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 WidowX250S

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

Overview

Concrete tool for simulating the WidowX 250S robot arm in ManiSkill environments.

Description

The WidowX250S is a 6-DOF robot arm with 2 gripper finger joints. The arm joints are: waist, shoulder, elbow, forearm_roll, wrist_angle, wrist_rotate. The gripper has left_finger and right_finger joints. This is a minimal agent definition that does not define its own controller configs or keyframes (relying on BaseAgent defaults). The robot provides finger link references (left_finger_link, right_finger_link) and a grasping detection method. The URDF config is empty, using default materials and collision settings. This is a work-in-progress model with a TODO note about proper real2sim modeling.

uid: widowx250s

URDF path: {ASSET_DIR}/robots/widowx/wx250s.urdf

Supported control modes: (inherited from BaseAgent defaults)

Usage

Use WidowX250S for manipulation tasks targeting the Interbotix WidowX 250S hardware. Suitable for real2sim transfer experiments and basic manipulation research with a low-cost arm platform.

Code Reference

Source Location

Signature

@register_agent(asset_download_ids=["widowx250s"])
class WidowX250S(BaseAgent):
    uid = "widowx250s"
    urdf_path = f"{ASSET_DIR}/robots/widowx/wx250s.urdf"
    arm_joint_names = ["waist", "shoulder", "elbow", "forearm_roll", "wrist_angle", "wrist_rotate"]
    gripper_joint_names = ["left_finger", "right_finger"]

Import

from mani_skill.agents.robots.widowx.widowx import WidowX250S

I/O Contract

Inputs

Name Type Required Description
(inherited from BaseAgent)

Outputs

Name Type Description
robot agent WidowX250S Configured 6-DOF arm with 2-finger gripper and grasping detection

Usage Examples

Creating Environment with Robot

import gymnasium as gym
import mani_skill.envs

env = gym.make("PickCube-v1", robot_uids="widowx250s")
obs, info = env.reset()

Related Pages

Page Connections

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