Updates pick place env to use steering wheel asset (#447)

<!--
Thank you for your interest in sending a pull request. Please make sure
to check the contribution guidelines.

Link:
https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html
-->

This change updates the Isaac-PickPlace-GR1T2-Abs-v0 env to use a
steering wheel asset instead of a metal rod. The steering wheel asset is
easier to grasp.

Changes:

1. Update Isaac-PickPlace-GR1T2-Abs-v0 to use steering wheel asset
2. Update Mimic docs to reflect the change

Fixes # (issue)

Fixes poor graspability of the object once it falls in the
Isaac-PickPlace-GR1T2-Abs-v0 env.

<!-- As you go through the list, delete the ones that are not
applicable. -->

- New feature (non-breaking change which adds functionality)
- This change requires a documentation update

- [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with
`./isaaclab.sh --format`
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have updated the changelog and the corresponding version in the
extension's `config/extension.toml` file
- [ ] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there

<!--
As you go through the checklist above, you can mark something as done by
putting an x character in it

For example,
- [x] I have done this task
- [ ] I have not done this task
-->

---------
Signed-off-by: Kelly Guo <kellyguo123@hotmail.com>
Co-authored-by: Kelly Guo <kellyg@nvidia.com>

docs/source/overview/teleop_imitation.rst

@@ -136,7 +136,7 @@ Pre-recorded demonstrations
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 We provide a pre-recorded ``dataset.hdf5`` containing 10 human demonstrations for ``Isaac-Stack-Cube-Franka-IK-Rel-v0``
-`here <https://omniverse-content-production.s3-us-west-2.amazonaws.com/Assets/Isaac/5.0/Isaac/IsaacLab/Mimic/dataset.hdf5>`_.
+`here <https://omniverse-content-production.s3-us-west-2.amazonaws.com/Assets/Isaac/5.0/Isaac/IsaacLab/Mimic/franka_stack_datasets/dataset.hdf5>`_.
 This dataset may be downloaded and used in the remaining tutorial steps if you do not wish to collect your own demonstrations.
 
 .. note::
@@ -307,10 +307,10 @@ By inferencing using the generated model, we can visualize the results of the po
          --checkpoint /PATH/TO/desired_model_checkpoint.pth
 
 
-Demo: Data Generation and Policy Training for a Humanoid Robot
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Demo 1: Data Generation and Policy Training for a Humanoid Robot
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. figure:: https://download.isaacsim.omniverse.nvidia.com/isaaclab/images/gr-1_pick_place.gif
+.. figure:: https://download.isaacsim.omniverse.nvidia.com/isaaclab/images/gr-1_steering_wheel_pick_place.gif
    :width: 100%
    :align: center
    :alt: GR-1 humanoid robot performing a pick and place task
@@ -352,11 +352,11 @@ This setup allows Isaac Lab Mimic to interpolate the right hand's trajectory acc
 Therefore, avoid moving the right hand while the left hand picks up the object and brings it to a stable position.
 
 
-.. |good_demo| image:: https://download.isaacsim.omniverse.nvidia.com/isaaclab/images/gr1_pick_place_good_human_demo.gif
+.. |good_demo| image:: https://download.isaacsim.omniverse.nvidia.com/isaaclab/images/gr-1_steering_wheel_pick_place_good_demo.gif
    :width: 49%
    :alt: GR-1 humanoid robot performing a good pick and place demonstration
 
-.. |bad_demo| image:: https://download.isaacsim.omniverse.nvidia.com/isaaclab/images/gr1_pick_place_bad_human_demo.gif
+.. |bad_demo| image:: https://download.isaacsim.omniverse.nvidia.com/isaaclab/images/gr-1_steering_wheel_pick_place_bad_demo.gif
    :width: 49%
    :alt: GR-1 humanoid robot performing a bad pick and place demonstration
 
@@ -459,7 +459,7 @@ Generate the dataset
 ^^^^^^^^^^^^^^^^^^^^
 
 If you skipped the prior collection and annotation step, download the pre-recorded annotated dataset ``dataset_annotated_gr1.hdf5`` from
-`here <https://omniverse-content-production.s3-us-west-2.amazonaws.com/Assets/Isaac/5.0/Isaac/IsaacLab/Mimic/dataset_annotated_gr1.hdf5>`_.
+`here <https://omniverse-content-production.s3-us-west-2.amazonaws.com/Assets/Isaac/5.0/Isaac/IsaacLab/Mimic/pick_place_datasets/dataset_annotated_gr1.hdf5>`_.
 Place the file under ``IsaacLab/datasets`` and run the following command to generate a new dataset with 1000 demonstrations.
 
 .. code:: bash
@@ -499,7 +499,7 @@ Visualize the results of the trained policy by running the following command, us
    --enable_pinocchio \
    --task Isaac-PickPlace-GR1T2-Abs-v0 \
    --num_rollouts 50 \
-   --horizon 250 \
+   --horizon 400 \
    --norm_factor_min <NORM_FACTOR_MIN> \
    --norm_factor_max <NORM_FACTOR_MAX> \
    --checkpoint /PATH/TO/desired_model_checkpoint.pth
@@ -507,7 +507,7 @@ Visualize the results of the trained policy by running the following command, us
 .. note::
    Change the ``NORM_FACTOR`` in the above command with the values generated in the training step.
 
-.. figure:: https://download.isaacsim.omniverse.nvidia.com/isaaclab/images/gr-1_pick_place_policy.gif
+.. figure:: https://download.isaacsim.omniverse.nvidia.com/isaaclab/images/gr-1_steering_wheel_pick_place_policy.gif
    :width: 100%
    :align: center
    :alt: GR-1 humanoid robot performing a pick and place task
@@ -516,8 +516,8 @@ Visualize the results of the trained policy by running the following command, us
    The trained policy performing the pick and place task in Isaac Lab.
 
 
-Demo: Visuomotor Policy for a Humanoid Robot
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Demo 2: Visuomotor Policy for a Humanoid Robot
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Download the Dataset
 ^^^^^^^^^^^^^^^^^^^^
@@ -526,6 +526,52 @@ Download the pre-generated dataset from `here <https://download.isaacsim.omniver
 The dataset contains 1000 demonstrations of a humanoid robot performing a pouring/placing task that was
 generated using Isaac Lab Mimic for the ``Isaac-NutPour-GR1T2-Pink-IK-Abs-Mimic-v0`` task.
 
+.. hint::
+
+   If desired, data collection, annotation, and generation can be done using the same commands as the prior examples.
+   **Note that the following commands are only for your reference and are not required for this demo.**
+
+   To collect demonstrations:
+
+   .. code:: bash
+
+      ./isaaclab.sh -p scripts/tools/record_demos.py \
+      --device cpu \
+      --task Isaac-NutPour-GR1T2-Pink-IK-Abs-v0 \
+      --teleop_device handtracking \
+      --dataset_file ./datasets/dataset_gr1_nut_pouring.hdf5 \
+      --num_demos 5 --enable_pinocchio
+
+   Since this is a visuomotor environment, the ``--enable_cameras`` flag must be added to the annotation and data generation commands.
+
+   To annotate the demonstrations:
+
+   .. code:: bash
+
+      ./isaaclab.sh -p scripts/imitation_learning/isaaclab_mimic/annotate_demos.py \
+      --device cpu \
+      --enable_cameras \
+      --rendering_mode balanced \
+      --task Isaac-NutPour-GR1T2-Pink-IK-Abs-Mimic-v0 \
+      --input_file ./datasets/dataset_gr1_nut_pouring.hdf5 \
+      --output_file ./datasets/dataset_annotated_gr1_nut_pouring.hdf5 --enable_pinocchio
+
+   To generate the dataset:
+
+   .. code:: bash
+
+      ./isaaclab.sh -p scripts/imitation_learning/isaaclab_mimic/generate_dataset.py \
+      --device cpu \
+      --headless \
+      --enable_pinocchio \
+      --enable_cameras \
+      --rendering_mode balanced \
+      --task Isaac-NutPour-GR1T2-Pink-IK-Abs-Mimic-v0 \
+      --generation_num_trials 1000 \
+      --num_envs 5 \
+      --input_file ./datasets/dataset_annotated_gr1_nut_pouring.hdf5 \
+      --output_file ./datasets/generated_dataset_gr1_nut_pouring.hdf5
+
 
 Train a policy
 ^^^^^^^^^^^^^^

source/isaaclab_tasks/config/extension.toml

 [package]
 
 # Note: Semantic Versioning is used: https://semver.org/
-version = "0.10.38"
+version = "0.10.39"
 
 # Description
 title = "Isaac Lab Environments"

source/isaaclab_tasks/docs/CHANGELOG.rst

 Changelog
 ---------
 
-0.10.38 (2025-06-26)
+0.10.39 (2025-06-26)
 ~~~~~~~~~~~~~~~~~~~~
 
 Fixed
@@ -10,7 +10,7 @@ Fixed
 * Relaxed upper range pin for protobuf python dependency for more permissive installation.
 
 
-0.10.37 (2025-05-22)
+0.10.38 (2025-05-22)
 ~~~~~~~~~~~~~~~~~~~~
 
 Fixed
@@ -19,7 +19,7 @@ Fixed
 * Fixed redundant body_names assignment in rough_env_cfg.py for H1 robot.
 
 
-0.10.36 (2025-06-16)
+0.10.37 (2025-06-16)
 ~~~~~~~~~~~~~~~~~~~~
 
 Changed
@@ -28,7 +28,7 @@ Changed
 * Show available RL library configs on error message when an entry point key is not available for a given task.
 
 
-0.10.35 (2025-05-15)
+0.10.36 (2025-05-15)
 ~~~~~~~~~~~~~~~~~~~~
 
 Added
@@ -38,7 +38,7 @@ Added
   implements assembly tasks to insert pegs into their corresponding sockets.
 
 
-0.10.34 (2025-05-21)
+0.10.35 (2025-05-21)
 ~~~~~~~~~~~~~~~~~~~~
 
 Added
@@ -48,6 +48,15 @@ Added
   can be pushed to a visualization dashboard to track improvements or regressions.
 
 
+0.10.34 (2025-05-22)
+~~~~~~~~~~~~~~~~~~~~
+
+Changed
+^^^^^^^
+
+* Changed ``Isaac-PickPlace-GR1T2-Abs-v0`` object asset to a steering wheel.
+
+
 0.10.33 (2025-05-12)
 ~~~~~~~~~~~~~~~~~~~~
 

source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/pick_place/mdp/terminations.py

@@ -26,15 +26,15 @@ if TYPE_CHECKING:
     from isaaclab.envs import ManagerBasedRLEnv
 
 
-def task_done(
+def task_done_pick_place(
     env: ManagerBasedRLEnv,
     object_cfg: SceneEntityCfg = SceneEntityCfg("object"),
     right_wrist_max_x: float = 0.26,
-    min_x: float = 0.30,
-    max_x: float = 0.95,
-    min_y: float = 0.25,
-    max_y: float = 0.66,
-    min_height: float = 1.13,
+    min_x: float = 0.40,
+    max_x: float = 0.85,
+    min_y: float = 0.35,
+    max_y: float = 0.60,
+    max_height: float = 1.10,
     min_vel: float = 0.20,
 ) -> torch.Tensor:
     """Determine if the object placement task is complete.
@@ -53,7 +53,7 @@ def task_done(
         max_x: Maximum x position of the object for task completion.
         min_y: Minimum y position of the object for task completion.
         max_y: Maximum y position of the object for task completion.
-        min_height: Minimum height (z position) of the object for task completion.
+        max_height: Maximum height (z position) of the object for task completion.
         min_vel: Minimum velocity magnitude of the object for task completion.
 
     Returns:
@@ -63,10 +63,10 @@ def task_done(
     object: RigidObject = env.scene[object_cfg.name]
 
     # Extract wheel position relative to environment origin
-    wheel_x = object.data.root_pos_w[:, 0] - env.scene.env_origins[:, 0]
-    wheel_y = object.data.root_pos_w[:, 1] - env.scene.env_origins[:, 1]
-    wheel_height = object.data.root_pos_w[:, 2] - env.scene.env_origins[:, 2]
-    wheel_vel = torch.abs(object.data.root_vel_w)
+    object_x = object.data.root_pos_w[:, 0] - env.scene.env_origins[:, 0]
+    object_y = object.data.root_pos_w[:, 1] - env.scene.env_origins[:, 1]
+    object_height = object.data.root_pos_w[:, 2] - env.scene.env_origins[:, 2]
+    object_vel = torch.abs(object.data.root_vel_w)
 
     # Get right wrist position relative to environment origin
     robot_body_pos_w = env.scene["robot"].data.body_pos_w
@@ -74,15 +74,15 @@ def task_done(
     right_wrist_x = robot_body_pos_w[:, right_eef_idx, 0] - env.scene.env_origins[:, 0]
 
     # Check all success conditions and combine with logical AND
-    done = wheel_x < max_x
-    done = torch.logical_and(done, wheel_x > min_x)
-    done = torch.logical_and(done, wheel_y < max_y)
-    done = torch.logical_and(done, wheel_y > min_y)
-    done = torch.logical_and(done, wheel_height < min_height)
+    done = object_x < max_x
+    done = torch.logical_and(done, object_x > min_x)
+    done = torch.logical_and(done, object_y < max_y)
+    done = torch.logical_and(done, object_y > min_y)
+    done = torch.logical_and(done, object_height < max_height)
     done = torch.logical_and(done, right_wrist_x < right_wrist_max_x)
-    done = torch.logical_and(done, wheel_vel[:, 0] < min_vel)
-    done = torch.logical_and(done, wheel_vel[:, 1] < min_vel)
-    done = torch.logical_and(done, wheel_vel[:, 2] < min_vel)
+    done = torch.logical_and(done, object_vel[:, 0] < min_vel)
+    done = torch.logical_and(done, object_vel[:, 1] < min_vel)
+    done = torch.logical_and(done, object_vel[:, 2] < min_vel)
 
     return done
 
@@ -108,6 +108,7 @@ def task_done_nut_pour(
 
     This function checks whether all success conditions for the task have been met:
     1. The factory nut is in the sorting bowl
+    2. The sorting beaker is in the sorting bin
     3. The sorting bowl is placed on the sorting scale
 
     Args:

source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/pick_place/pickplace_gr1t2_env_cfg.py

@@ -31,7 +31,7 @@ from isaaclab.managers import TerminationTermCfg as DoneTerm
 from isaaclab.scene import InteractiveSceneCfg
 from isaaclab.sim.spawners.from_files.from_files_cfg import GroundPlaneCfg, UsdFileCfg
 from isaaclab.utils import configclass
-from isaaclab.utils.assets import ISAAC_NUCLEUS_DIR
+from isaaclab.utils.assets import ISAAC_NUCLEUS_DIR, ISAACLAB_NUCLEUS_DIR
 
 from . import mdp
 
@@ -54,24 +54,13 @@ class ObjectTableSceneCfg(InteractiveSceneCfg):
         ),
     )
 
-    # Object
     object = RigidObjectCfg(
         prim_path="{ENV_REGEX_NS}/Object",
-        init_state=RigidObjectCfg.InitialStateCfg(pos=[-0.35, 0.40, 1.1691], rot=[1, 0, 0, 0]),
-        spawn=sim_utils.CylinderCfg(
-            radius=0.018,
-            height=0.35,
+        init_state=RigidObjectCfg.InitialStateCfg(pos=[-0.45, 0.45, 0.9996], rot=[1, 0, 0, 0]),
+        spawn=UsdFileCfg(
+            usd_path=f"{ISAACLAB_NUCLEUS_DIR}/Mimic/pick_place_task/pick_place_assets/steering_wheel.usd",
+            scale=(0.75, 0.75, 0.75),
             rigid_props=sim_utils.RigidBodyPropertiesCfg(),
-            mass_props=sim_utils.MassPropertiesCfg(mass=0.3),
-            collision_props=sim_utils.CollisionPropertiesCfg(),
-            visual_material=sim_utils.PreviewSurfaceCfg(diffuse_color=(0.15, 0.15, 0.15), metallic=1.0),
-            physics_material=sim_utils.RigidBodyMaterialCfg(
-                friction_combine_mode="max",
-                restitution_combine_mode="min",
-                static_friction=0.9,
-                dynamic_friction=0.9,
-                restitution=0.0,
-            ),
         ),
     )
 
@@ -300,7 +289,7 @@ class TerminationsCfg:
         func=mdp.root_height_below_minimum, params={"minimum_height": 0.5, "asset_cfg": SceneEntityCfg("object")}
     )
 
-    success = DoneTerm(func=mdp.task_done)
+    success = DoneTerm(func=mdp.task_done_pick_place)
 
 
 @configclass
@@ -314,8 +303,8 @@ class EventCfg:
         mode="reset",
         params={
             "pose_range": {
-                "x": [-0.05, 0.0],
-                "y": [0.0, 0.05],
+                "x": [-0.01, 0.01],
+                "y": [-0.01, 0.01],
             },
             "velocity_range": {},
             "asset_cfg": SceneEntityCfg("object"),