LeRobot SO-101 Tabletop Isaac Sim Environment Release
Overview
LeRobot releases an Isaac Sim 6.2 environment for the SO-101 robotic arm, featuring a simulated tabletop setup with wooden cubes and a green box. The environment supports RGB observations from front and wrist cameras, and is compatible with policies trained in MuJoCo. It can be run locally with an NVIDIA RTX GPU and the Isaac Sim simulator.
From LeRobot — Model repository updates
Event evidence and corrections
1 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Environment: simulation
“SO-101 tabletop (Isaac Sim) A LeRobot EnvHub environment built natively in NVIDIA Isaac Sim 6.2: an SO-101 arm in the turquoise of the LeRobot kits, four painted wooden 3 cm cubes and a green open box on a table in a simple room, simulated by PhysX and rendered with RTX. The layout, cameras, observations, actions and LEROBOT_SIM match the MuJoCo version, lerobot/so101-tabletop-mujoco , so the same policies and comman”
Exact source · revision 6huggingface
Reported quantity · observation pixels: 480 other · Basis not reported · Differing source assertions
“ds run against both. Observation pixels : front (scene camera) and wrist (gripper camera), 480×640 RGB; agent_pos : 6 joint positions Action 6 absolute joint position targets: shoulder_pan , shoulder_lift , elbow_flex , wrist_flex , wrist_roll in degrees, gripper 0-100 (the units of LeRobot's so101_follower with use_degrees=True ) Control rate 30 fps (8 PhysX steps per control step) Task "Put all the cubes in the gre”
Exact source · revision 6huggingface
Reported quantity · observation pixels: 640 other · Basis not reported · Differing source assertions
“ds run against both. Observation pixels : front (scene camera) and wrist (gripper camera), 480×640 RGB; agent_pos : 6 joint positions Action 6 absolute joint position targets: shoulder_pan , shoulder_lift , elbow_flex , wrist_flex , wrist_roll in degrees, gripper 0-100 (the units of LeRobot's so101_follower with use_degrees=True ) Control rate 30 fps (8 PhysX steps per control step) Task "Put all the cubes in the gre”
Exact source · revision 6huggingface
Reported quantity · control rate: 30 other · Basis not reported
“ds run against both. Observation pixels : front (scene camera) and wrist (gripper camera), 480×640 RGB; agent_pos : 6 joint positions Action 6 absolute joint position targets: shoulder_pan , shoulder_lift , elbow_flex , wrist_flex , wrist_roll in degrees, gripper 0-100 (the units of LeRobot's so101_follower with use_degrees=True ) Control rate 30 fps (8 PhysX steps per control step) Task "Put all the cubes in the gre”
Exact source · revision 6huggingface
Reported quantity · episode length: 3600 other · Basis not reported
“en box." Reward the fraction of cubes in the box at each step (0, 0.25, ... 1); info["cubes_in_box"] gives the count Episode end success (terminated) when all four cubes are in the box; truncated after 3600 steps (2 minutes), set with episode_length Reset seeded cube positions and yaws, joint noise Isaac Sim starts once per process, in make_env : about 20 s, plus a few minutes of shader compilation the first time on”
Exact source · revision 6huggingface
Reported quantity · step time: 80 other · Basis not reported
“a machine or in a container. It holds one world, so make_env takes n_envs=1 . A step takes about 80 ms on an RTX 3080 Laptop GPU, so lockstep evaluation is exact, while realtime runs slower than 30 fps. The arm asset is bundled, so the environment needs no network access at runtime. With the LeRobot simulator server From a LeRobot checkout, start the server. The image installs packages.txt (system libraries) and requ”
Exact source · revision 6huggingface
Reported quantity · fps: 30 other · Basis not reported
“irements.txt (Isaac Sim 6.2 from PyPI and NVIDIA's index, Python 3.12); it needs an NVIDIA RTX GPU and the NVIDIA Container Toolkit: uv run scripts/run_sim.py --envhub lerobot/so101-tabletop-isaac Then run a policy against it, for example: lerobot-rollout --robot.type=remote --robot.endpoint=tcp/127.0.0.1:7448 \ --robot.deployment=envhub --robot.task=so101_tabletop \ --policy.path=<your SO-101 checkpoint> --fps=30 Ob”
Exact source · revision 6huggingface
Reported quantity · number of cubes: 4 other · Basis not reported
“en box." Reward the fraction of cubes in the box at each step (0, 0.25, ... 1); info["cubes_in_box"] gives the count Episode end success (terminated) when all four cubes are in the box; truncated after 3600 steps (2 minutes), set with episode_length Reset seeded cube positions and yaws, joint noise Isaac Sim starts once per process, in make_env : about 20 s, plus a few minutes of shader compilation the first time on”
Exact source · revision 6huggingface
Reported quantity · reward fraction: 0 other · Basis not reported
“en box." Reward the fraction of cubes in the box at each step (0, 0.25, ... 1); info["cubes_in_box"] gives the count Episode end success (terminated) when all four cubes are in the box; truncated after 3600 steps (2 minutes), set with episode_length Reset seeded cube positions and yaws, joint noise Isaac Sim starts once per process, in make_env : about 20 s, plus a few minutes of shader compilation the first time on”
Exact source · revision 6huggingface
Evidence dependency changes (4)
- 2026-10-30T22:52:40.246Z · evidence updated · source revision 6. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T22:52:25.638Z · evidence updated · source revision 6. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-29T02:50:42.362Z · evidence updated · source revision 6. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-28T03:26:40.045Z · evidence updated · source revision 5. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- LeRobot — Model repository updatesSignalLeRobot SO-101 Tabletop Environment in Isaac Sim 6.2
LeRobot releases an Isaac Sim 6.2 environment for the SO-101 robotic arm, featuring a simulated tabletop setup with wooden cubes and a green box. The environment supports RGB observations from front and wrist cameras, and is compatible with policies trained in MuJoCo. It can be run locally with an NVIDIA RTX GPU and the Isaac Sim simulator.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).