[Bug Report] Unable to run example add a new robot to Isaac Lab #5480

Activity

1. RandomOakForest commented on May 7, 2026

   

   RandomOakForest

   on May 7, 2026

   Collaborator

   More actions

   Thank you for posting this. The team will review it and follow up.
2. RandomOakForest

   added

   bugSomething isn't workingSomething isn't working

   on May 7, 2026
3. Exokern commented on May 7, 2026

   

   Exokern

   on May 7, 2026

   More actions

   This looks like a type mismatch between the tutorial and the PhysX backend:

   • The tutorial scripts/tutorials/01_assets/add_new_robot.py builds action = torch.Tensor([[10.0, 10.0]]) (a torch.Tensor).
   • BaseArticulation.set_joint_velocity_target() forwards that into set_joint_velocity_target_index(), which ends up calling wp.launch(...) in isaaclab_physx/assets/articulation/articulation.py.
   • Warp expects a wp.array there; the error you see (expects array(ndim=2, dtype=float32), but passed value has type Tensor) is consistent with passing a torch tensor straight into a Warp kernel.

   Quick workaround in the tutorial: make action a wp.array (float32, correct device) before calling set_joint_velocity_target[_index].

   Upstream fix options (small):

   1. Fix the tutorial to pass a wp.array.
   2. Or make set_joint_velocity_target_index() accept torch.Tensor and internally convert to a wp.array before the wp.launch(...) call (so the public API can consistently accept torch inputs).

   Happy to send a tiny PR for either approach if maintainers have a preference.
4. RandomOakForest commented on May 7, 2026

   

   RandomOakForest

   on May 7, 2026

   Collaborator

   More actions

   Following up, the team is actively working to resolve this. @kellyguo11 for vis.
5. lqxisok commented on May 8, 2026

   

   lqxisok

   on May 8, 2026

   More actions

   The follow code works well for me:

     # drive around
     if count % 100 < 75:
         # Drive straight by setting equal wheel velocities
         action = wp.from_torch(torch.Tensor([[10.0, 10.0]]).cuda())
     else:
         # Turn by applying different velocities
         action = wp.from_torch(torch.Tensor([[5.0, -5.0]]).cuda())
   
6. theunknowninfinite commented on May 12, 2026

   

   theunknowninfinite

   on May 12, 2026

   Last edited by theunknowninfinite

   Author

   More actions

   @Exokern @lqxisok Thank you for your suggestions.
   I tried using your code snippets but I get this error.

   Traceback (most recent call last):
     File "/home/infinity/isaac_scripts/lab_config_test.py", line 188, in <module>
       main()
     File "/home/infinity/isaac_scripts/lab_config_test.py", line 184, in main
       run_simulator(sim, scene)
     File "/home/infinity/isaac_scripts/lab_config_test.py", line 114, in run_simulator
       root_jetbot_pose = scene["Jetbot"].data.default_root_pose.torch.clone()
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
   AttributeError: 'array' object has no attribute 'torch'
   

   For which when checking the type , it is of <class 'warp._src.types.array'>.
7. theunknowninfinite commented on May 12, 2026

   

   theunknowninfinite

   on May 12, 2026

   Author

   More actions

   I tried using wp.from_torch
   The script seems to run but however there's no UI popping up and I can see this in the terminal.
   I had to pass the args -viz kit . My bad.
   The code works now with the edited code in the section below.

   Modified Code

   # Copyright (c) 2022-2026, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md).
   # All rights reserved.
   #
   # SPDX-License-Identifier: BSD-3-Clause
   
   import argparse
   
   from isaaclab.app import AppLauncher
   
   # add argparse arguments
   parser = argparse.ArgumentParser(
       description="This script demonstrates adding a custom robot to an Isaac Lab environment."
   )
   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
   
   import numpy as np
   import torch
   import warp as wp
   
   
   import isaaclab.sim as sim_utils
   from isaaclab.actuators import ImplicitActuatorCfg
   from isaaclab.assets import AssetBaseCfg
   from isaaclab.assets.articulation import ArticulationCfg
   from isaaclab.scene import InteractiveScene, InteractiveSceneCfg
   from isaaclab.utils.assets import ISAAC_NUCLEUS_DIR
   
   JETBOT_CONFIG = ArticulationCfg(
       spawn=sim_utils.UsdFileCfg(usd_path=f"{ISAAC_NUCLEUS_DIR}/Robots/NVIDIA/Jetbot/jetbot.usd"),
       actuators={"wheel_acts": ImplicitActuatorCfg(joint_names_expr=[".*"], damping=None, stiffness=None)},
   )
   
   DOFBOT_CONFIG = ArticulationCfg(
       spawn=sim_utils.UsdFileCfg(
           usd_path=f"{ISAAC_NUCLEUS_DIR}/Robots/Yahboom/Dofbot/dofbot.usd",
           rigid_props=sim_utils.RigidBodyPropertiesCfg(
               disable_gravity=False,
               max_depenetration_velocity=5.0,
           ),
           articulation_props=sim_utils.ArticulationRootPropertiesCfg(
               enabled_self_collisions=True, solver_position_iteration_count=8, solver_velocity_iteration_count=0
           ),
       ),
       init_state=ArticulationCfg.InitialStateCfg(
           joint_pos={
               "joint1": 0.0,
               "joint2": 0.0,
               "joint3": 0.0,
               "joint4": 0.0,
           },
           pos=(0.25, -0.25, 0.0),
       ),
       actuators={
           "front_joints": ImplicitActuatorCfg(
               joint_names_expr=["joint[1-2]"],
               effort_limit_sim=100.0,
               velocity_limit_sim=100.0,
               stiffness=10000.0,
               damping=100.0,
           ),
           "joint3_act": ImplicitActuatorCfg(
               joint_names_expr=["joint3"],
               effort_limit_sim=100.0,
               velocity_limit_sim=100.0,
               stiffness=10000.0,
               damping=100.0,
           ),
           "joint4_act": ImplicitActuatorCfg(
               joint_names_expr=["joint4"],
               effort_limit_sim=100.0,
               velocity_limit_sim=100.0,
               stiffness=10000.0,
               damping=100.0,
           ),
       },
   )
   
   
   class NewRobotsSceneCfg(InteractiveSceneCfg):
       """Designs the scene."""
   
       # Ground-plane
       ground = AssetBaseCfg(prim_path="/World/defaultGroundPlane", spawn=sim_utils.GroundPlaneCfg())
   
       # lights
       dome_light = AssetBaseCfg(
           prim_path="/World/Light", spawn=sim_utils.DomeLightCfg(intensity=3000.0, color=(0.75, 0.75, 0.75))
       )
   
       # robot
       Jetbot = JETBOT_CONFIG.replace(prim_path="{ENV_REGEX_NS}/Jetbot")
       Dofbot = DOFBOT_CONFIG.replace(prim_path="{ENV_REGEX_NS}/Dofbot")
   
   
   def run_simulator(sim: sim_utils.SimulationContext, scene: InteractiveScene):
       sim_dt = sim.get_physics_dt()
       sim_time = 0.0
       count = 0
   
       while simulation_app.is_running():
           # reset
           if count % 500 == 0:
               # reset counters
               count = 0
               # reset the scene entities to their initial positions offset by the environment origins
               root_jetbot_pose = wp.to_torch(scene["Jetbot"].data.default_root_pose).clone()
               root_jetbot_pose[:, :3] += scene.env_origins
               root_dofbot_pose = wp.to_torch(scene["Dofbot"].data.default_root_pose).clone()
               root_dofbot_pose[:, :3] += scene.env_origins
   
               # copy the default root state to the sim for the jetbot's orientation and velocity
               scene["Jetbot"].write_root_pose_to_sim_index(root_pose=root_jetbot_pose)
               root_jetbot_vel = wp.to_torch(scene["Jetbot"].data.default_root_vel).clone()
               scene["Jetbot"].write_root_velocity_to_sim_index(root_velocity=root_jetbot_vel)
               scene["Dofbot"].write_root_pose_to_sim_index(root_pose=root_dofbot_pose)
               root_dofbot_vel = wp.to_torch(scene["Dofbot"].data.default_root_vel).clone()
               scene["Dofbot"].write_root_velocity_to_sim_index(root_velocity=root_dofbot_vel)
   
               # copy the default joint states to the sim
               joint_pos, joint_vel = (
                   wp.to_torch(scene["Jetbot"].data.default_joint_pos).clone(),
                   wp.to_torch(scene["Jetbot"].data.default_joint_vel).clone(),
               )
               scene["Jetbot"].write_joint_position_to_sim_index(position=joint_pos)
               scene["Jetbot"].write_joint_velocity_to_sim_index(velocity=joint_vel)
               joint_pos, joint_vel = (
                   wp.to_torch(scene["Dofbot"].data.default_joint_pos).clone(),
                   wp.to_torch(scene["Dofbot"].data.default_joint_vel).clone(),
               )
               scene["Dofbot"].write_joint_position_to_sim_index(position=joint_pos)
               scene["Dofbot"].write_joint_velocity_to_sim_index(velocity=joint_vel)
               # clear internal buffers
               scene.reset()
               print("[INFO]: Resetting Jetbot and Dofbot state...")
   
           # drive around
           if count % 100 < 75:
               # Drive straight by setting equal wheel velocities
               action = torch.Tensor([[10.0, 10.0]])
               # action=wp.from_torch(action).device('cuda:0')
               action = wp.from_torch(torch.Tensor([[10.0, 10.0]]).cuda())
           else:
               # Turn by applying different velocities
               action = torch.Tensor([[5.0, -5.0]])
               # action=wp.from_torch(action).device('cuda:0')
               action = wp.from_torch(torch.Tensor([[10.0, 10.0]]).cuda())
   
           scene["Jetbot"].set_joint_velocity_target(action)
   
           # wave
           wave_action = wp.to_torch(scene["Dofbot"].data.default_joint_pos)
           wave_action[:, 0:4] = 0.25 * np.sin(2 * np.pi * 0.5 * sim_time)
           scene["Dofbot"].set_joint_position_target_index(target=wave_action)
   
           scene.write_data_to_sim()
           sim.step()
           sim_time += sim_dt
           count += 1
           scene.update(sim_dt)
   
   
   def main():
       """Main function."""
       # Initialize the simulation context
       sim_cfg = sim_utils.SimulationCfg(device=args_cli.device)
       sim = sim_utils.SimulationContext(sim_cfg)
       sim.set_camera_view([3.5, 0.0, 3.2], [0.0, 0.0, 0.5])
       # Design scene
       scene_cfg = NewRobotsSceneCfg(args_cli.num_envs, env_spacing=2.0)
       scene = InteractiveScene(scene_cfg)
       # Play the simulator
       sim.reset()
       # Now we are ready!
       print("[INFO]: Setup complete...")
       # Run the simulator
       run_simulator(sim, scene)
   
   
   if __name__ == "__main__":
       main()
       simulation_app.close()

   👍React with 👍1Reacted by Pablo Hennings
8. CarlosEngler commented on Jun 19, 2026

   

   CarlosEngler

   on Jun 19, 2026

   More actions

   I had a problem in this tutorial aswell. When executing add_new_robot.py with whichever number assigned to num_envs i get the following problem:

   Command:
   ./isaaclab.sh -p scripts/tutorials/01_assets/add_new_robot.py --num_envs 2 --viz kit

   Error:

   Traceback (most recent call last):
     File "/workspace/isaaclab/scripts/tutorials/01_assets/add_new_robot.py", line 187, in <module>
       main()
     File "/workspace/isaaclab/scripts/tutorials/01_assets/add_new_robot.py", line 177, in main
       scene = InteractiveScene(scene_cfg)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^
     File "/workspace/isaaclab/source/isaaclab/isaaclab/scene/interactive_scene.py", line 138, in __init__
       cfg.validate()
     File "/workspace/isaaclab/source/isaaclab/isaaclab/utils/configclass.py", line 381, in _validate
       raise TypeError(
   TypeError: Missing values detected in object NewRobotsSceneCfg for the following fields:
     - num_envs
   

   I think the problem happens due to num_envs, defined in ArgumentParser, never being assigned in NewRobotsSceneCfg(). The solution i got to this problem is by simply changing the call of NewRobotsSceneCfg() in function main to:

   scene_cfg = NewRobotsSceneCfg(num_envs=args_cli.num_envs, env_spacing=2.0)

   I tested this and got this problem both running locally and through docker, using the branch develop of IsaacLab and IsaacSim 6.0.0.

   Another thing I saw is that in the tutorial the code snippet for the run_deformable function is incomplete.

   I'm happy to send a PR if it's correct and appreciated!
9. AntoineRichard

   assigned

   matthewtrepte

   on Sep 3, 2026
10. matthewtrepte commented on Oct 19, 2026

    

    matthewtrepte

    on Oct 19, 2026

    Collaborator

    More actions

    should be fixed (PR #7327 and #7120). the tutorial now builds its action tensors on sim.device and the articulation setters accept torch tensors or warp arrays. closing as fixed. pls reopen if you still hit it
11. matthewtrepte

    closed this as completedon Oct 19, 2026