Using Visualizer Tiled Cameras

Using Visualizer Tiled Cameras#

For general visualizer documentation, see Visualization.

The visualizer tiled camera view is a live monitoring and debugging tool. It opens a non-interactive panel in the Kit or Newton visualizer and displays tiled camera views across all selected environments. They can stream observation camera data or generate cameras that follow the robots.

This guide is accompanied by the run_tiled_camera_visualizer.py script in the IsaacLab/scripts/tutorials/07_visualizers directory.

Running this script demonstrates two ways to use tiled cameras:

configured tiled cameras pointed at and following moving Anymal-D robots shown in the Kit visualizer
streaming from existing wrist-mounted robot cameras shown in the Newton visualizer

Note: Visualizer tiled cameras are currently supported only in the Kit and Newton visualizers. Either visualizer can be used to run either example.

Code for run_tiled_camera_visualizer.py

# Copyright (c) 2022-2026, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md).
# All rights reserved.
#
# SPDX-License-Identifier: BSD-3-Clause

"""
This script demonstrates the visualizer tiled camera panel.

.. code-block:: bash

    # Kit visualizer tiled camera panel
    ./isaaclab.sh -p scripts/tutorials/07_visualizers/run_tiled_camera_visualizer.py \
        --enable_cameras --task Isaac-Velocity-Rough-Anymal-D-v0 --num_envs 256 --viz kit

    # Newton visualizer tiled camera panel
    ./isaaclab.sh -p scripts/tutorials/07_visualizers/run_tiled_camera_visualizer.py \
        --task Isaac-Stack-Cube-Galbot-Left-Arm-Gripper-Visuomotor-v0 --num_envs 25 --viz newton

"""

from __future__ import annotations

import argparse
import contextlib
import sys

import gymnasium as gym
import torch

import isaaclab_tasks  # noqa: F401

with contextlib.suppress(ImportError):
    import isaaclab_tasks_experimental  # noqa: F401
from isaaclab_tasks.utils import (
    add_launcher_args,
    launch_simulation,
    resolve_task_config,
    setup_preset_cli,
)

KIT_DEFAULT_TASK = "Isaac-Velocity-Rough-Anymal-D-v0"
NEWTON_DEFAULT_TASK = "Isaac-Stack-Cube-Galbot-Left-Arm-Gripper-Visuomotor-v0"
SUPPORTED_TILED_VISUALIZERS = {"kit", "newton"}
UNSUPPORTED_TILED_VISUALIZERS = {"rerun", "viser"}


def _resolve_env_regex_path(prim_path: str) -> str:
    """Resolve scene config env namespace macros to the cloned-env regex."""
    return prim_path.format(ENV_REGEX_NS="/World/envs/env_.*")


def _requested_visualizers(args_cli: argparse.Namespace) -> list[str]:
    """Return requested visualizers, defaulting to Kit for this tutorial."""
    visualizers = args_cli.visualizer or ["kit"]
    visualizers = [str(visualizer).lower() for visualizer in visualizers]

    if "none" in visualizers:
        raise ValueError("This demo requires a tiled-camera visualizer. Use '--viz kit' or '--viz newton'.")
    unsupported = sorted(set(visualizers) & UNSUPPORTED_TILED_VISUALIZERS)
    if unsupported:
        raise ValueError(
            "The visualizer tiled camera panel is only implemented for Kit and Newton. "
            f"Unsupported selection: {unsupported}."
        )
    unknown = sorted(set(visualizers) - SUPPORTED_TILED_VISUALIZERS)
    if unknown:
        raise ValueError(f"Unknown visualizer selection for this demo: {unknown}.")
    return visualizers


def _make_kit_visualizer_cfg(env_cfg):
    """Create the Kit tiled-camera visualizer for the selected task."""
    from isaaclab_visualizers.kit import KitVisualizerCfg

    visualizer_cfg = KitVisualizerCfg()
    visualizer_cfg.tiled_cam_view = True
    visualizer_cfg.tiled_cam_num = 36

    ego_cam_cfg = getattr(env_cfg.scene, "ego_cam", None)
    if ego_cam_cfg is not None:
        visualizer_cfg.tiled_cam_prim_path = _resolve_env_regex_path(ego_cam_cfg.prim_path)
        visualizer_cfg.tiled_cam_eye = None
        visualizer_cfg.tiled_cam_target_prim_path = None
        return visualizer_cfg

    visualizer_cfg.tiled_cam_prim_path = None
    # Here is an alternative eye position for a top down view
    # visualizer_cfg.tiled_cam_eye = (0.0, 0.0, 5.0)
    visualizer_cfg.tiled_cam_eye = (3.0, 3.0, 3.0)
    visualizer_cfg.tiled_cam_target_prim_path = "/World/envs/*/Robot/base"
    return visualizer_cfg


def _make_newton_visualizer_cfg(env_cfg):
    """Create the Newton tiled-camera visualizer for the selected task."""
    from isaaclab_visualizers.newton import NewtonVisualizerCfg

    visualizer_cfg = NewtonVisualizerCfg()
    visualizer_cfg.tiled_cam_view = True
    visualizer_cfg.tiled_cam_num = 12

    ego_cam_cfg = getattr(env_cfg.scene, "ego_cam", None)
    if ego_cam_cfg is not None:
        visualizer_cfg.tiled_cam_prim_path = _resolve_env_regex_path(ego_cam_cfg.prim_path)
        visualizer_cfg.tiled_cam_eye = None
        visualizer_cfg.tiled_cam_target_prim_path = None
        return visualizer_cfg

    # Here are other robot mounted camera options for this environment
    # visualizer_cfg.tiled_cam_prim_path = "/World/envs/env_.*/Robot/left_arm_camera_sim_view_frame/left_camera"
    # visualizer_cfg.tiled_cam_prim_path = "/World/envs/env_.*/Robot/right_arm_camera_sim_view_frame/right_camera"
    visualizer_cfg.tiled_cam_prim_path = None
    visualizer_cfg.tiled_cam_eye = (3.0, 3.0, 3.0)
    visualizer_cfg.tiled_cam_target_prim_path = "/World/envs/*/Robot/base"
    return visualizer_cfg


def _configure_visualizers(env_cfg, args_cli: argparse.Namespace) -> None:
    """Attach tiled camera visualizer configs to the environment simulation config."""
    visualizers = _requested_visualizers(args_cli)
    args_cli.visualizer = visualizers
    env_cfg.sim.visualizer_cfgs = [
        _make_kit_visualizer_cfg(env_cfg) if visualizer == "kit" else _make_newton_visualizer_cfg(env_cfg)
        for visualizer in visualizers
    ]


def _resolve_task(args_cli: argparse.Namespace) -> str:
    """Resolve the task for the selected visualizer."""
    if args_cli.task is not None:
        return args_cli.task
    if "newton" in _requested_visualizers(args_cli):
        return NEWTON_DEFAULT_TASK
    return KIT_DEFAULT_TASK


# add argparse arguments
parser = argparse.ArgumentParser(description="Showcase the Kit/Newton visualizer tiled camera panel.")
parser.add_argument("--num_envs", type=int, default=None, help="Number of environments to simulate.")
parser.add_argument("--task", type=str, default=None, help="Name of the task.")
# append AppLauncher cli args
add_launcher_args(parser)
args_cli, hydra_args = setup_preset_cli(parser)
args_cli.task = _resolve_task(args_cli)
sys.argv = [sys.argv[0]] + hydra_args


def main():
    """Run a random-action environment with a tiled camera visualizer."""
    # parse configuration via Hydra (supports preset selection, e.g. presets=newton_mjwarp)
    env_cfg, _ = resolve_task_config(args_cli.task, "")
    _configure_visualizers(env_cfg, args_cli)

    with launch_simulation(env_cfg, args_cli):
        # override with CLI arguments
        env_cfg.scene.num_envs = args_cli.num_envs if args_cli.num_envs is not None else env_cfg.scene.num_envs
        env_cfg.sim.device = args_cli.device if args_cli.device is not None else env_cfg.sim.device

        # create environment
        env = gym.make(args_cli.task, cfg=env_cfg)

        # print info (this is vectorized environment)
        print(f"[INFO]: Gym observation space: {env.observation_space}")
        print(f"[INFO]: Gym action space: {env.action_space}")
        env.reset()

        # keep stepping until all visualizer windows have been closed
        sim = env.unwrapped.sim
        if not sim.visualizers:
            print("[WARN]: No visualizers found. Exiting.")
            env.close()
            return

        while True:
            if sim.visualizers and not any(v.is_running() and not v.is_closed for v in sim.visualizers):
                break
            with torch.inference_mode():
                actions = 2 * torch.rand(env.action_space.shape, device=env.unwrapped.device) - 1
                env.step(actions)

        env.close()


if __name__ == "__main__":
    main()

Example One: Following Anymal-D Robots#

The Kit Visualizer shows the tiled camera view in a separate tab inside the main Viewport window. The highlighted tab area in the figures below shows where to toggle between the interactive viewport and the visualizer tiled camera view.

Kit visualizer interactive viewport for Anymal-D robots — Kit visualizer showing the default interactive viewport.#

Kit visualizer tiled camera view for Anymal-D robots — Kit visualizer showing the tiled camera view generated for selected Anymal-D robots.#

Note, you can also display the main visualizer camera and the tiled camera view side by side for dual monitoring.

To run the tutorial with the args for this example, use:

python scripts/tutorials/07_visualizers/run_tiled_camera_visualizer.py --enable_cameras --task Isaac-Velocity-Rough-Anymal-D-v0 --num_envs 256 --viz kit

Within the script, you’ll find the KitVisualizerCfg configuration used to generate this example. You can use this config as a template for your own use cases.

In this example, a set of cameras is created to point toward each robot’s base prim and follow its motion. The camera’s position, relative to the prim, is set by the tiled_cam_eye field of KitVisualizerCfg. For this demo, the camera is offset by (3.0, 3.0, 3.0) from each robot base. If you change tiled_cam_eye (for example, to (0, 0, 5)), the panel will show a top-down view instead.

In this example, there are 256 total environments, and we randomly sample 36 to stream to the tiled camera view.

Also note that the Kit visualizer tiled camera view requires passing the --enable_cameras CLI arg.

Example Two: Streaming from Robot-Mounted Cameras#

The Newton visualizer provides a tiled camera view in a lightweight OpenGL window. Use the highlighted Tiled Camera View dropdown in the left-hand sidebar to show or hide the tiled camera panel.

Newton visualizer interactive view for the Galbot cube stacking environment — Newton visualizer showing the default interactive viewport.#

Newton visualizer tiled camera view for Galbot wrist cameras — Newton visualizer showing the selected Galbot head-camera feeds in the tiled camera panel.#

In this example, we use the Galbot cube stacking environment, which comes with built-in wrist-mounted cameras. This setup provides an egocentric view of the gripper, table, and cubes in each selected environment.

To launch this example, run:

python scripts/tutorials/07_visualizers/run_tiled_camera_visualizer.py --task Isaac-Stack-Cube-Galbot-Left-Arm-Gripper-Visuomotor-v0 --num_envs 25 --viz newton

Within the script, the NewtonVisualizerCfg is configured to stream images from the existing camera sensor located at /World/envs/env_.*/Robot/head_camera_sim_view_frame/head_camera. This path points to the head camera, but you can edit the tiled_cam_prim_path field of NewtonVisualizerCfg in the script to show a different existing camera if needed.

In this demo, 25 environments are simulated, and 12 camera feeds are shown in the tiled panel by default.

Configuration notes#

To customize tiled camera behavior, edit the highlighted VisualizerCfg fields in run_tiled_camera_visualizer.py:

For generated cameras, tiled_cam_target_prim_path chooses the followed prim and tiled_cam_eye sets the camera offset from that prim.
For existing scene cameras, tiled_cam_prim_path must match an Isaac Lab Camera sensor in the selected task.
tiled_cam_num controls how many environment tiles are shown.

Troubleshooting#

If a generated view fails with a missing prim error, check that tiled_cam_target_prim_path resolves in each selected environment. Common template forms include /World/envs/*/... and /World/envs/env_.*/....
If an existing-camera view reports that no Isaac Lab camera owns the prim, check that tiled_cam_prim_path matches a Camera sensor in the task.
If rerun or viser is selected, use --viz kit or --viz newton instead. The tiled camera panel is currently implemented for Kit and Newton.
If the view is too expensive, reduce tiled_cam_num, --num_envs, or the camera resolution. The visualizer caps the tiled panel at 100 tiles.