-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Replies: 1 comment · 4 replies
-
Hi there, here's an example for modifying the robot in an existing environment with the direct workflow - https://isaac-sim.github.io/IsaacLab/main/source/tutorials/03_envs/modify_direct_rl_env.html. The concept should also be similar with the manager-based workflow, which shouldn't require the additional modifications on the actions/observations spaces and joint gears in the tutorial. The |
Beta Was this translation helpful? Give feedback.
All reactions
-
Thank you, I will review this tutorial and try to modify it. Can you explain how to run with the --enable camera flag? I am running the examples from the tutorial in Visual studio by pressing play on the code. And if I am changing a task from one to another, how do I know what attributes does the new one need to define? |
Beta Was this translation helpful? Give feedback.
All reactions
-
Beta Was this translation helpful? Give feedback.
All reactions
-
Thank you for posting this. The way you are running the example is correct, but you are running into a python environment issue with your setup or your import statement is misplaced. Could you share the |
Beta Was this translation helpful? Give feedback.
All reactions
-
Hi, I think there is a problem with the Isaac-Stack-Cube-Franka-v0 enviroment. Iv'e modified the original enviroment and I was able to run the task as an environment, but when I wanted to train franka with sb3, I couldn’t run the script. Attaching it here, there aren’t many changes from the example environment of franka stacking cubes (I couldn’t run the original environment either, attached after the code): import omni.isaac.lab.sim as sim_utils from omni.isaac.lab.scene import InteractiveSceneCfg from omni.isaac.lab_tasks.manager_based.manipulation.stack import mdp Pre-defined configsfrom omni.isaac.lab.markers.config import FRAME_MARKER_CFG # isort: skip @configclass
@configclass
@configclass
@configclass
@configclass
@configclass
@configclass ####refer @configclass
@configclass got these warnings:
During handling of the above exception, another exception occurred: Traceback (most recent call last):
Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace. When I tried to train with the original Isaac-Stack-Cube-Franka-v0, I got these warnings: |
Beta Was this translation helpful? Give feedback.
-
Hi,
I want to create a simple simulation of the Franka robot stacking cubes task, and record her arm position for a later use. I've started by trying to implement the stack cube task for the Franka robot in a manager based enviroment, like in the example from the toturial for creating a manager RL enviroment:
https://isaac-sim.github.io/IsaacLab/main/source/tutorials/03_envs/create_manager_rl_env.html
Currently I am facing the problem of defining the camera "AttributeError: 'Camera' object has no attribute '_is_outdated'", and how to use policy when it is Franka env and not cartpole.
Is there any document/tutorial on how to replace a robot in the simulation (for example from cartpole to franka)? Or from one task to another? I would really appreciate your help!
This is the code I am working on:
import argparse
from omni.isaac.lab.app import AppLauncher
add argparse arguments
parser = argparse.ArgumentParser(description="franka manager based.")
parser.add_argument("--robot", type=str, default="franka_panda", help="Name of the robot.")
parser.add_argument("--num_envs", type=int, default=1, help="Number of environments to spawn.")
append AppLauncher cli args
AppLauncher.add_app_launcher_args(parser)
parse the arguments
args_cli = parser.parse_args()
launch omniverse app
app_launcher = AppLauncher(args_cli)
simulation_app = app_launcher.app
"""Rest everything follows."""
import torch
import omni.isaac.lab.sim as sim_utils
from omni.isaac.lab.assets import AssetBaseCfg
#from omni.isaac.lab.controllers import DifferentialIKController, DifferentialIKControllerCfg
#from omni.isaac.lab.managers import SceneEntityCfg
#from omni.isaac.lab.markers import VisualizationMarkers
#from omni.isaac.lab.markers.config import FRAME_MARKER_CFG
from omni.isaac.lab.scene import InteractiveScene, InteractiveSceneCfg
from omni.isaac.lab.utils import configclass
from omni.isaac.lab.utils.assets import ISAAC_NUCLEUS_DIR
#from omni.isaac.lab.utils.math import subtract_frame_transforms
Pre-defined configs
from omni.isaac.lab_assets import FRANKA_PANDA_HIGH_PD_CFG # isort:skip
from omni.isaac.lab.envs import ManagerBasedRLEnv
from omni.isaac.lab_tasks.manager_based.manipulation.stack.config.franka.stack_joint_pos_env_cfg import FrankaCubeStackEnvCfg
@configclass
class TableTopSceneCfg(InteractiveSceneCfg):
def main():
"""Main function."""
# create environment configuration
env_cfg = FrankaCubeStackEnvCfg()
env_cfg.scene.num_envs = args_cli.num_envs
# setup RL environment
env = ManagerBasedRLEnv(cfg=env_cfg)
if name == "main":
# run the main function
main()
# close sim app
simulation_app.close()
Thank you!
Beta Was this translation helpful? Give feedback.
All reactions