Language Language English 简体中文

unilab.base — Core Contracts

The shared substrate everything else stands on. If you only read one module in this reference, read this one.

Symbol	Role
NpEnv / NpEnvState	The env contract every task implements
SimBackend	Abstract backend interface (MuJoCo / Motrix implement it)
Registry	Task / backend / algorithm registration and lookup
Scene	Cold-path scene materialization
observations, final_observation	Observation builders & terminal handling
curriculum	Curriculum schedule primitives

unilab.base

Environment registry and base classes.

Selected detail

class unilab.base.np_env.NpEnv

Bases: ABEnv

Backend-agnostic numpy environment base class.

Parameters:

• cfg (EnvCfg)

• backend (SimBackend)

• num_envs (int)

__init__(cfg, backend, num_envs)

Parameters:

• cfg (EnvCfg)

• backend (SimBackend)

• num_envs (int)

property cfg: EnvCfg

The configuration of the environment

property num_envs: int

return the size of the env if it is vectorized

property state: NpEnvState | None

Current environment state (None before first reset)

property obs_groups_spec: dict[str, int]

101}.

Subclasses MUST override this property.

Type:

Return observation group dimensions, e.g. {“obs”

Type:

98, “critic”

property observation_space: Space

Observation space

init_state()

Initialize environment and return initial state

Return type:

NpEnvState

step(actions)

Step the environment with given actions, return new state

Parameters:

actions (ndarray)

Return type:

NpEnvState

reset(env_indices)

Parameters:

env_indices (ndarray)

Return type:

Tuple[dict[str, ndarray], dict]

init_play_renderer(render_spacing=None, render_offset_mode=None, *, headless=False, capture=False, width=1280, height=720, camera_kwargs=None)

Initialize backend-native playback rendering when available.

Parameters:

• render_spacing (float | None)

• render_offset_mode (str | None)

• headless (bool)

• capture (bool)

• width (int)

• height (int)

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

Return type:

None

resolve_play_render_plan(*, play_render_mode, play_steps, output_video)

Resolve high-level playback mode through the concrete backend.

Parameters:

• play_render_mode (str | None)

• play_steps (int | None)

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

Return type:

BackendPlayRenderPlan

run_playback(*, 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)

Execute playback through the concrete backend.

on_frame is declared on the env contract but the unisim SimBackend.run_playback boundary does not accept it yet; passing a callback fails closed until the upstream contract lands. Use unilab.visualization.playback_session.SnapshotPlaybackSession for deferred rendering with per-frame callbacks today.

Parameters:

• 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

render_play_frame()

Render one interactive playback frame through the env contract.

Return type:

None

render(mode='rgb_array')

Render the current state to an RGB array through the play renderer.

Lazily initializes a headless capture renderer on first use and returns one detached (H, W, 3) uint8 frame per call. Backends without native video capture fail closed with a class-named error.

Parameters:

mode (str)

Return type:

ndarray

capture_play_video_frame()

Capture one detached RGB video frame through the env contract.

Return type:

ndarray

get_physics_state_snapshot()

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

Return type:

ndarray

abstract apply_action(actions, state)

Subclasses implement the action-to-control conversion.

Parameters:

• actions (ndarray)

• state (NpEnvState)

Return type:

ndarray

abstract update_state(state)

Subclasses compute observation, reward, and termination state.

Parameters:

state (NpEnvState)

Return type:

NpEnvState

property play_capabilities: EnvPlayCapabilities

Return env-facing play/render capabilities.

get_playback_model(env_index=None)

Return the backend playback model for one env in a vectorized batch.

Parameters:

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

Return type:

Any

Returns:

The backend-specific playback model.

get_scene_visual_model_file()

Return the backend scene visual model file on the cold path, when available.

Return type:

str | None

set_nan_guard(guard)

Parameters:

guard (NanGuard)

Return type:

None

set_autoreset(enabled)

Toggle automatic reset of done envs at the end of step.

Defaults to True (standard RL autoreset). Interactive playback can disable it so a terminated robot stays put until a manual reset.

Parameters:

enabled (bool)

Return type:

None

export_training_state()

Export cumulative training progress, independently of episode/physics state.

Task-specific curriculum state belongs to the task’s explicit provider; this payload deliberately does not inspect manager or environment internals.

Return type:

dict[str, Any]

import_training_state(state)

Validate and restore cumulative progress before the next control step.

Parameters:

state (Mapping[str, Any])

Return type:

None

close()

Close the environment and release backend-owned scene assets.

Return type:

None

class unisim.backend.base.SimBackend

Bases: ABC

Unified simulation backend contract.

backend_type: str

property capabilities

Coarse capability labels for clients that need a cheap feature check.

The detailed contract is expressed by the methods on this class. The labels remain useful for benchmark/conformance metadata and are derived from the mandatory lifecycle methods rather than maintained separately by every adapter.

get_state(fields=None)

Return a detached, backend-neutral state snapshot.

qpos and qvel are assembled from the public kinematic getters; adapters may override this to expose native fields such as ctrl. This convenience API keeps benchmark clients independent from private model/data objects while the full reset contract remains set_state.

reset(env_ids=None)

Reset selected environments to the backend’s default state.

Parameters:

env_ids (ndarray | None)

Return type:

None

abstract property num_envs: int

Number of vectorized environments.

abstract property model

Underlying physics model.

abstract property num_actuators: int

Number of actuators.

abstract property num_dof_vel: int

Number of joint velocity DoFs, excluding the floating base.

abstract get_actuator_ctrl_range()

Return actuator control ranges.

Return type:

ndarray

Returns:

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

get_actuator_names()

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

Return type:

tuple[str, ...]

get_actuator_joint_names()

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()

Return the materialized scene path for diagnostics, when available.

Return type:

str | None

get_scene_visual_model_file()

Return the scene visual model file on the cold path, when available.

Backends without a separate visual scene model return None.

Return type:

str | None

get_terrain_spawn_data()

Return backend-materialized terrain metadata on the cold path.

Backends without generated terrain support return None. Callers should resolve this once during env initialization and cache the returned height-sampling callable for reset/reward hot paths.

Return type:

BackendTerrainSpawnData | None

abstract get_keyframe_qpos(name)

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()

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

Return type:

ndarray

get_default_dof_pos()

Return default joint positions in the same column order as get_dof_pos.

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

abstract get_init_qvel()

Return a zero-initialized qvel vector compatible with set_state.

Return type:

ndarray

Returns:

Zero-filled qvel array.

get_root_state_layout(root_body_name)

Resolve one body’s floating-root columns on the cold path.

Backends must verify that root_body_name owns a free/floating joint; fixed bodies and runtimes without body-to-root metadata fail closed. Name/model lookup is forbidden on reset and step hot paths, so callers cache either the returned layout or the unsupported result during scene materialization.

Parameters:

root_body_name (str)

Return type:

BackendRootStateLayout

abstract get_body_ids(names)

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_body_id(name)

Resolve one body/link name through the backend contract.

Parameters:

name (str)

Return type:

int

get_geom_id(name)

Resolve one geom name through the backend contract.

Parameters:

name (str)

Return type:

int

get_geom_size(name)

Return one geom size vector through the backend contract.

Parameters:

name (str)

Return type:

ndarray

get_geom_sizes()

Return default geometry sizes, shape (ngeom, 3).

Return type:

ndarray

get_geom_solref()

Return default contact reference parameters, shape (ngeom, 2).

Return type:

ndarray

get_geom_solimp()

Return default contact impedance parameters, shape (ngeom, 5).

Return type:

ndarray

get_dof_damping()

Return default joint damping, shape (nv,).

Return type:

ndarray

get_dof_frictionloss()

Return default joint friction loss, shape (nv,).

Return type:

ndarray

bind_mocap_pose(body_name)

Resolve a mocap body once; unavailable capabilities fail at binding.

Parameters:

body_name (str)

Return type:

BackendMocapPoseBinding

create_hfield_scanner(*, hfield_geom_id, offsets, frame_body_id, alignment='yaw', output='height')

Create a reusable height-field scanner on the init/cold path.

Backends that support height-field terrain scan must override this method.

Parameters:

• hfield_geom_id (int)

• offsets (ndarray)

• frame_body_id (int)

• alignment (str)

• output (str)

Return type:

BackendHeightScanner

get_body_subtree_ids(root_body_id)

Return body ids in the subtree rooted at root_body_id.

Parameters:

root_body_id (int)

Return type:

ndarray

get_geom_names()

Return backend geom names in backend id order.

Return type:

tuple[str, ...]

get_geom_body_ids()

Return the owning body id for each geom.

Return type:

ndarray

get_geom_contact_masks()

Return per-geom contact type and affinity masks.

Return type:

tuple[ndarray, ndarray]

get_geom_friction()

Return the backend geom-friction table.

Return type:

ndarray

get_gravity()

Return the backend gravity vector.

Return type:

ndarray

get_body_mass()

Return the backend body-mass table.

Return type:

ndarray

get_body_ipos()

Return the backend body inertial-position table.

Return type:

ndarray

get_dof_armature()

Return the backend dof-armature table.

Return type:

ndarray

get_motion_body_ids(names)

Resolve backend-native body IDs used by motion datasets.

Parameters:

names (Sequence[str])

Return type:

ndarray

cleanup_scene_assets()

Release cold-path scene artifacts owned by the backend.

Return type:

None

abstract get_joint_range()

Return joint position limits, excluding the floating base.

Return type:

ndarray | None

Returns:

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

abstract step(ctrl, nsteps=1)

Advance physics.

Parameters:

• ctrl (ndarray) – Control input with shape (num_envs, nu).

• nsteps (int) – Number of physics substeps.

Return type:

dict | None

Returns:

Optional dictionary. Backends may include a "timing" key with per-phase timings in milliseconds.

set_pre_step_control(fn)

Register an env-owned policy-control to physics-control converter.

The callback receives (backend, ctrl) so owner code can read the backend’s freshly-updated sensor contract before every physics substep. It must return backend-native actuator control with the same shape. Position-actuator envs leave this unset and keep the direct control path.

Parameters:

fn (Callable[[Any, ndarray], ndarray] | None)

Return type:

None

abstract set_state(env_indices, qpos, qvel, randomization=None)

Set physics state for selected environments.

Parameters:

• env_indices (ndarray) – Environment indices.

• qpos (ndarray) – Position state. Free-root columns exposed by get_root_state_layout() use world xyz and wxyz quaternion.

• qvel (ndarray) – Velocity state. Free-root columns exposed by get_root_state_layout() use world linear velocity and body-frame angular velocity.

• randomization (ResetRandomizationPayload | None) – Optional backend randomization payload.

Return type:

dict | None

Returns:

Optional dictionary. Backends MAY include a "timing" key with per-substep timings in milliseconds (e.g. set_state_mask_ms, set_state_data_slice_ms, …). Callers MUST treat None or missing keys as “not reported” — the outer wall-clock measurement in DomainRandomizationManager.reset (dr_reset_set_state_ms) remains authoritative for total set_state time.

abstract get_dr_capabilities()

Return supported domain-randomization capabilities for this backend.

Return type:

DomainRandomizationCapabilities

apply_init_randomization(plan)

Apply cold-path model/materialization randomization.

Parameters:

plan (InitRandomizationPlan)

Return type:

None

materialize()

Finalize cold-path backend resources before reset/step.

Return type:

None

apply_interval_randomization(plan)

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(). 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

apply_body_force(body_ids, force, torque=None)

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_play_capabilities()

Return backend-native play/render capabilities.

Return type:

BackendPlayCapabilities

resolve_play_render_plan(*, play_render_mode, play_steps, output_video)

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

Parameters:

• play_render_mode (str | None)

• play_steps (int | None)

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

Return type:

BackendPlayRenderPlan

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)

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[[], ndarray] | None)

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

• debug_overlay_getter (Callable[[], Sequence[Sequence[DebugPrimitive] | None] | None] | None)

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

Return type:

str | None

init_renderer(spacing=1.0, *, offset_mode='grid', headless=False, capture=False, width=1280, height=720, camera_kwargs=None)

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:

• spacing (float)

• offset_mode (str)

• headless (bool)

• capture (bool)

• width (int)

• height (int)

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

Return type:

None

render()

Render one frame through a backend-native interactive renderer.

Raises:

RenderClosedError – If the user closed the render window.

Return type:

None

capture_video_frame()

Capture one RGB frame through a backend-native renderer.

Raises:

RenderClosedError – If the user closed the render window.

Return type:

ndarray

get_physics_state()

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.

Return type:

ndarray

set_physics_state(state)

Restore a snapshot produced by get_physics_state.

Backends implementing this must refresh their host caches so state and sensor getters stay consistent with the restored physics state.

Parameters:

state (ndarray)

Return type:

None

get_playback_model(env_index=None)

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

Parameters:

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

Return type:

Any

Returns:

The backend model object used by playback tooling.

get_actuator_gains()

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

Return type:

tuple[ndarray, ndarray]

abstract get_base_pos()

Return base position in the world frame.

Return type:

ndarray

Returns:

(num_envs, 3)

abstract get_base_quat()

Return base quaternion in the world frame as wxyz.

Return type:

ndarray

Returns:

(num_envs, 4)

abstract get_base_lin_vel()

Return base linear velocity in the world frame.

This is the first three dimensions of generalized velocity qvel, expressed in world coordinates.

Return type:

ndarray

Returns:

(num_envs, 3)

abstract get_base_ang_vel()

Return base angular velocity in the world frame.

This is dimensions 3-5 of generalized velocity qvel, expressed in world coordinates. It differs from gyro readings: gyro sensors report angular velocity components in the body/sensor local frame, while this contract returns world-frame values. Use the matching sensor contract when body-frame angular velocity is required.

Return type:

ndarray

Returns:

(num_envs, 3)

abstract get_dof_pos()

Return joint positions, excluding the base.

Return type:

ndarray

Returns:

(num_envs, num_dof)

abstract get_dof_vel()

Return joint velocities, excluding the base.

Return type:

ndarray

Returns:

(num_envs, num_dof)

abstract get_body_pos_w(body_ids)

Return selected body positions in the world frame.

Parameters:

body_ids (ndarray) – Body ID array.

Return type:

ndarray

Returns:

(num_envs, len(body_ids), 3)

abstract get_body_quat_w(body_ids)

Return selected body quaternions in the world frame as wxyz.

Parameters:

body_ids (ndarray) – Body ID array.

Return type:

ndarray

Returns:

(num_envs, len(body_ids), 4)

get_body_pose_w(body_ids)

Return selected body positions and quaternions in the world frame.

Parameters:

body_ids (ndarray)

Return type:

tuple[ndarray, ndarray]

abstract get_body_lin_vel_w(body_ids)

Return selected body linear velocities in the world frame.

Parameters:

body_ids (ndarray) – Body ID array.

Return type:

ndarray

Returns:

(num_envs, len(body_ids), 3)

get_body_vel_w(body_ids)

Return selected body linear and angular velocities in the world frame.

Parameters:

body_ids (ndarray)

Return type:

tuple[ndarray, ndarray]

abstract get_body_ang_vel_w(body_ids)

Return selected body angular velocities in the world frame.

Parameters:

body_ids (ndarray) – Body ID array.

Return type:

ndarray

Returns:

(num_envs, len(body_ids), 3)

get_body_state_w(body_ids)

Get selected body position, quaternion, linear velocity, and angular velocity.

Parameters:

body_ids (ndarray)

Return type:

tuple[ndarray, ndarray, ndarray, ndarray]

copy_body_state_w(body_ids, out_pos, out_quat, out_lin_vel, out_ang_vel)

Copy selected world-frame body state into caller-owned buffers.

Parameters:

• body_ids (ndarray)

• out_pos (ndarray)

• out_quat (ndarray)

• out_lin_vel (ndarray)

• out_ang_vel (ndarray)

Return type:

tuple[ndarray, ndarray, ndarray, ndarray]

get_body_pose_w_rows(env_ids, body_ids)

Get selected env rows of world-frame body position and quaternion.

Parameters:

• env_ids (ndarray)

• body_ids (ndarray)

Return type:

tuple[ndarray, ndarray]

get_body_lin_vel_w_rows(env_ids, body_ids)

Get selected env rows of world-frame body linear velocity.

Parameters:

• env_ids (ndarray)

• body_ids (ndarray)

Return type:

ndarray

get_body_ang_vel_w_rows(env_ids, body_ids)

Get selected env rows of world-frame body angular velocity.

Parameters:

• env_ids (ndarray)

• body_ids (ndarray)

Return type:

ndarray

abstract get_body_pos_b(body_ids)

Return selected body positions in the baselink frame.

Parameters:

body_ids (ndarray) – Body ID array.

Return type:

ndarray

Returns:

(num_envs, len(body_ids), 3)

abstract get_body_quat_b(body_ids)

Return selected body quaternions in the baselink frame as wxyz.

Parameters:

body_ids (ndarray) – Body ID array.

Return type:

ndarray

Returns:

(num_envs, len(body_ids), 4)

abstract get_body_lin_vel_b(body_ids)

Return selected body linear velocities expressed in each body’s own frame.

The value is the body’s world-frame velocity rotated by the inverse of the body’s world-frame orientation, i.e. quat_apply_inverse(quat_w, lin_vel_w) (mjlab/Isaac-style analytical definition). It is well-defined for every body — including the root body — and must NOT be implemented as the motion relative to the baselink frame (which degenerates to zero for the root body).

Parameters:

body_ids (ndarray) – Body ID array.

Return type:

ndarray

Returns:

(num_envs, len(body_ids), 3)

abstract get_body_ang_vel_b(body_ids)

Return selected body angular velocities expressed in each body’s own frame.

The value is the body’s world-frame angular velocity rotated by the inverse of the body’s world-frame orientation, i.e. quat_apply_inverse(quat_w, ang_vel_w) (mjlab/Isaac-style analytical definition). It is well-defined for every body — including the root body — and must NOT be implemented as the motion relative to the baselink frame (which degenerates to zero for the root body).

Parameters:

body_ids (ndarray) – Body ID array.

Return type:

ndarray

Returns:

(num_envs, len(body_ids), 3)

get_site_ids(names)

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)

Resolve joint names to DoF indices in velocity space (qvel).

Parameters:

names (Sequence[str]) – Joint names.

Return type:

ndarray

Returns:

int32 index array with shape (len(names),) relative to the qvel start.

get_joint_dof_pos_indices(names)

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)

Resolve joint names to DoF indices in velocity space (qvel).

Parameters:

names (Sequence[str]) – Joint names.

Return type:

ndarray

Returns:

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

get_joint_state_qpos_indices(names)

Resolve single-DoF joints to full set_state qpos columns.

Unlike get_joint_dof_pos_indices(), these indices address the complete qpos vector accepted by set_state(), 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)

Resolve single-DoF joints to full set_state qvel columns.

Parameters:

names (Sequence[str])

Return type:

ndarray

get_site_jacobian_w(site_id, dof_indices)

Compute world-frame Jacobians for one site and selected DoF columns.

Parameters:

• site_id (int) – Integer site ID.

• dof_indices (ndarray) – DoF column indices to extract, with shape (n_dof,).

Return type:

tuple[ndarray, ndarray]

Returns:

(jacp, jacr) translation/rotation Jacobians, each with shape (num_envs, 3, n_dof).

abstract get_sensor_data(name)

Return sensor data.

Parameters:

name (str) – Sensor name.

Return type:

ndarray

Returns:

Sensor data array.

get_sensor_data_rows(name, env_ids)

Get selected env rows of a sensor array.

Parameters:

• name (str)

• env_ids (ndarray)

Return type:

ndarray

get_sensor_data_batch(names)

Fetch multiple sensors and concatenate their flattened values.

Parameters:

names (Sequence[str]) – Sensor names in output order.

Return type:

ndarray

Returns:

Array with shape (num_envs, total_sensor_values).

bind_sensor_data(names)

Materialize a validated view over named sensors on the cold path.

The existing sensor getters remain the sole backend adapter surface. This method validates each requested sensor once, records its flattened width, and returns a stable view for manager terms. Backends override the protected reader hook when numeric slots or stable cache slices are available; callers do not depend on that implementation detail.

Parameters:

names (Sequence[str])

Return type:

BackendSensorView