Move each of the 14 servos of the robot duck, switch between its standing, sitting and folded poses and watch how the biped balances, all in your browser. Nothing to install and no robot needed.
Loading the physics engine…
Drag to turn the view, scroll or pinch to zoom.
Open your own files
Open a folder with an MJCF model (.xml) and its meshes to load a robot of your own, STL files with the same names to swap parts of this one, or an ONNX policy to let it drive the servos. You can also drop files onto the 3D view.
Record up to 60 simulation seconds or 12,000 samples. Downloads contain initial state, controls, trajectory, versions and file hashes; local model files stay on this device.
Playback sets the stored poses. Rerun requires matching engine/model/policy hashes and recomputes physics from recorded controls, without policy inference. Results need not match bit for bit across environments. The pose book lasts until this page closes.
Record an experiment or save the current pose.
Servo target angles (degrees)
What this simulator shows
The MuJoCo browser model represents 14 servo joints of the UNO Q robot duck. The physical build has 15 servos; the mouth servo (ID 34) is excluded from this simulation.
Sliders set servo targets. The built-in model uses an identified BAM servo approximation and bundled walking, recovery and action policies; simulated torque, friction and contact still differ from a physical robot.
This page runs browser simulation and ONNX inference, without robot firmware or a hardware connection. Use recorded experiments to inspect behavior; physical assembly, calibration and verification remain separate tasks.
Robot model by Luwu Dynamics, used with permission, based on Microduck by Pollen Robotics. Physics by MuJoCo (Apache-2.0). Walking, get-up and action policies by Luwu Dynamics, the same ones the Arduino UNO Q build runs, used with permission.