e

LeRobot ACT learned joint policy for OpenArm v2 right. 384 contact dabs with six palette wells in MuJoCo. Seven CAN tests, five configuration tests and a full one-dab runner cycle passed over virtual CAN. Video shows simulated arm motion. Physical arm and real paint NOT tested; hardware commissioning required. Scripted paint sequence, learned motor control.

e·Other robot

Neural joint and pigment policies trained on HIM L4 compute. Includes weights, TorchScript, training data, simulation, and evaluations. Scripted waypoints; ideal color-fed brush. Simulation only.

e·I2RT YAM

Continued as OpenArm Mona Lisa — LeRobot ACT: https://arena.himrobotics.com/uploads/source_59ffd3291f3623fc498d . The new version includes a learned joint policy and an articulated simulator video. This older ROS 2 archive has scripted motor primitives and a motion-plan diagram; its physical-arm validation is still incomplete.

e·Other robot

A trained PPO policy (no keyframes, no scripted launch) kicks a randomly spawned ball into the goal with real foot-ball contact: 32/32 goals in held-out eval. Reproduce with ./run_policy.sh

e·Unitree G1

A Unitree G1 taps a strike on a neon micro-lane. Scripted MuJoCo demo — kinematically posed robot, deterministic launch, real physics for ball and pins, measured 3/3 knockdown. Not a trained controller.

e·Unitree G1