Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Haosulab ManiSkill GoogleRobot

From Leeroopedia
Knowledge Sources
Domains Robotics, Simulation, Manipulation
Last Updated 2026-02-15 08:00 GMT

Overview

Concrete tool for simulating the Google Robot in ManiSkill environments.

Description

The GoogleRobot is a minimal robot agent definition (31 lines) that loads a URDF model of the Google mobile manipulator. It has an overhead camera sensor configured with 640x512 resolution and a custom intrinsic matrix (fx=425.0, fy=413.1, cx=305.0, cy=233.0) mounted on link_camera. The URDF config is empty, relying on defaults. No controller configs or keyframes are defined in the file -- they are inherited from BaseAgent. This is a work-in-progress robot model; the source contains a TODO note about adding a mobile base and proper real2sim modeling.

uid: googlerobot

URDF path: {ASSET_DIR}/robots/googlerobot/google_robot_meta_sim_fix_fingertip.urdf

Supported control modes: (inherited from BaseAgent defaults)

Usage

Use GoogleRobot for real2sim transfer experiments that replicate the Google Robot hardware. The camera is configured with real-world intrinsic parameters for visual policy transfer. Primarily used for simulation of Google's manipulation research platform.

Code Reference

Source Location

Signature

@register_agent(asset_download_ids=["googlerobot"])
class GoogleRobot(BaseAgent):
    uid = "googlerobot"
    urdf_path = f"{ASSET_DIR}/robots/googlerobot/google_robot_meta_sim_fix_fingertip.urdf"
    urdf_config = dict()

Import

from mani_skill.agents.robots.googlerobot.googlerobot import GoogleRobot

I/O Contract

Inputs

Name Type Required Description
(inherited from BaseAgent)

Outputs

Name Type Description
robot agent GoogleRobot Configured robot with overhead camera sensor using real-world intrinsics

Usage Examples

Creating Environment with Robot

import gymnasium as gym
import mani_skill.envs

env = gym.make("PickCube-v1", robot_uids="googlerobot")
obs, info = env.reset()

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment