Randomizing effort limits

74 · Domain randomization

Five stiff arms with a 2.1 kg payload start hanging 80 degrees below level, with the drive target at level. Each world gets a sampled joint_effort_limit. Holding the arm level takes 6.9 N m, so arms with a lower limit cannot hold it there and swing below it, while the others settle at the target. Steel reads joint_effort_limit every step; the script still notifies JOINT_DOF_FORCE_PROPERTIES after writing it.

drag to orbit · scroll to zoom

Pause0.00 s

0.1×¼×½×1×2×

Reset view

What to look at

• Limits above 6.9 N m: the arm reaches level.
• Limits below it: the arm may pass level briefly but cannot stay there.

Key parameter

model.joint_effort_limit

With the default drive_mode="augmented" only the explicit drive force is clamped; drive_mode="rows" clamps the whole drive reaction.

Try changing

• Switch to drive_mode="rows" (see Drive saturation).
• Randomize the payload mass as well and watch where the threshold moves.

Concept

When Steel sees a randomized value

What it is

Steel reads this input from the model or state every step, so a write takes effect on the next step. The tutorial still notifies where a flag exists, which keeps sleeping islands and carried kinematics consistent.

In this scene

Limits below it: the arm may pass level briefly but cannot stay there.

Considerations

Cost

Call only, default solver, six-link chain and four boxes per world, 1024 worlds (1.12 ms per collide + step): JOINT_DOF_FORCE_PROPERTIES 25 µs (7 µs captured). Flags measured one at a time; combined calls and feature validation can cost more. Body-inertial and joint-DOF notifications also request a mass-matrix refresh.

Graph capture

These flags can be captured in a reset graph. Kinematic-flag changes, sleeping, and shape flags with sparse factors plus restitution run eagerly; captured calls skip some value checks.

Use it when

Motors near their torque limit, such as lifting near capacity.

The script

cd tutorials && python dr_effort_limits.py prints each variant's final metric; --record out.json also writes the replay. Every tutorial imports replay.py from the same folder.

dr_effort_limits.py

tutorials/dr_effort_limits.py

# SPDX-FileCopyrightText: Copyright (c) 2026 Skild AI and the Steel contributors
# SPDX-License-Identifier: Apache-2.0

"""Effort-limit randomization: per-world joint_effort_limit decides which arms lift."""

import math

import newton
import numpy as np
import warp as wp
from newton.solvers import SolverSteel

from replay import Recorder

DT = 1.0 / 240.0
SUBSTEPS = 8
WORLDS = 5


def tf(x, y, z):
    return wp.transform((x, y, z), wp.quat_identity())


def build():
    arm = newton.ModelBuilder()
    link = arm.add_link(xform=tf(0.0, 0.0, 0.6))
    arm.add_shape_box(link, xform=tf(0.15, 0.0, 0.0), hx=0.15, hy=0.02, hz=0.02)
    cfg = newton.ModelBuilder.ShapeConfig(density=4000.0)
    arm.add_shape_sphere(link, xform=tf(0.3, 0.0, 0.0), radius=0.05, cfg=cfg)  # 2.1 kg payload
    j = arm.add_joint_revolute(
        -1,
        link,
        axis=(0.0, -1.0, 0.0),  # positive angles raise the arm
        parent_xform=tf(0.0, 0.0, 0.6),
        target_ke=500.0,
        target_kd=20.0,
    )
    arm.add_articulation([j])
    arm.joint_q[-1] = math.radians(-80.0)  # start hanging
    builder = newton.ModelBuilder()
    builder.replicate(arm, WORLDS, spacing=(0.0, 0.35, 0.0))
    return builder.finalize()


def simulate(rec, label, limit):
    model = build()
    solver = SolverSteel(model)
    model.joint_effort_limit.assign(limit.astype(np.float32))  # N m, one DOF per world
    solver.notify_model_changed(newton.ModelFlags.JOINT_DOF_FORCE_PROPERTIES)
    state_0, state_1, control = model.state(), model.state(), model.control()
    newton.eval_fk(model, model.joint_q, model.joint_qd, state_0)
    control.joint_target_q.zero_()  # lift to horizontal

    run = rec.variant(label, model)
    for _ in range(rec.frames(4.0)):
        q = np.degrees(state_0.joint_q.numpy())
        run.frame(state_0, **{f"limit {e:.1f} N m": v for e, v in zip(limit, q)})
        for _ in range(SUBSTEPS):
            solver.step(state_0, state_1, control, None, DT)
            state_0, state_1 = state_1, state_0
    run.check(solver)


if __name__ == "__main__":
    rng = np.random.default_rng(9)
    limit = np.sort(rng.uniform(2.0, 10.0, WORLDS))
    rec = Recorder()
    simulate(rec, "effort limit sampled per world", limit)
    rec.save()
    model = build()
    torque = 9.81 * float((model.body_mass.numpy() * model.body_com.numpy()[:, 0])[0])
    print(f"gravity torque at horizontal: {torque:.2f} N m")

replay.py

tutorials/replay.py

# SPDX-FileCopyrightText: Copyright (c) 2026 Skild AI and the Steel contributors
# SPDX-License-Identifier: Apache-2.0

"""Record Steel tutorial runs as replay JSON for the tutorials page, or print a summary.

Every tutorial imports this module. ``python NN_name.py`` runs the variants and prints
the final metric of each; ``--record out.json`` also writes body poses, shapes and metric
series that the page replays in 3D.
"""

import argparse
import base64
import json
import os
import subprocess
import sys
import time

import newton
import numpy as np
import warp as wp

from source_hash import source_sha256

_RENDERED_TYPES = {
    newton.GeoType.PLANE,
    newton.GeoType.SPHERE,
    newton.GeoType.CAPSULE,
    newton.GeoType.ELLIPSOID,
    newton.GeoType.CYLINDER,
    newton.GeoType.BOX,
    newton.GeoType.MESH,
    newton.GeoType.CONE,
    newton.GeoType.CONVEX_MESH,
}


class Recorder:
    """Collect the variants of one tutorial; ``fps`` is the replay frame rate."""

    def __init__(self, fps: int = 30):
        parser = argparse.ArgumentParser()
        parser.add_argument(
            "--record", metavar="OUT.json", help="write a replay file for the tutorials page"
        )
        parser.add_argument("--device", default=None, help="Warp device, for example cuda:0")
        self.args = parser.parse_args()
        if self.args.device:
            wp.set_device(self.args.device)
        self.fps = fps
        self.script = os.path.abspath(sys.argv[0])
        self.variants: list[Variant] = []

    def frames(self, seconds: float) -> int:
        """Number of replay frames in ``seconds``, including the first."""
        return int(round(seconds * self.fps)) + 1

    def variant(
        self,
        label: str,
        model: newton.Model,
        *,
        ghost: bool = False,
        slot: int | None = None,
        scene: str | None = None,
    ) -> "Variant":
        """Start one run; ``ghost`` overlays run ``slot``, ``scene`` groups runs for charts."""
        variant = Variant(label, model, self.fps, ghost, slot, scene)
        self.variants.append(variant)
        return variant

    def save(self) -> None:
        """Print a summary and, with ``--record``, write the replay file."""
        for variant in self.variants:
            last = variant.metrics[-1] if variant.metrics else {}
            flag = "  (rows dropped)" if variant.overflow else ""
            print(f"{variant.label:<48} {json.dumps(last)}  {variant.wall:.2f} s{flag}")
        if not self.args.record:
            return
        source_sha = source_sha256(self.script)
        doc = {
            "script": os.path.basename(self.script),
            "script_sha256": source_sha,
            "newton_commit": _newton_commit(),
            "newton_version": newton.__version__,
            "warp_version": wp.config.version,
            "gpu": wp.get_device().name,
            "fps": self.fps,
            "variants": [v.to_json() for v in self.variants],
        }
        with open(self.args.record, "w") as f:
            json.dump(doc, f, separators=(",", ":"))
        print(f"wrote {self.args.record}")


class Variant:
    """One recorded run: a pose per frame for every body, plus named metric values."""

    def __init__(self, label, model, fps, ghost, slot, scene):
        self.label, self.model, self.fps, self.ghost, self.slot = label, model, fps, ghost, slot
        self.scene = scene
        self.poses: list[np.ndarray] = []
        self.metrics: list[dict] = []
        self.awake: list[list[int]] = []
        self.particles: list[np.ndarray] = []
        self.overflow = False
        self.start = time.perf_counter()
        self.wall = 0.0

    def frame(self, state: newton.State, awake=None, particles=None, **metrics) -> None:
        """Record ``state.body_q``, optional awake flags, particle positions and metric values."""
        self.poses.append(state.body_q.numpy().astype(np.float32).copy())
        if particles is not None:
            self.particles.append(particles.numpy().astype(np.float32).copy())
        self.metrics.append({k: _round(v) for k, v in metrics.items()})
        if awake is not None:
            self.awake.append([int(x) for x in awake.numpy()])
        self.wall = time.perf_counter() - self.start

    def check(self, solver) -> None:
        """Note whether the solver dropped rows; call once after the run."""
        try:
            solver.check_constraint_capacity()
        except RuntimeError:
            self.overflow = True

    def to_json(self) -> dict:
        poses = (
            np.stack(self.poses)
            if self.poses
            else np.zeros((0, self.model.body_count, 7), np.float32)
        )
        return {
            "label": self.label,
            "fps": self.fps,
            "ghost": self.ghost,
            "slot": self.slot,
            "scene": self.scene,
            "bodies": int(self.model.body_count),
            "frames": int(poses.shape[0]),
            "poses": base64.b64encode(poses.astype(np.float32).tobytes()).decode(),
            "shapes": _shape_table(self.model),
            "metric": self.metrics,
            "awake": self.awake or None,
            "particles": self._particles_json(),
            "wall_s": round(self.wall, 3),
            "overflow": self.overflow,
        }

    def _particles_json(self):
        if not self.particles:
            return None
        frames = np.stack(self.particles)
        tris = self.model.tri_indices
        radius = self.model.particle_radius.numpy()
        return {
            "count": int(frames.shape[1]),
            "frames": base64.b64encode(frames.astype(np.float32).tobytes()).decode(),
            "radius": round(float(radius.mean()), 5) if radius.size else 0.0,
            "tris": [int(v) for v in tris.numpy().reshape(-1)]
            if tris is not None and tris.shape[0]
            else None,
        }


def _shape_table(model):
    types = model.shape_type.numpy()
    scales = model.shape_scale.numpy()
    xforms = model.shape_transform.numpy()
    bodies = model.shape_body.numpy()
    flags = model.shape_flags.numpy()
    shapes = []
    for i, t in enumerate(types):
        if int(t) not in _RENDERED_TYPES or not flags[i] & int(newton.ShapeFlags.VISIBLE):
            continue
        shape = {
            "b": int(bodies[i]),
            "t": int(t),
            "s": [round(float(v), 5) for v in scales[i]],
            "x": [round(float(v), 6) for v in xforms[i]],
        }
        if int(t) in (newton.GeoType.MESH, newton.GeoType.CONVEX_MESH):
            mesh = model.shape_source[i]
            shape["v"] = [round(float(v), 5) for v in np.asarray(mesh.vertices).reshape(-1)]
            shape["i"] = [int(v) for v in np.asarray(mesh.indices).reshape(-1)]
        shapes.append(shape)
    return shapes


def _round(value):
    value = float(value)
    return round(value, 5) if np.isfinite(value) else None


def _newton_commit():
    if os.environ.get("NEWTON_COMMIT"):
        return os.environ["NEWTON_COMMIT"]
    try:
        root = os.path.dirname(os.path.dirname(newton.__file__))
        return subprocess.check_output(["git", "-C", root, "rev-parse", "HEAD"], text=True).strip()
    except (OSError, subprocess.CalledProcessError):
        return None

Recorded with SolverSteel on Newton 1.9.0.dev0, Warp 1.19.0, NVIDIA RTX PRO 6000 Blackwell Server Edition. Replays read the state back every frame, so they are not a speed benchmark. Script · page text