XvKuoMing/embryo_lab-locomotion-spot-fast

A locomotion policy for spot (fast) trained with embryo_lab on Isaac Lab task Isaac-Velocity-Flat-Spot-v0 and exported to TorchScript.

Deploy

Pull this checkpoint straight from the Hub -- no manual download:

from embryo_lab import World
from embryo_lab.robots import Spot
from embryo_lab.skills import Locomotion

robot = Spot(locomotion=Locomotion("hub:spot/fast"))
with World(robot=robot) as world:
    robot.locomotion.move(vx=1.0)
    while world.is_running:
        world.step()

Locomotion reads the metadata.json deploy contract beside the policy and World auto-pins the physics rate to training, so it drives correctly with no tuning.

Deploy contract (metadata.json)

  • physics_dt: 0.002 decimation: 10 action_scale: 0.75
  • observation terms: ['base_lin_vel', 'base_ang_vel', 'projected_gravity', 'velocity_commands', 'joint_pos', 'joint_vel', 'actions']
Downloads last month

-

Downloads are not tracked for this model. How to track
Video Preview
loading

Collection including XvKuoMing/embryo_lab-locomotion-spot-fast