Physics Backends

Physics Backends#

Isaac Lab 3.0 supports multiple physics backends through a unified API. Each backend exposes the same Articulation, RigidObject, sensor and renderer surfaces, while differing in solver characteristics, maturity, and feature coverage. See Multi-Backend Architecture for how the dispatch and factory machinery work under the hood.

This page summarizes what each backend supports today; the sub-pages document backend-specific configuration, installation, and limitations.

For backend-specific access to native engine data and views, see Direct Physics Engine API Access. That guide explains the different ownership and synchronization models rather than presenting a false common low-level API.

Choosing a Backend#

  • PhysX — the historical default. Production-ready, broad coverage of Isaac Lab features, and the reference for behavior parity. Selected via PhysxCfg.

  • Newton — GPU-accelerated, Warp-native, and differentiable. The Newton integration ships with the MuJoCo-Warp solver and beta support for the Kamino solver. Selected via NewtonCfg.

  • OvPhysX — a highly experimental kit-less PhysX backend that reads scene-level parameters from the USD PhysicsScene prim. Selected via OvPhysxCfg. Not recommended for general use yet.

The active backend is selected at simulation construction time and applies to every asset, sensor, and renderer instantiated thereafter:

from isaaclab.sim import SimulationCfg
from isaaclab_physx.physics import PhysxCfg
from isaaclab_newton.physics import NewtonCfg, MJWarpSolverCfg

# PhysX (default)
sim_cfg = SimulationCfg(physics=PhysxCfg())

# Newton with MuJoCo-Warp
sim_cfg = SimulationCfg(physics=NewtonCfg(solver_cfg=MJWarpSolverCfg()))

Feature Support Matrix#

The matrix below is intentionally coarse-grained. For exhaustive per-asset and per-task support, see each backend’s own limitations page.

Feature

PhysX

Newton

OvPhysX

Maturity

Stable

Beta

Highly experimental

Default solver

TGS (rigid body)

MuJoCo-Warp

PhysX (TGS / PGS via USD)

Alternative solvers

PGS

Kamino (beta), additional Newton solvers planned

—

Differentiable

No

Yes (via Warp)

No

Articulation API

Yes

Yes

Yes

Rigid Object API

Yes

Yes

Yes

Rigid Object Collection API

Yes

Yes

Yes

Deformable Object API

Yes

Yes (experimental VBD)

Experimental (CUDA only)

Cable Object API

No

VBD

No

Contact Sensor

Yes

Yes

Yes

IMU

Yes

Yes

In-flight

Frame Transformer / Ray Caster / PVA / Joint-Wrench Sensor

Yes

Yes

In-flight

Camera / Tiled Rendering

Yes (RTX)

Yes (Newton-Warp renderer)

Not yet

Requires Isaac Sim

Yes

Optional (only for the Omniverse visualizer)

Yes

Solver configuration source

PhysxCfg

NewtonCfg + solver config

USD PhysicsScene + OvPhysxCfg

Selecting Backends per Task#

Tasks that support more than one backend define a Hydra preset on SimulationCfg.physics. The example below shows the cartpole task config which declares all three backends side by side:

from isaaclab.physics import PhysxAutoCfg
from isaaclab_newton.physics import MJWarpSolverCfg, NewtonCfg
from isaaclab_ov.physics import OvPhysxCfg
from isaaclab_physx.physics import PhysxCfg

@configclass
class CartpolePhysicsCfg(PresetCfg):
    isaacsim_physx: PhysxCfg = PhysxCfg()
    ovphysx: OvPhysxCfg = OvPhysxCfg()
    physx: PhysxAutoCfg = PhysxAutoCfg(
        isaacsim_physx=isaacsim_physx,
        ovphysx=ovphysx,
    )
    default: PhysxCfg = isaacsim_physx
    newton_mjwarp: NewtonCfg = NewtonCfg(solver_cfg=MJWarpSolverCfg())

With no selector, the task uses concrete Isaac Sim PhysX. Users can select a backend with physics=<name>; physics=physx explicitly opts into automatic selection between the configured PhysX-family implementations. See Backend and Solver Presets for the full Hydra interaction.