Adds visual-based tactile sensor with shape sensing example

.gitignore

@@ -69,3 +69,5 @@ tests/
 
 # Docker history
 .isaac-lab-docker-history
+
+**/tactile_record/*

CONTRIBUTORS.md

@@ -84,6 +84,7 @@ Guidelines for modifications:
 * Jingzhou Liu
 * Jinqi Wei
 * Johnson Sun
+* Juana Du
 * Kaixi Bao
 * Kris Wilson
 * Kourosh Darvish

docs/conf.py

@@ -190,6 +190,8 @@
     "nvidia.srl",
     "flatdict",
     "IPython",
+    "cv2",
+    "imageio",
     "ipywidgets",
     "mpl_toolkits",
 ]

docs/source/api/lab/isaaclab.sensors.rst

@@ -33,6 +33,9 @@
     RayCasterCameraCfg
     Imu
     ImuCfg
+    VisuoTactileSensor
+    VisuoTactileSensorCfg
+    VisuoTactileSensorData
 
 Sensor Base
 -----------
@@ -166,3 +169,22 @@ Inertia Measurement Unit
     :inherited-members:
     :show-inheritance:
     :exclude-members: __init__, class_type
+
+Visuo-Tactile Sensor
+--------------------
+
+.. autoclass:: VisuoTactileSensor
+    :members:
+    :inherited-members:
+    :show-inheritance:
+
+.. autoclass:: VisuoTactileSensorData
+    :members:
+    :inherited-members:
+    :exclude-members: __init__
+
+.. autoclass:: VisuoTactileSensorCfg
+    :members:
+    :inherited-members:
+    :show-inheritance:
+    :exclude-members: __init__, class_type

docs/source/overview/core-concepts/sensors/index.rst

@@ -19,3 +19,4 @@ The following pages describe the available sensors in more detail:
     frame_transformer
     imu
     ray_caster
+    visuo_tactile_sensor

docs/source/overview/core-concepts/sensors/visuo_tactile_sensor.rst

@@ -0,0 +1,195 @@
+.. _overview_sensors_tactile:
+
+.. currentmodule:: isaaclab
+
+Visuo-Tactile Sensor
+====================
+
+
+The visuo-tactile sensor in Isaac Lab provides realistic tactile feedback through integration with TacSL (Tactile Sensor Learning) [Akinola2025]_. It is designed to simulate high-fidelity tactile interactions, generating both visual and force-based data that mirror real-world tactile sensors like GelSight devices. The sensor can provide tactile RGB images, force field distributions, and other intermediate tactile measurements essential for robotic manipulation tasks requiring fine tactile feedback.
+
+
+.. figure:: ../../../_static/overview/sensors/tacsl_diagram.jpg
+    :align: center
+    :figwidth: 100%
+    :alt: Tactile sensor with RGB visualization and force fields
+
+
+Configuration
+~~~~~~~~~~~~~
+
+Tactile sensors require specific configuration parameters to define their behavior and data collection properties. The sensor can be configured with various parameters including sensor resolution, force sensitivity, and output data types.
+
+.. code-block:: python
+
+    from isaaclab.sensors.tacsl_sensor import VisuoTactileSensorCfg
+    from isaaclab_assets.sensors import GELSIGHT_R15_CFG
+    import isaaclab.sim as sim_utils
+
+    # Tactile sensor configuration
+    tactile_sensor = VisuoTactileSensorCfg(
+        prim_path="{ENV_REGEX_NS}/Robot/tactile_sensor",
+        ## Sensor configuration
+        render_cfg=GELSIGHT_R15_CFG,
+        enable_camera_tactile=True,
+        enable_force_field=True,
+        ## Elastomer configuration
+        elastomer_rigid_body="elastomer",
+        ## Force field configuration
+        num_tactile_rows=20,
+        num_tactile_cols=25,
+        tactile_margin=0.003,
+        ## Indenter configuration (will be set based on indenter type)
+        indenter_rigid_body="indenter",
+        indenter_sdf_mesh="factory_nut_loose/collisions",
+        ## Force field physics parameters
+        tactile_kn=1.0,
+        tactile_mu=2.0,
+        tactile_kt=0.1,
+        ## Camera configuration
+        camera_cfg=TiledCameraCfg(
+            prim_path="{ENV_REGEX_NS}/Robot/elastomer_tip/cam",
+            update_period=1 / 60,  # 60 Hz
+            height=320,
+            width=240,
+            data_types=["distance_to_image_plane"],
+            spawn=None,  # camera already spawned in USD file
+        ),
+    )
+
+The configuration supports customization of:
+
+* **Render Configuration**: Specify the GelSight sensor rendering parameters using predefined configs
+  (e.g., ``GELSIGHT_R15_CFG``, ``GELSIGHT_MINI_CFG`` from ``isaaclab_assets.sensors``)
+* **Tactile Modalities**:
+    * ``enable_camera_tactile`` - Enable tactile RGB imaging through camera sensors
+    * ``enable_force_field`` - Enable force field computation and visualization
+* **Force Field Grid**: Set tactile grid dimensions (``num_tactile_rows``, ``num_tactile_cols``) and margins, which directly affects the spatial resolution of the computed force field
+* **Indenter Configuration**: Define properties of interacting objects including rigid body name and collision mesh
+* **Physics Parameters**: Control the sensor's force field computation:
+    * ``tactile_kn``, ``tactile_mu``, ``tactile_kt`` - Normal stiffness, friction coefficient, and tangential stiffness
+* **Camera Settings**: Configure resolution, focal length, update rates, and 6-DOF positioning relative to the sensor
+
+Configuration Requirements
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. important::
+   The following requirements must be satisfied for proper sensor operation:
+
+   **Camera Tactile Imaging**
+      If ``enable_camera_tactile=True``, a valid ``camera_cfg`` (TiledCameraCfg) must be provided with appropriate camera parameters.
+
+   **Force Field Computation**
+      If ``enable_force_field=True``, the following parameters are required:
+
+      * ``indenter_rigid_body`` - Specific rigid body within the actor
+      * ``indenter_sdf_mesh`` - Collision mesh for SDF computation
+      * ``elastomer_rigid_body`` - Elastomer rigid body, this is required to track the elastomer's pose and velocity.
+
+   **SDF Computation**
+      When force field computation is enabled, penalty-based normal and shear forces are computed using Signed Distance Field (SDF) queries. To achieve GPU acceleration:
+
+      * Interacting objects should have SDF collision meshes
+      * An SDFView must be defined during initialization, therefore interacting objects should be specified before simulation.
+
+   **Elastomer Configuration**
+      Elastomer properties (``elastomer_rigid_body``, ``elastomer_tip_link_name``) must match the robot model where the sensor is attached.
+
+   **Physics Materials**
+      The sensor uses physics materials to configure the compliant contact properties of the elastomer.
+      By default, physics material properties are pre-configured in the USD asset. However, you can override
+      these properties by specifying the following parameters in ``UsdFileWithPhysicsMaterialOnPrimsCfg`` when
+      spawning the robot:
+
+      * ``compliant_contact_stiffness`` - Contact stiffness for the elastomer surface
+      * ``compliant_contact_damping`` - Contact damping for the elastomer surface
+      * ``apply_physics_material_prim_path`` - Prim path where physics material is applied (typically ``"elastomer/collisions"``)
+
+      If any parameter is set to ``None``, the corresponding property from the USD asset will be retained.
+
+
+Usage Example
+~~~~~~~~~~~~~
+
+To use the tactile sensor in a simulation environment, run the demo:
+
+.. code-block:: bash
+
+    cd scripts/demos/sensors/tacsl
+    python tacsl_example.py --use_tactile_rgb --use_tactile_ff --indenter_type nut --num_envs 16 --save_viz
+
+Available command-line options include:
+
+* ``--use_tactile_rgb``: Enable camera-based tactile sensing
+* ``--use_tactile_ff``: Enable force field tactile sensing
+* ``--indenter_type``: Specify the type of indenter object (nut, cube, etc.)
+* ``--num_envs``: Number of parallel environments
+* ``--save_viz``: Save visualization outputs for analysis
+
+For a complete list of available options:
+
+.. code-block:: bash
+
+    python tacsl_example.py -h
+
+.. note::
+   The demo examples are based on the Gelsight R1.5, which is a prototype sensor that is now discontinued. The same procedure can be adapted for other visuotactile sensors.
+
+.. figure:: ../../../_static/overview/sensors/tacsl_demo.jpg
+    :align: center
+    :figwidth: 100%
+    :alt: TacSL tactile sensor demo showing RGB tactile images and force field visualizations
+
+The tactile sensor supports multiple data modalities that provide comprehensive information about contact interactions:
+
+
+Output Tactile Data
+~~~~~~~~~~~~~~~~~~~
+**RGB Tactile Images**
+    Real-time generation of tactile RGB images as objects make contact with the sensor surface. These images show deformation patterns and contact geometry similar to gel-based tactile sensors [Si2022]_
+
+
+**Force Fields**
+    Detailed contact force field and pressure distributions across the sensor surface, including normal and shear components.
+
+.. list-table::
+   :widths: 50 50
+   :class: borderless
+
+   * - .. figure:: ../../../_static/overview/sensors/tacsl_taxim_example.jpg
+          :align: center
+          :figwidth: 80%
+          :alt: Tactile output with RGB visualization
+
+     - .. figure:: ../../../_static/overview/sensors/tacsl_force_field_example.jpg
+          :align: center
+          :figwidth: 80%
+          :alt: Tactile output with force field visualization
+
+Integration with Learning Frameworks
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The tactile sensor is designed to integrate seamlessly with reinforcement learning and imitation learning frameworks. The structured tensor outputs can be directly used as observations in learning algorithms:
+
+.. code-block:: python
+
+    def get_tactile_observations(self):
+        """Extract tactile observations for learning."""
+        tactile_data = self.scene["tactile_sensor"].data
+
+        # tactile RGB image
+        tactile_rgb = tactile_data.tactile_rgb_image
+
+        # force field
+        tactile_normal_force = tactile_data.tactile_normal_force
+        tactile_shear_force = tactile_data.tactile_shear_force
+
+        return [tactile_rgb, tactile_normal_force, tactile_shear_force]
+
+
+
+References
+~~~~~~~~~~
+
+.. [Akinola2025] Akinola, I., Xu, J., Carius, J., Fox, D., & Narang, Y. (2025). TacSL: A library for visuotactile sensor simulation and learning. *IEEE Transactions on Robotics*.
+.. [Si2022] Si, Z., & Yuan, W. (2022). Taxim: An example-based simulation model for GelSight tactile sensors. *IEEE Robotics and Automation Letters*, 7(2), 2361-2368.