Implementation:Haosulab ManiSkill TwoRobotPickCube

Knowledge Sources	Haosulab_ManiSkill
Domains	Robotics, Simulation, Tabletop_Manipulation
Last Updated	2026-02-15 08:00 GMT

Overview

Concrete implementation of the two-robot cooperative cube picking task environment in ManiSkill.

Description

The TwoRobotPickCube environment features two Panda robot arms that must cooperate to pick up a red cube and lift it to a goal location. The cube is within reach of the left robot but not the right, while the goal is within reach of the right robot but not the left. This forces handover coordination between the two robots.

Registered as TwoRobotPickCube-v1 with max_episode_steps=100. Uses MultiAgent with two Panda robots. Reward modes include "normalized_dense", "dense", "sparse", and "none".

Randomizations: cube z-rotation randomized, cube xy position in left robot's reachable workspace, goal position in right robot's reachable workspace (marked by green sphere). Success requires the cube to be within the goal threshold distance.

Usage

Use this environment for multi-agent cooperative manipulation research. It tests coordination, handover, and joint planning between two robot arms.

Code Reference

Source Location

• Repository: Haosulab_ManiSkill
• File: mani_skill/envs/tasks/tabletop/two_robot_pick_cube.py

Signature

@register_env("TwoRobotPickCube-v1", max_episode_steps=100)
class TwoRobotPickCube(BaseEnv):
    agent: MultiAgent

Import

import gymnasium as gym
import mani_skill.envs
env = gym.make("TwoRobotPickCube-v1")

I/O Contract

Inputs

Name	Type	Required	Description
obs_mode	str	No	Observation mode
reward_mode	str	No	Reward mode: "normalized_dense", "dense", "sparse", "none"
control_mode	str	No	Control mode for the two Panda robots

Outputs

Name	Type	Description
obs	dict/array	Observation including both robots' TCP poses, cube pose, goal position
reward	float	Dense reward based on cooperative reaching, grasping, and placing
terminated	bool	Whether episode ended by success
truncated	bool	Whether episode hit max steps (100)
info	dict	Contains success flag

Usage Examples

Basic Usage

import gymnasium as gym
import mani_skill.envs

env = gym.make("TwoRobotPickCube-v1", obs_mode="state", render_mode="rgb_array")
obs, info = env.reset()
for _ in range(100):
    action = env.action_space.sample()
    obs, reward, terminated, truncated, info = env.step(action)
    if terminated or truncated:
        obs, info = env.reset()
env.close()

Related Pages

• Environment:Haosulab_ManiSkill_Python_SAPIEN_Core