Two robots, facing each other across the table, lift a pot by its two handles

robosuite-twoarm-lift-pandapanda variantrobosuiteFranka PandaManipulationhard

Reference solution, 77 of 400 steps.

Instruction

Two Franka Emika Panda (7-DoF) with its parallel-jaw gripper arms face each other across a table: robot0 on the -y side, robot1 on the +y side. The scene is robosuite's TwoArmLift environment (MuJoCo).

Goal: Lift the pot together: robot0 holds handle0, robot1 holds handle1. robosuite's TwoArmLift check: the pot's bottom is more than 10 cm above the table. The episode ends by itself at that moment.

The episode ends as solved the moment the check first passes (you do not need to call robo done then).

This robot

The action has 14 numbers: robot0's DX DY DZ DROLL DPITCH DYAW GRIP, then robot1's, each in [-1, 1]: robosuite's OSC_POSE end-effector commands plus the gripper, 20 steps per second, all in the world frame (the same frame for both robots). DX/DY/DZ = 1.0 asks for a 5 cm move (held at 1.0 a hand travels about 1.1 cm per step); DROLL/DPITCH/DYAW rotate that hand about the world x/y/z axes (1.0 asks for 0.5 rad); GRIP +1 closes, -1 opens, 0 keeps the fingers as they are (they move over about 5 steps).
robo move-to and robo grip are not available (two robots); use robo act.
World frame, metres: +x points away from the table edge between the robots, +y to the robot1 side, +z up.
robo observe fields: for each robot i in 0, 1: roboti_hand_pos, roboti_hand_quat (x, y, z, w), and, if it has a gripper, roboti_gripper_open (finger-pad distance, metres) and roboti_gripper_yaw_deg (direction of the fingertip line in the table plane, degrees from +x, in [-90, 90)); pot_pos, pot_quat, pot_yaw_deg; handle0_pos (robot0's handle), handle1_pos (robot1's handle); table_height. Every <object>_quat (x, y, z, w) comes with <object>_yaw_deg, the object's heading about the vertical axis (its local x axis, degrees from +x).
robo observe --image saves the frontview camera; add --camera robot0_eye_in_hand for the wrist camera. Images are 320x320.
The step budget is 400 steps.
Each handle is a bar; close the fingers across it (the fingertip line along the direction from the pot's centre to that handle). Lift both hands at the same rate, or the pot tips.

How the robot is controlled and scored

You are controlling a simulated robot. Read the task below, then solve it by running the robo command in your shell (start with robo info and robo observe). Keep going until the task is done, then call robo done once. Do not stop to ask questions; there is no human to answer.

How to control the robot

You are the robot's policy. You act only through the robo command in your shell. There is no other way to move the robot, and you cannot read or change the simulator, the scoring, or other files to succeed; the episode server judges the final physical state itself.

robo info                         # action space, available skills, step budget
robo observe                      # robot and object state as numbers
robo observe --image              # also saves a camera image and prints its path (open it to look)
robo act DX DY DZ GRIP [--repeat N]   # low-level action, applied N times (N <= 50)
robo move-to X Y Z [--grip G]     # skill: move the gripper toward a point (if enabled for this task)
robo grip G [--steps N]           # skill: hold position and set the gripper (+1 close, -1 open)
robo done "short summary"         # end the episode and ask for scoring
robo give-up "reason"             # end the episode without claiming success

Positions are in metres in the world frame (x, y on the table plane, z up).
The episode has a fixed step budget (see robo info); every simulated step counts, including skills.
Unless the task says otherwise, success is judged about 10 steps after you call robo done, with the robot holding still, so the goal must still be true when the robot stops.
Work in small steps and re-observe after each motion. Call robo done exactly once when finished.

Run this task

ROBOUSE_ORACLE_TOKEN=$(openssl rand -hex 16) \
  bench eval run \
    -d arise-initiative/robosuite@0.2 \
    --registry https://robouse.ai/hub/registry.json \
    --agent oracle \
    --include robosuite-twoarm-lift-panda

Embodiment

Franka Panda

Bimanual · robosuite 1.5.2

Action · 14 numbers per step

r0_dxr0_dx1r0_dyr0_dy1r0_dzr0_dz1r0_drollr0_droll1r0_dpitchr0_dpitch1r0_dyawr0_dyaw1r0_gripr0_grip1r1_dxr1_dx1r1_dyr1_dy1r1_dzr1_dz1r1_drollr1_droll1r1_dpitchr1_dpitch1r1_dyawr1_dyaw1r1_gripr1_grip1

OSC end-effector deltas in the world frame, 20 steps per second. dx/dy/dz: 1.0 asks for a 5 cm move (held at 1.0 the hand travels about 1.1 cm per step); droll/dpitch/dyaw: rotation about world x/y/z, 1.0 asks for 0.5 rad. grip: +1 close, -1 open, 0 keep (fingers move gradually). Two robots: robot0's numbers (prefix r0_) come first, then robot1's (r1_).

Skills

None: low-level actions only.

Observation

State: positions of the robot and objects

robot0_hand_posrobot0_hand_quatrobot0_gripper_openrobot0_gripper_yaw_degrobot1_hand_posrobot1_hand_quatrobot1_gripper_openrobot1_gripper_yaw_degpot_pospot_quatpot_yaw_deghandle0_poshandle1_postable_height

Camera

frontview

Budget and scoring

400 stepsends when first reached

In datasets

Pinned to robohub commit e472b1a1e041. The verifier and the reference solution are not published.

Filter models

					Trial
GPT-6 Astra · Codex	Solved	67 / 400	60 s	Sep 27, 2026	Trial Compare
Kimi K3 · Claude Code	Solved	60 / 400	3 min	Sep 28, 2026	Trial Compare
Kimi K3 · mini-swe-agent	Solved	54 / 400	4 min	Sep 28, 2026	Trial Compare
GLM-5.3 · mini-swe-agent	Solved	92 / 400	2 min	Sep 27, 2026	Trial Compare
GLM-5.3 · Claude Code	Solved	59 / 400	3 min	Sep 27, 2026	Trial Compare
GLM-5.3 · Codex	Infra failure	17 / 400	32 s	Sep 27, 2026	Trial Compare

These trials ran on version 0.1, now deprecated (superseded by 0.2).