so-arm100

Isaac Lab external project for SO-ARM100/101 arm robot.

3D-printed parallel gripper compatible with Feetech STS3215 and Waveshare ST3215 servos. Ready-to-use solution for the SO-ARM 100/SO-ARM 101.

ROS 2–based SO-ARM100 Reinforcement Learning System

HALO is a live multimodal robot agent for real-time manipulation. It combines natural voice interaction, scene understanding, narrated execution, and autonomous skill orchestration in a robotics runtime designed for continuous control.

Plugins for Robonine Lab

Lightweight per-camera scalar gating for multi-view robot imitation learning — plug-in module for LeRobot ACT, no stage annotations required.

SmolVLA (450M VLA) fine-tuned for language-conditioned pick-and-place on free-tier compute: 0% -> 55% -> 90%, incl. a cross-architecture data study vs ACT

End-to-end imitation learning on a MuJoCo SO-ARM100 work-cell: scripted expert -> LeRobotDataset -> ACT -> domain-randomization robustness study (90% nominal, 87-100% under DR)

teaching a robot arm by hand

WebXR teleoperation for LeKiwi (SO-101 arm + omni base) and other SO-101 robots from a Meta Quest headset — closed-form kinematics, no APK, no Unity

From-scratch RGB-D perception-to-grasp pipeline in MuJoCo: segmentation -> point cloud -> 6-DoF pose (yaw-sweep + trimmed ICP, 0.58mm) -> grasp -> closed-loop pick (20/20)

RL + from-scratch world model on the SO-ARM100 work-cell: CEM-MPC 100% at 8k env steps (37x fewer than PPO); SAC lift-and-hold via a 4-stage reward study