feat(visualization): add foxglove support (#3902)

* Add Foxglove display mode for teleoperate

Add a --display_mode flag (rerun|foxglove) to lerobot-teleoperate. When set
to foxglove, stream observations/actions over a Foxglove WebSocket server:
images as RawImage/CompressedImage, scalars as typed JSON channels with
schemas generated from the feature names (sanitized so paths don't need
quoting). Adds a `foxglove` extra.

* Add Foxglove display mode to lerobot-record

Wire the --display_mode flag (rerun|foxglove) into lerobot-record, matching
lerobot-teleoperate: route init/log through the backend-agnostic dispatchers
and stop the visualization backend on exit.

* update foxglove-sdk to 0.25.1

* Use static lerobot.Scalars schema for Foxglove state topics

Replace the per-topic JSON schema derived from feature names with a single
static lerobot.Scalars schema: a scalars array of {label, value} objects. The
same schema fits any robot regardless of which observation/action features it
reports, and the label field lets Foxglove name each series automatically so
one filtered path plots every feature.

* add foxglove option to dataset viz

* Make Foxglove dataset playback loop the sole frame emitter

Address review: the listener no longer emits frames, it only mutates
playback state and queues a one-shot seek index that the playback loop
services. The loop is now the only caller of emit_frame, so concurrent
random access into the on-disk dataset / video decoder never overlaps.

Also remove the dead server_holder and tighten the _foxglove_safe_name
docstring to state what it does and why.

* Label Foxglove dataset scalars with feature dimension names

Use the dataset's per-dimension feature names (e.g. joint names) as the
Foxglove series labels for /observation/state and /action/state instead
of bare indices. LeRobot stores `names` inconsistently (flat list,
{category: [...]}, or {name: index}), so _feature_dim_names handles each
and falls back to indices on any unknown format or length mismatch.

* Make Foxglove server host bindable and refactor topic/channel handling

Pass display_ip through as the Foxglove WebSocket bind host (127.0.0.1
for local only, 0.0.0.0 for all interfaces) instead of always binding
locally. In lerobot-dataset-viz, fold the separate --port into --web-port
so one flag covers both the Rerun web viewer and the Foxglove server port.

Add a _foxglove_topic() helper and thread a per-topic channel cache
through the log helpers so dataset playback stays self-contained instead
of mutating the module-global cache. Promote SUCCESS to constants.py.

* feat(viz): add support for foxglove in rollout + add to viz tag

* fix(docs): remove misleading installation note

* fix(visualization): no duplicated prefix, consolidated norm + warnings log

* chore(viz): minor improvements

* refactor(viz): split files + autoplay + updated docs + added minimal tests

* fix(viz): right tags + warning

* feat(deprecated ws-port): removing rerun's depreacted ws-port parameter in dataset visualization

* chore(web ports): adding global variables for default foxglove/rerun web ports

* feat(depth): adding depth support to foxglove visualizer. Because of foxglove limitations (min and max values on RawImage cannot be set from the SDK), depth is normalized between [0,1] when a depth range is provided.

* fix(rerun depth range): making rerun depth range computation safe against missing stats

* chore(foxglove depth): make it simple, and make it work.

* fix(scaling): fixing depth frames scaling

---------

Co-authored-by: Roman Shtylman <roman@foxglove.dev>
Co-authored-by: Caroline Pascal <caroline8.pascal@gmail.com>

docs/source/il_robots.mdx

@@ -126,7 +126,7 @@ import time
 from lerobot.teleoperators.so_leader import SO101Leader, SO101LeaderConfig
 from lerobot.robots.so_follower import SO101Follower, SO101FollowerConfig
 from lerobot.cameras.opencv import OpenCVCameraConfig
-from lerobot.utils.visualization_utils import init_rerun, log_rerun_data, shutdown_rerun
+from lerobot.utils.visualization_utils import init_visualization, log_visualization_data, shutdown_visualization
 
 robot_config = SO101FollowerConfig(
     port="/dev/tty.usbmodem5AB90687491",
@@ -142,7 +142,7 @@ teleop_config = SO101LeaderConfig(
     id="my_leader_arm",
 )
 
-init_rerun(session_name="teleoperation")
+init_visualization("rerun", session_name="teleoperation")  # pass "foxglove" to stream to Foxglove instead
 
 robot = SO101Follower(robot_config)
 teleop_device = SO101Leader(teleop_config)
@@ -158,7 +158,7 @@ while True:
     observation = robot.get_observation()
     action = teleop_device.get_action()
     robot.send_action(action)
-    log_rerun_data(observation=observation, action=action)
+    log_visualization_data("rerun", observation=observation, action=action)
 
     elapsed_time = time.perf_counter() - start_time
     sleep_time = TIME_PER_FRAME - elapsed_time
@@ -223,7 +223,7 @@ from lerobot.teleoperators.so_leader.config_so_leader import SO101LeaderConfig
 from lerobot.teleoperators.so_leader.so_leader import SO101Leader
 from lerobot.common.control_utils import init_keyboard_listener
 from lerobot.utils.utils import log_say
-from lerobot.utils.visualization_utils import init_rerun
+from lerobot.utils.visualization_utils import init_visualization
 from lerobot.scripts.lerobot_record import record_loop
 from lerobot.processor import make_default_processors
 
@@ -270,7 +270,7 @@ def main():
 
     # Initialize the keyboard listener and rerun visualization
     _, events = init_keyboard_listener()
-    init_rerun(session_name="recording")
+    init_visualization("rerun", session_name="recording")
 
     # Connect the robot and teleoperator
     robot.connect()

docs/source/using_dataset_tools.mdx

@@ -265,6 +265,8 @@ lerobot-dataset-viz \
 
 Once executed, the tool opens `rerun.io` and displays the camera streams, robot states, and actions for the selected episode.
 
+To use [Foxglove](https://foxglove.dev) instead of Rerun, install the extra add `--display-mode foxglove`. This starts a WebSocket server (connect the Foxglove app to `ws://127.0.0.1:8765`) that serves the episode as a seekable timeline you can play/pause and scrub.
+
 For advanced usage—including visualizing datasets stored on a remote server—run:
 
 ```bash