Drive saturation

31 · Joints and drives

An arm with a heavy tip is released 60° below its target and driven by a stiff PD drive limited to 12 N·m, so the drive saturates on the way up. The default augmented drive clamps only its explicit force and leaves the implicit part unbounded. drive_mode="rows" solves the drive as a PGS row, like a PhysX articulation drive, and clamps the whole impulse.

drag to orbit · scroll to zoom

0.00 s

Cost

Time per step, CUDA graph replay, median of 7 interleaved rounds on one NVIDIA RTX PRO 6000 Blackwell Server Edition; ratios are against the first row. Solver allocation is the GPU memory the solver allocates at construction, before warm-up and graph capture. Scene: a driven 6-link chain in each world (target_ke 50, joint friction 0.01).

Option	1 world	64 worlds	1024 worlds	solver allocation, 1024 worlds	result in this tutorial
drive_mode="augmented"	0.21 ms	0.30 ms	0.34 ms	48 MB	settles in 1.8 s
drive_mode="rows"	0.30 ms 1.42×	0.40 ms 1.36×	0.48 ms 1.40×	49 MB	settles in 1.0 s

What to look at

Both reach the target.
The row drive overshoots less (7.5° vs 9.2°).

Key parameter

drive_mode

"augmented" (default): implicit drives in the mass matrix. "rows": one row per driven DOF, solved with contacts and limits, counted against articulation_constraint_max.

Try changing

Lower effort_limit to 6 N·m: can the arm still lift?
Add enable_joint_velocity_limits=True with drive rows.

Concept

Drive rows

What it is

drive_mode="rows" solves each drive as a PGS row with the PhysX articulation drive update and clamps the accumulated impulse at effort_limit·h. The drive is then solved together with contacts and limits, and its whole reaction respects the limit.

In this scene

Released 60° below target with a 12 N·m limit, drive rows settle within 1° in 1.0 s; the default augmented drive overshoots more and settles in 1.8 s.

Considerations

Cost: One row per driven DOF, counted against articulation_constraint_max: about +40% per step on a driven 6-link chain (0.34 → 0.47 ms in 1024 worlds).
Interactions: Disables sparse factors; with velocity limits, fuse_joint_velocity_limits applies.
Use it when: Effort limits matter, as in sim-to-real transfer from PhysX.

The script

cd tutorials && python 31_drive_saturation.py prints each variant's final metric; --record out.json also writes the replay. Every tutorial imports replay.py from the same folder.

31_drive_saturation.py
replay.py

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

"""Drive saturation: drive_mode="augmented" vs "rows" when a stiff drive hits its effort limit."""

import math

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

from replay import Recorder

DT = 1.0 / 240.0
SUBSTEPS = 8


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


def build():
    builder = newton.ModelBuilder()
    arm = builder.add_link(xform=tf(0.25, 0.0, 0.6))
    builder.add_shape_box(
        arm, hx=0.25, hy=0.02, hz=0.02, cfg=newton.ModelBuilder.ShapeConfig(density=200.0)
    )
    builder.add_shape_sphere(
        arm,
        xform=tf(0.25, 0.0, 0.0),
        radius=0.05,
        cfg=newton.ModelBuilder.ShapeConfig(density=3000.0),
    )
    j = builder.add_joint_revolute(
        -1,
        arm,
        axis=(0.0, -1.0, 0.0),
        parent_xform=tf(0.0, 0.0, 0.6),
        child_xform=tf(-0.25, 0.0, 0.0),
        target_ke=3000.0,
        target_kd=60.0,
        target_q=0.0,
        effort_limit=12.0,
    )
    builder.add_articulation([j])
    model = builder.finalize()
    model.joint_q.fill_(math.radians(-60.0))  # released 60 degrees below the target
    return model


def simulate(rec, label, **options):
    model = build()
    solver = SolverSteel(model, **options)
    pipeline = newton.CollisionPipeline(model)
    contacts = pipeline.contacts()
    state_0, state_1, control = model.state(), model.state(), model.control()
    newton.eval_fk(model, model.joint_q, model.joint_qd, state_0)

    run = rec.variant(label, model)
    for _ in range(rec.frames(3.0)):
        run.frame(state_0, angle_deg=math.degrees(state_0.joint_q.numpy()[0]))
        for _ in range(SUBSTEPS):
            pipeline.collide(state_0, contacts)
            solver.step(state_0, state_1, control, contacts, DT)
            state_0, state_1 = state_1, state_0
    run.check(solver)


if __name__ == "__main__":
    rec = Recorder()
    simulate(rec, 'drive_mode="augmented" (default)')
    simulate(rec, 'drive_mode="rows"', drive_mode="rows")
    rec.save()

# 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

Steel docs and tutorials are licensed under Apache-2.0. Third-party notices. "Skild", "Skild AI" and the Skild logo are trademarks of Skild AI and are not licensed under Apache-2.0.