 🔥 5 months ago
Post
1579
Our paper is now published in HardwareX!
"An open-source test stand for backlash measurement in low-cost UART servo motors" presents a ~$100 automated platform for measuring backlash in compact serial bus servos — no dial indicators, no probe contact force, fully scripted and repeatable.
All CAD files, control software, and analysis tools are open source.
Read the full article: https://www.hardware-x.com/article/S2468-0672(26)00027-1/fulltext
Appearing in HardwareX Volume 26 (June 2026): https://www.sciencedirect.com/journal/hardwarex/vol/26/suppl/Cf
"An open-source test stand for backlash measurement in low-cost UART servo motors" presents a ~$100 automated platform for measuring backlash in compact serial bus servos — no dial indicators, no probe contact force, fully scripted and repeatable.
All CAD files, control software, and analysis tools are open source.
Read the full article: https://www.hardware-x.com/article/S2468-0672(26)00027-1/fulltext
Appearing in HardwareX Volume 26 (June 2026): https://www.sciencedirect.com/journal/hardwarex/vol/26/suppl/Cf
posted an update 5 months ago
Post
1579
Our paper is now published in HardwareX!
"An open-source test stand for backlash measurement in low-cost UART servo motors" presents a ~$100 automated platform for measuring backlash in compact serial bus servos — no dial indicators, no probe contact force, fully scripted and repeatable.
All CAD files, control software, and analysis tools are open source.
Read the full article: https://www.hardware-x.com/article/S2468-0672(26)00027-1/fulltext
Appearing in HardwareX Volume 26 (June 2026): https://www.sciencedirect.com/journal/hardwarex/vol/26/suppl/Cf
"An open-source test stand for backlash measurement in low-cost UART servo motors" presents a ~$100 automated platform for measuring backlash in compact serial bus servos — no dial indicators, no probe contact force, fully scripted and repeatable.
All CAD files, control software, and analysis tools are open source.
Read the full article: https://www.hardware-x.com/article/S2468-0672(26)00027-1/fulltext
Appearing in HardwareX Volume 26 (June 2026): https://www.sciencedirect.com/journal/hardwarex/vol/26/suppl/Cf
reacted to their post with 🚀 5 months ago
Post
2599
We added multi-simulator support for our parallel gripper on the SO-ARM 100/101 arm. One URDF, one launch file, five physics engines: Gazebo, MuJoCo, Webots, CoppeliaSim, Isaac Sim.
The ROS2 package includes xacro descriptions, joint trajectory controllers, robot state publisher, and parameterized hardware interfaces for each simulator.
https://github.com/roboninecom/SO-ARM100-101-Parallel-Gripper
The ROS2 package includes xacro descriptions, joint trajectory controllers, robot state publisher, and parameterized hardware interfaces for each simulator.
https://github.com/roboninecom/SO-ARM100-101-Parallel-Gripper
posted an update 5 months ago
Post
2599
We added multi-simulator support for our parallel gripper on the SO-ARM 100/101 arm. One URDF, one launch file, five physics engines: Gazebo, MuJoCo, Webots, CoppeliaSim, Isaac Sim.
The ROS2 package includes xacro descriptions, joint trajectory controllers, robot state publisher, and parameterized hardware interfaces for each simulator.
https://github.com/roboninecom/SO-ARM100-101-Parallel-Gripper
The ROS2 package includes xacro descriptions, joint trajectory controllers, robot state publisher, and parameterized hardware interfaces for each simulator.
https://github.com/roboninecom/SO-ARM100-101-Parallel-Gripper
reacted to their post with 🔥 6 months ago
Post
3094
We have received the majority of components for our first small commercial batch of SO-ARM101 robotic arms. Feetech STS3250 servo drives, parallel gripper, and depth camera.
- 1 reply
posted an update 6 months ago
Post
3094
We have received the majority of components for our first small commercial batch of SO-ARM101 robotic arms. Feetech STS3250 servo drives, parallel gripper, and depth camera.
- 1 reply
reacted to their post with 🔥 6 months ago
Post
5638
Progress update on our Robonine mobile robotic platform. We've wired up the full electronics stack - Raspberry Pi, motor controllers, and a camera module - and added Bluetooth joystick and keyboard control with WiFi-based management. A 7 kg counterweight keeps the platform stable. Powered by a powerbank and ready to roll.
- 1 reply
posted an update 6 months ago
Post
5638
Progress update on our Robonine mobile robotic platform. We've wired up the full electronics stack - Raspberry Pi, motor controllers, and a camera module - and added Bluetooth joystick and keyboard control with WiFi-based management. A 7 kg counterweight keeps the platform stable. Powered by a powerbank and ready to roll.
- 1 reply
liked a
model 6 months ago
replied to their post 6 months ago
I'm not familiar with it.
reacted to their post with 🚀 6 months ago
Post
1874
Robonine just published a new article! Mechanical backlash is a common limitation in servo-driven robotic joints. In this experiment, paired Feetech STS3215 servos are used with a small opposing preload to eliminate gearbox play, significantly improving positional stability and motion precision in robotic manipulators.
https://robonine.com/backlash-compensation-in-sts3215-servo-actuators/
https://robonine.com/backlash-compensation-in-sts3215-servo-actuators/
- 2 replies
posted an update 6 months ago
Post
1874
Robonine just published a new article! Mechanical backlash is a common limitation in servo-driven robotic joints. In this experiment, paired Feetech STS3215 servos are used with a small opposing preload to eliminate gearbox play, significantly improving positional stability and motion precision in robotic manipulators.
https://robonine.com/backlash-compensation-in-sts3215-servo-actuators/
https://robonine.com/backlash-compensation-in-sts3215-servo-actuators/
- 2 replies