unisim.backend.drake.backend

UniSim adapter for the drake-uni batch runtime.

UniLab owns task logic, reset sampling, named sensor views, and training flow. DrakeUni owns Drake model construction, batched stepping, and raw sensor evaluation. This module translates the SimBackend contract into DrakeUni runtime calls and keeps UniLab’s cached state/sensor views synchronized.

Functions

ensure_drake_batch_available()

Report whether the DrakeUni batch extension can be used.

Classes

DrakeBackend

UniLab SimBackend implementation backed by DrakeUni batch runtime.
class unisim.backend.drake.backend.DrakeBackend[source]

Bases: SimBackend

UniLab SimBackend implementation backed by DrakeUni batch runtime.

The backend keeps the public UniLab API stable while delegating model construction, integration, and raw sensor evaluation to DrakeUni.

Parameters:

  • scene (SceneCfg)

  • num_envs (int)

  • sim_dt (float)

  • drake_backend_mode (str)

  • nthread (int)

backend_type: str = 'drake'
__init__(scene, num_envs, sim_dt, *, drake_backend_mode='batch', nthread=0)[source]
Parameters:

  • scene (SceneCfg)

  • num_envs (int)

  • sim_dt (float)

  • drake_backend_mode (str)

  • nthread (int)

property scene_model_file: str
property num_envs: int

Number of vectorized environments.

property nthread: int
property model: _DrakeUniModelView

Underlying physics model.

property num_actuators: int

Number of actuators.

property num_dof_vel: int

Number of joint velocity DoFs, excluding the floating base.

get_actuator_ctrl_range()[source]

Return actuator control ranges.

Return type:

ndarray

Returns:

Array with shape (num_actuators, 2) and columns [low, high].

get_actuator_names()[source]

Return actuator names in control-vector order on the cold path.

Return type:

tuple[str, ...]

get_actuator_joint_names()[source]

Return each actuator’s target single-DoF joint in control-vector order.

Backends must fail closed when an actuator does not target exactly one hinge/slide joint. Manager action terms use this cold-path metadata to map community joint selectors onto the backend control vector without inspecting backend-private model objects.

Return type:

tuple[str, ...]

get_scene_model_file()[source]

Return the materialized scene path for diagnostics, when available.

Return type:

str | None

get_scene_layout()[source]

Return the immutable materialized public addresses, never native handles.

Return type:

CompiledSceneLayout

get_entity_names()[source]

Return materialized physical entity names in the frozen public order.

Return type:

tuple[str, ...]

get_entity_default_state(entity, env_ids=None)[source]

Detached construction/keyframe defaults in selected environment order.

Fields and frames match get_entity_state. Defaults follow immutable variant assignment and never reflect current reset-time randomization. This query does not reset, step or reparse the scene.

Parameters:
Return type:

Mapping[str, ndarray]

get_entity_state(entity)[source]

Return detached root_pose/root_velocity/joint_positions/joint_velocities.

Root fields follow EntityStatePatch’s link-origin/world-frame contract. Non-root joint fields use the frozen entity joint order and native generalized widths. Unavailable fields must fail, never return old data as if current. State freshness follows the adapter’s declared profile.

Parameters:

entity (str)

Return type:

Mapping[str, ndarray]

get_joint_range(*, names=None)[source]

Return joint position limits, excluding the floating base.

Parameters:

names (Sequence[str] | None) – Optional joint names in requested return order. Adapters that support named scalar joints resolve the model mapping internally.

Return type:

ndarray | None

Returns:

Array with shape (num_dof, 2) and columns [low, high], or None when the backend does not expose limits.

When names is provided by a supporting adapter, the result has shape (len(names), 2). Hinge limits are radians, slide limits are meters, and joints without enabled limits return infinities.

get_keyframe_qpos(name)[source]

Return the full qpos for a named keyframe, including the floating base.

Parameters:

name (str) – Keyframe name such as "stand" or "home".

Return type:

ndarray

Returns:

Array with shape (nq,).

get_default_qpos()[source]

Return the backend/model default qpos through a stable contract.

Return type:

ndarray

get_default_dof_pos()[source]

Return default joint positions in canonical non-root qpos order.

The returned array is detached, one-dimensional, and excludes floating root coordinates. Backends whose DoF view is actuator-indexed must use that same actuator-target order here.

Return type:

ndarray

get_init_qvel()[source]

Return a zero-initialized qvel vector compatible with set_state_tensor.

Return type:

ndarray

Returns:

Zero-filled qvel array.

get_actuator_gains()[source]

Return per-joint (kp, kd) arrays from the backend model.

Return type:

tuple[ndarray, ndarray]

get_body_ids(names)[source]

Resolve body/link names to backend integer IDs.

Parameters:

names (Sequence[str]) – Body/link names.

Return type:

ndarray

Returns:

int32 array with shape (len(names),).

Raises:

ValueError – If any name is not found.

get_motion_body_ids(names)[source]

Resolve body IDs used by motion datasets.

Motion datasets are generated from MuJoCo, so the returned ids follow the MJCF body order with worldbody as id 0, regardless of the backend-native indexing used by get_body_ids.

Parameters:

names (Sequence[str])

Return type:

ndarray

get_site_ids(names)[source]

Resolve site names to integer ID arrays.

Parameters:

names (Sequence[str]) – Site names.

Return type:

ndarray

Returns:

int32 ID array with shape (len(names),).

get_joint_dof_indices(names)[source]

Resolve joint names to absolute DoF indices in velocity space.

Parameters:

names (Sequence[str]) – Joint names.

Return type:

ndarray

Returns:

int32 index array with shape (len(names),) addressing the complete qvel vector, including any root coordinates.

get_joint_dof_pos_indices(names)[source]

Resolve joint names to DoF indices in position space (qpos).

Only single-DoF joints are supported; free joints are excluded.

Parameters:

names (Sequence[str]) – Joint names.

Return type:

ndarray

Returns:

int32 index array with shape (len(names),) relative to the joint section of qpos.

get_joint_dof_vel_indices(names)[source]

Resolve joint names to joint-section DoF indices in velocity space.

Unlike get_joint_dof_indices(), the returned indices exclude any root/free-joint velocity columns. They address the same joint section used by get_joint_dof_pos_indices().

Parameters:

names (Sequence[str])

Return type:

ndarray

get_joint_state_qpos_indices(names)[source]

Resolve single-DoF joints to full set_state_tensor qpos columns.

Unlike get_joint_dof_pos_indices(), these indices address the complete qpos vector accepted by set_state_tensor(), including any root coordinates. Manager reset transactions resolve them on the cold path.

Parameters:

names (Sequence[str])

Return type:

ndarray

get_joint_state_qvel_indices(names)[source]

Resolve single-DoF joints to full set_state_tensor qvel columns.

Parameters:

names (Sequence[str])

Return type:

ndarray

reset_entities(request)[source]

Validate the complete selected-entity request, then commit it once.

Validation failure leaves all state unchanged. A native partial commit failure must fault the backend unless the adapter can actually roll back. Unselected entities/environments and fixed identity remain unchanged.

Parameters:

request (SceneResetRequest)

Return type:

None

get_dr_capabilities()[source]

Return supported domain-randomization capabilities for this backend.

Return type:

DomainRandomizationCapabilities

apply_interval_randomization(plan)[source]

Apply a scheduled interval randomization plan.

Generic dispatch: each op yielded by plan.iter_ops() is validated against the builtin term specs (custom terms pass through) and routed to the backend-owned handler table returned by _interval_term_handlers(). Op payloads are torch-first: Torch tensors or TensorIntervalPayload values produced by the caller; host adapters convert tensors at their private boundary through unisim.dr._host, and a missing producer-sampled payload fails closed. A term without a handler fails closed with NotImplementedError naming the backend class and the term. Backends that need per-plan prologue/epilogue semantics (for example clearing staged external forces before the ops accumulate) keep a thin override that calls this base implementation.

Parameters:

plan (IntervalRandomizationPlan)

Return type:

None

get_play_capabilities()[source]

Return backend-native play/render capabilities.

Return type:

PlayCapabilities

resolve_play_render_plan(*, play_render_mode, play_steps, output_video)[source]

Resolve high-level playback mode into backend-owned render parameters.

Parameters:
Return type:

PlayRenderPlan

run_playback(*, env, initialize, step, num_steps, output_video=None, render_spacing=None, render_offset_mode=None, headless=None, record_video=None, frame_state_getter=None, camera_kwargs=None, debug_overlay_getter=None, on_frame=None)[source]

Execute backend-owned playback for an env wrapper.

camera_kwargs is normalized into CameraCfg at this boundary; unknown mapping keys fail closed with an error naming them.

debug_overlay_getter is an optional per-frame callback returning a sequence with one entry per environment (len == num_envs); each entry is that env’s sequence of DebugPrimitive (None or empty marks an env without overlay) and returning None disables overlays for the frame. Primitive poses are env-local; the renderer applies grid offsets when composing multiple envs. Backends whose get_play_capabilities().supports_debug_overlay is False fail closed with NotImplementedError when this is not None. On the interactive rendering path only backends whose supports_interactive_debug_overlay is True consume it; the others fail closed with NotImplementedError.

on_frame is an optional per-frame video hook called by offline render pipelines before encoding: it receives (frame_index, frame) with the frame an (H, W, 3) uint8 array, and returns a replacement frame of the same shape/dtype or None to keep the original. Backends rendering through a native (non-offline) renderer fail closed with NotImplementedError when this is not None.

Known boundary: env is the owning env wrapper, not a physics-layer concept. Current playback implementations read env-level configuration (e.g. cfg.scene, cfg.ctrl_dt, cfg.render_spacing) and env-owned playback helpers (get_playback_model, get_physics_state_snapshot) that have no backend-native equivalent yet. The parameter stays on this contract until playback asset/config resolution moves onto backend-owned metadata; backends must only use it on the cold playback path.

Parameters:

  • env (Any)

  • initialize (Callable[[], Any])

  • step (Callable[[Any], Any])

  • num_steps (int | None)

  • output_video (str | PathLike[str] | None)

  • render_spacing (float | None)

  • render_offset_mode (str | None)

  • headless (bool | None)

  • record_video (bool | None)

  • frame_state_getter (Callable[[], np.ndarray] | None)

  • camera_kwargs (CameraCfg | Mapping[str, Any] | None)

  • debug_overlay_getter (DebugOverlayGetter | None)

  • on_frame (Callable[[int, np.ndarray], np.ndarray | None] | None)

Return type:

str | None

bind_renderer(spacing=1.0, *, offset_mode='grid', headless=False, capture=False, width=1280, height=720, camera_kwargs=None)[source]

Initialize a backend-native renderer.

headless controls whether a native window is opened. capture controls whether capture_video_frame is valid for the renderer. camera_kwargs is normalized into CameraCfg at this boundary; unknown mapping keys fail closed with an error naming them.

Parameters:
Return type:

None

render()[source]

Render one frame through a backend-native interactive renderer.

Raises:

RenderClosedError – If the user closed the render window.

Return type:

None

capture_video_frame()[source]

Capture one RGB frame through a backend-native renderer.

Raises:

RenderClosedError – If the user closed the render window.

Return type:

ndarray

get_physics_state_layout()[source]

Return the [time, qpos, qvel] packet layout (no mocap bodies).

Return type:

PhysicsStateLayout

get_physics_state()[source]

Return a physics snapshot suitable for offline playback/video export.

Rows use the [time, qpos, qvel] layout; backends whose model has mocap bodies append [mocap_pos(nmocap*3), mocap_quat(nmocap*4)] so offline rendering can replay mocap-driven geometry at its recorded pose. Consumers must decode snapshots through get_physics_state_layout().split_state rather than hardcoding column slices.

Return type:

ndarray

get_playback_model(env_index=None)[source]

Return the playback model for a specific env when variants exist.

Parameters:

env_index (int | None) – Optional vectorized environment index.

Return type:

str

Returns:

The backend model object used by playback tooling.

diagnostics()[source]
Return type:

Any

apply_body_force(body_ids, force, torque=None)[source]

Apply a world-frame force (and optional torque) to bodies for the upcoming step.

Parameters:

  • body_ids (ndarray) – Body ids whose external forces should be perturbed.

  • force (ndarray) – Force values with shape (num_envs, len(body_ids), 3).

  • torque (ndarray | None) – Optional world-frame torque values with the same shape. Backends without a torque channel must fail closed when this is not None.

Return type:

None

Returns:

None. Backends that support this mutate their pending simulation state.

get_tensor_execution()[source]

Declare Drake’s CPU-authoritative tensor execution profile.

Return type:

TensorExecution

get_tensor_capabilities()[source]

Return the deliberately narrow initial packed host-bridge profile.

Return type:

TensorLifecycleCapabilities

bind_host_bridge_io(spec)[source]

Compile persistent Drake staging and packed device layouts.

Parameters:

spec (TensorIOSpec)

Return type:

HostBridgeTransferPlan

get_state_views(fields=None, device=None)[source]

Copy authoritative CPU state to an explicitly selected Torch device.

Parameters:
Return type:

Mapping[str, Any]

get_sensor_view(name, device=None)[source]

Copy one authoritative CPU sensor block to a Torch device.

Parameters:
Return type:

Any

step_tensor(ctrl, nsteps=1)[source]

Bridge one accelerator control tensor to CPU Drake physics.

Parameters:
Return type:

dict | None

set_state_tensor(env_indices, qpos, qvel, randomization=None)[source]

Bridge selected accelerator reset state to CPU Drake physics.

Parameters:

  • env_indices (Any)

  • qpos (Any)

  • qvel (Any)

  • randomization (TensorResetRandomizationPayload | None)

Return type:

dict | None

cleanup_scene_assets()[source]

Release cold-path scene artifacts owned by the backend.

Return type:

None

close()[source]
Return type:

None

unisim.backend.drake.backend.ensure_drake_batch_available()[source]

Report whether the DrakeUni batch extension can be used.

Return type:

tuple[bool, ImportError | None]