Interacting with a deformable object

Interacting with a deformable object#

While deformable objects sometimes refer to a broader class of objects, such as cloths, fluids and soft bodies, Isaac Lab represents deformable objects as either surface or volume deformables. Unlike rigid objects, soft bodies can deform under external forces and collisions. In this tutorial, we focus on volume deformable bodies. For an example of surface deformables (cloth), see the deformable demo at scripts/demos/deformables.py.

The deformable object API and schema define/modify functions are shared across backends, while deformable property and material configuration classes are backend-specific. PhysX simulates soft bodies using the Finite Element Method (FEM); the Newton experimental backend uses VBD-based deformable support from isaaclab_contrib.deformable. The volume deformable comprises of two tetrahedral meshes – a simulation mesh and a collision mesh. The simulation mesh is used to simulate the deformations of the soft body, while the collision mesh is used to detect collisions with other objects in the scene. For PhysX-specific details, please check the PhysX documentation.

This tutorial shows how to interact with a deformable object in the simulation. We will spawn a set of soft cubes and see how to set their nodal positions and velocities, along with apply kinematic commands to the mesh nodes to move the soft body.

Note

This tutorial automatically tetrahedralizes volume deformables. Run it with the tetrahedralization extra:

uv run --extra tetrahedralization python scripts/tutorials/01_assets/run_deformable_object.py --visualizer kit

With the legacy installer, install the optional dependencies first:

./isaaclab.sh -i tetrahedralization

The Code#

The tutorial corresponds to the run_deformable_object.py script in the scripts/tutorials/01_assets directory.

Code for run_deformable_object.py
  1# Copyright (c) 2022-2026, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md).
  2# All rights reserved.
  3#
  4# SPDX-License-Identifier: BSD-3-Clause
  5
  6"""
  7This script demonstrates how to work with the deformable object and interact with it.
  8
  9.. code-block:: bash
 10
 11    # Usage with default PhysX physics and default kit visualizer.
 12    uv run python scripts/tutorials/01_assets/run_deformable_object.py
 13
 14    # Usage with Newton VBD physics and default kit visualizer.
 15    uv run python scripts/tutorials/01_assets/run_deformable_object.py --backend newton_vbd
 16
 17    # Usage with OvPhysX physics without a visualizer.
 18    uv run python scripts/tutorials/01_assets/run_deformable_object.py --backend ovphysx
 19
 20"""
 21
 22"""Parse CLI first so we can decide whether to launch Isaac Sim Kit."""
 23
 24import argparse
 25
 26from isaaclab.app import add_launcher_args, launch_simulation
 27
 28# add argparse arguments
 29parser = argparse.ArgumentParser(description="Tutorial on interacting with a deformable object.")
 30parser.add_argument(
 31    "--backend", type=str, default="physx", choices=["physx", "newton_vbd", "ovphysx"], help="Physics backend."
 32)
 33# append simulation launcher CLI arguments
 34add_launcher_args(parser)
 35# Kit cannot be combined with OvPhysX, so use no visualizer by default for that backend
 36backend_args, _ = parser.parse_known_args()
 37parser.set_defaults(visualizer=None if backend_args.backend == "ovphysx" else ["kit"])
 38# parse the arguments
 39args_cli = parser.parse_args()
 40args_cli.physics = args_cli.backend
 41
 42"""Rest everything follows."""
 43
 44import torch
 45
 46import isaaclab.sim as sim_utils
 47import isaaclab.utils.math as math_utils
 48from isaaclab.assets import DeformableObject, DeformableObjectCfg
 49from isaaclab.physics import PhysicsCfg
 50
 51
 52def design_scene():
 53    """Designs the scene."""
 54    # Ground-plane
 55    cfg = sim_utils.GroundPlaneCfg()
 56    cfg.func("/World/defaultGroundPlane", cfg)
 57    # Lights
 58    cfg = sim_utils.DomeLightCfg(intensity=2000.0, color=(0.8, 0.8, 0.8))
 59    cfg.func("/World/Light", cfg)
 60
 61    # Create a dictionary for the scene entities
 62    scene_entities = {}
 63
 64    # Create separate groups called "env_0", "env_1", ...
 65    # Newton's scene loader requires the "env_\d+" naming convention to
 66    # detect per-environment Xforms and replicate them as separate worlds.
 67    origins = [[0.25, 0.25, 0.0], [-0.25, 0.25, 0.0], [0.25, -0.25, 0.0], [-0.25, -0.25, 0.0]]
 68    for i, origin in enumerate(origins):
 69        sim_utils.create_prim(f"/World/env_{i}", "Xform", translation=origin)
 70
 71    youngs_modulus = 1e5
 72    poissons_ratio = 0.4
 73    density = 500.0
 74    if args_cli.backend == "newton_vbd":
 75        from isaaclab_newton.sim.schemas import NewtonDeformableBodyPropertiesCfg
 76        from isaaclab_newton.sim.spawners.materials import NewtonDeformableBodyMaterialCfg
 77
 78        deformable_props = NewtonDeformableBodyPropertiesCfg()
 79        # Newton's VBD path skips the simulation mesh collider, so collision offsets do not apply
 80        collision_props = None
 81        physics_material = NewtonDeformableBodyMaterialCfg(
 82            k_mu=youngs_modulus / (2.0 * (1.0 + poissons_ratio)),
 83            k_lambda=youngs_modulus * poissons_ratio / ((1.0 + poissons_ratio) * (1.0 - 2.0 * poissons_ratio)),
 84            density=density,
 85        )
 86    else:
 87        from isaaclab_physx.sim.schemas import PhysxCollisionCfg, PhysxDeformableBodyPropertiesCfg
 88        from isaaclab_physx.sim.spawners.materials import PhysxDeformableBodyMaterialCfg
 89
 90        deformable_props = PhysxDeformableBodyPropertiesCfg()
 91        collision_props = [PhysxCollisionCfg(rest_offset=0.0, contact_offset=0.001)]
 92        physics_material = PhysxDeformableBodyMaterialCfg(
 93            poissons_ratio=poissons_ratio, youngs_modulus=youngs_modulus, density=density
 94        )
 95
 96    # 3D Deformable Object
 97    cfg = DeformableObjectCfg(
 98        prim_path="/World/env_.*/Cube",
 99        spawn=sim_utils.MeshCuboidCfg(
100            size=(0.2, 0.2, 0.2),
101            deformable_props=deformable_props,
102            collision_props=collision_props,
103            visual_material=sim_utils.PreviewSurfaceCfg(diffuse_color=(0.5, 0.1, 0.0)),
104            physics_material=physics_material,
105        ),
106        init_state=DeformableObjectCfg.InitialStateCfg(pos=(0.0, 0.0, 1.0)),
107        debug_vis=True,
108    )
109
110    cube_object = DeformableObject(cfg=cfg)
111    scene_entities["cube_object"] = cube_object
112
113    # return the scene information
114    return scene_entities, origins
115
116
117def run_simulator(sim: sim_utils.SimulationContext, entities: dict, origins: torch.Tensor):
118    """Runs the simulation loop."""
119    # Extract scene entities
120    # note: we only do this here for readability. In general, it is better to access the entities directly from
121    #   the dictionary. This dictionary is replaced by the InteractiveScene class in the next tutorial.
122    cube_object: DeformableObject = entities["cube_object"]
123
124    # Define simulation stepping
125    sim_dt = sim.get_physics_dt()
126    sim_time = 0.0
127    count = 0
128
129    # Nodal kinematic targets of the deformable bodies
130    nodal_kinematic_target = cube_object.data.nodal_kinematic_target.torch.clone()
131
132    # Simulate physics
133    while sim.is_headless_or_exist_active_visualizer():
134        # reset at start and after 3 seconds
135        if count % int(3.0 / sim_dt) == 0:
136            # reset counters
137            count = 0
138
139            # reset the nodal state of the object
140            nodal_state = cube_object.data.default_nodal_state_w.torch.clone()
141            # apply random pose to the object
142            pos_w = torch.rand(cube_object.num_instances, 3, device=sim.device) * 0.1 + origins
143            quat_w = math_utils.random_orientation(cube_object.num_instances, device=sim.device)
144            nodal_state[..., :3] = cube_object.transform_nodal_pos(nodal_state[..., :3], pos_w, quat_w)
145
146            # write nodal state to simulation
147            cube_object.write_nodal_state_to_sim_index(nodal_state)
148
149            # Write the nodal state to the kinematic target and free all vertices
150            nodal_kinematic_target[..., :3] = nodal_state[..., :3]
151            nodal_kinematic_target[..., 3] = 1.0
152            cube_object.write_nodal_kinematic_target_to_sim_index(nodal_kinematic_target)
153
154            # reset buffers
155            cube_object.reset()
156
157            print("----------------------------------------")
158            print("[INFO]: Resetting object state...")
159
160        # update the kinematic target for cubes at index 0 and 3
161        kinematic_cubes = [0, 3]
162        # we slightly move the cube in the z-direction by picking the vertex at index 0
163        nodal_kinematic_target[kinematic_cubes, 0, 2] += 0.2 * sim_dt
164        # set vertex at index 0 to be kinematically constrained
165        # 0: constrained, 1: free
166        nodal_kinematic_target[kinematic_cubes, 0, 3] = 0.0
167        # write kinematic target to simulation
168        cube_object.write_nodal_kinematic_target_to_sim_index(nodal_kinematic_target)
169
170        # write internal data to simulation
171        cube_object.write_data_to_sim()
172        # perform step
173        sim.step()
174        # update sim-time
175        sim_time += sim_dt
176        count += 1
177        # update buffers
178        cube_object.update(sim_dt)
179
180        # print the root positions every second
181        if count % int(1.0 / sim_dt) == 0:
182            print(f"Time {sim_time:.2f}s: \tRoot position (in world): {cube_object.data.root_pos_w.torch[:, :3]}")
183
184
185def main():
186    """Main function."""
187    with launch_simulation(cfg=PhysicsCfg(), launcher_args=args_cli) as physics_cfg:
188        if args_cli.backend == "newton_vbd":
189            physics_cfg.solver_cfg.iterations = 10
190            physics_cfg.num_substeps = 4
191        sim_cfg = sim_utils.SimulationCfg(dt=0.01, device=args_cli.device, physics=physics_cfg)
192        sim = sim_utils.SimulationContext(sim_cfg)
193        # Set main camera
194        sim.set_camera_view(eye=[2.0, 2.0, 2.0], target=[0.0, 0.0, 0.75])
195        # Design scene
196        scene_entities, scene_origins = design_scene()
197        scene_origins = torch.tensor(scene_origins, device=sim.device)
198        # Play the simulator
199        sim.reset()
200        # Now we are ready!
201        print("[INFO]: Setup complete...")
202        # Run the simulator
203        run_simulator(sim, scene_entities, scene_origins)
204        print("[INFO]: Simulation complete...")
205
206
207if __name__ == "__main__":
208    # run the main function
209    main()

The Code Explained#

Designing the scene#

Similar to the Interacting with a rigid object tutorial, we populate the scene with a ground plane and a light source. In addition, we add a deformable object to the scene using the assets.DeformableObject class. This class is responsible for spawning the prims at the input path and initializes their corresponding deformable body physics handles.

In this tutorial, we create a cubical soft object using the spawn configuration similar to the deformable cube in the Spawn Objects tutorial. The only difference is that now we wrap the spawning configuration into the assets.DeformableObjectCfg class. This class contains information about the asset’s spawning strategy and default initial state. When this class is passed to the assets.DeformableObject class, it spawns the object and initializes the corresponding physics handles when the simulation is played.

Note

Deformable objects require a mesh object to be spawned with backend-specific deformable body physics properties and a matching deformable physics material. Use --backend physx for the PhysX implementation or --backend newton_vbd for the experimental Newton implementation.

As seen in the rigid body tutorial, we can spawn the deformable object into the scene in a similar fashion by creating an instance of the assets.DeformableObject class by passing the configuration object to its constructor.

    # Create separate groups called "env_0", "env_1", ...
    # Newton's scene loader requires the "env_\d+" naming convention to
    # detect per-environment Xforms and replicate them as separate worlds.
    origins = [[0.25, 0.25, 0.0], [-0.25, 0.25, 0.0], [0.25, -0.25, 0.0], [-0.25, -0.25, 0.0]]
    for i, origin in enumerate(origins):
        sim_utils.create_prim(f"/World/env_{i}", "Xform", translation=origin)

    youngs_modulus = 1e5
    poissons_ratio = 0.4
    density = 500.0
    if args_cli.backend == "newton_vbd":
        from isaaclab_newton.sim.schemas import NewtonDeformableBodyPropertiesCfg
        from isaaclab_newton.sim.spawners.materials import NewtonDeformableBodyMaterialCfg

        deformable_props = NewtonDeformableBodyPropertiesCfg()
        # Newton's VBD path skips the simulation mesh collider, so collision offsets do not apply
        collision_props = None
        physics_material = NewtonDeformableBodyMaterialCfg(
            k_mu=youngs_modulus / (2.0 * (1.0 + poissons_ratio)),
            k_lambda=youngs_modulus * poissons_ratio / ((1.0 + poissons_ratio) * (1.0 - 2.0 * poissons_ratio)),
            density=density,
        )
    else:
        from isaaclab_physx.sim.schemas import PhysxCollisionCfg, PhysxDeformableBodyPropertiesCfg
        from isaaclab_physx.sim.spawners.materials import PhysxDeformableBodyMaterialCfg

        deformable_props = PhysxDeformableBodyPropertiesCfg()
        collision_props = [PhysxCollisionCfg(rest_offset=0.0, contact_offset=0.001)]
        physics_material = PhysxDeformableBodyMaterialCfg(
            poissons_ratio=poissons_ratio, youngs_modulus=youngs_modulus, density=density
        )

    # 3D Deformable Object
    cfg = DeformableObjectCfg(
        prim_path="/World/env_.*/Cube",
        spawn=sim_utils.MeshCuboidCfg(
            size=(0.2, 0.2, 0.2),
            deformable_props=deformable_props,
            collision_props=collision_props,
            visual_material=sim_utils.PreviewSurfaceCfg(diffuse_color=(0.5, 0.1, 0.0)),
            physics_material=physics_material,
        ),
        init_state=DeformableObjectCfg.InitialStateCfg(pos=(0.0, 0.0, 1.0)),
        debug_vis=True,
    )

    cube_object = DeformableObject(cfg=cfg)

Running the simulation loop#

Continuing from the rigid body tutorial, we reset the simulation at regular intervals, apply kinematic commands to the deformable body, step the simulation, and update the deformable object’s internal buffers.

Resetting the simulation state#

Unlike rigid bodies and articulations, deformable objects have a different state representation. The state of a deformable object is defined by the nodal positions and velocities of the mesh. The nodal positions and velocities are defined in the simulation world frame and are stored in the assets.DeformableObject.data attribute.

We use the assets.DeformableObject.data.default_nodal_state_w attribute to get the default nodal state of the spawned object prims. This default state can be configured from the assets.DeformableObjectCfg.init_state attribute, which we left as identity in this tutorial.

Attention

The initial state in the configuration assets.DeformableObjectCfg specifies the pose of the deformable object at the time of spawning. Based on this initial state, the default nodal state is obtained when the simulation is played for the first time.

We apply transformations to the nodal positions to randomize the initial state of the deformable object.

            # reset the nodal state of the object
            nodal_state = cube_object.data.default_nodal_state_w.torch.clone()
            # apply random pose to the object
            pos_w = torch.rand(cube_object.num_instances, 3, device=sim.device) * 0.1 + origins
            quat_w = math_utils.random_orientation(cube_object.num_instances, device=sim.device)
            nodal_state[..., :3] = cube_object.transform_nodal_pos(nodal_state[..., :3], pos_w, quat_w)

To reset the deformable object, we first set the nodal state by calling the assets.DeformableObject.write_nodal_state_to_sim() method. This method writes the nodal state of the deformable object prim into the simulation buffer. Additionally, we free all the kinematic targets set for the nodes in the previous simulation step by calling the assets.DeformableObject.write_nodal_kinematic_target_to_sim() method. We explain the kinematic targets in the next section.

Finally, we call the assets.DeformableObject.reset() method to reset any internal buffers and caches.

            # write nodal state to simulation
            cube_object.write_nodal_state_to_sim_index(nodal_state)

            # Write the nodal state to the kinematic target and free all vertices
            nodal_kinematic_target[..., :3] = nodal_state[..., :3]
            nodal_kinematic_target[..., 3] = 1.0
            cube_object.write_nodal_kinematic_target_to_sim_index(nodal_kinematic_target)

            # reset buffers
            cube_object.reset()

Stepping the simulation#

Deformable bodies support user-driven kinematic control where a user can specify position targets for some of the mesh nodes while the rest of the nodes are simulated by the active deformable solver. This partial kinematic control is useful for applications where the user wants to interact with the deformable object in a controlled manner.

In this tutorial, we apply kinematic commands to two out of the four cubes in the scene. We set the position targets for the node at index 0 (bottom-left corner) to move the cube along the z-axis.

At every step, we increment the kinematic position target for the node by a small value. Additionally, we set the flag to indicate that the target is a kinematic target for that node in the simulation buffer. These are set into the simulation buffer by calling the assets.DeformableObject.write_nodal_kinematic_target_to_sim() method.

        # update the kinematic target for cubes at index 0 and 3
        kinematic_cubes = [0, 3]
        # we slightly move the cube in the z-direction by picking the vertex at index 0
        nodal_kinematic_target[kinematic_cubes, 0, 2] += 0.2 * sim_dt
        # set vertex at index 0 to be kinematically constrained
        # 0: constrained, 1: free
        nodal_kinematic_target[kinematic_cubes, 0, 3] = 0.0
        # write kinematic target to simulation
        cube_object.write_nodal_kinematic_target_to_sim_index(nodal_kinematic_target)

Similar to the rigid object and articulation, we perform the assets.DeformableObject.write_data_to_sim() method before stepping the simulation. For deformable objects, this method does not apply any external forces to the object. However, we keep this method for completeness and future extensions.

        # write internal data to simulation
        cube_object.write_data_to_sim()

Updating the state#

After stepping the simulation, we update the internal buffers of the deformable object prims to reflect their new state inside the assets.DeformableObject.data attribute. This is done using the assets.DeformableObject.update() method.

At a fixed interval, we print the root position of the deformable object to the terminal. As mentioned earlier, there is no concept of a root state for deformable objects. However, we compute the root position as the average position of all the nodes in the mesh.

        # update buffers
        cube_object.update(sim_dt)

        # print the root positions every second
        if count % int(1.0 / sim_dt) == 0:
            print(f"Time {sim_time:.2f}s: \tRoot position (in world): {cube_object.data.root_pos_w.torch[:, :3]}")

The Code Execution#

Now that we have gone through the code, let’s run the script and see the result:

uv run python scripts/tutorials/01_assets/run_deformable_object.py --visualizer kit

./isaaclab.sh -p scripts/tutorials/01_assets/run_deformable_object.py --visualizer kit

To run the same tutorial with the experimental Newton deformable backend:

uv run python scripts/tutorials/01_assets/run_deformable_object.py --backend newton_vbd --visualizer kit

./isaaclab.sh -p scripts/tutorials/01_assets/run_deformable_object.py --backend newton_vbd --visualizer kit

This should open a stage with a ground plane, lights, and several cubes. Two of the four cubes must be dropping from a height and settling on to the ground. Meanwhile the other two cubes must be moving along the z-axis. You should see a marker showing the kinematic target position for the nodes at the bottom-left corner of the cubes. To stop the simulation, you can either close the window, or press Ctrl+C in the terminal

result of run_deformable_object.py

This tutorial showed how to spawn deformable objects and wrap them in a DeformableObject class to initialize their physics handles which allows setting and obtaining their state. We also saw how to apply kinematic commands to the deformable object to move the mesh nodes in a controlled manner. An advanced demo of deformable objects, including surface deformables and loading USD assets and applying deformable material on them, can be found in scripts/demos/deformables.py. In the next tutorial, we will see how to create a scene using the InteractiveScene class.