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 FloatingRobotiq2F85Gripper

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

Overview

Concrete tool for simulating a floating Robotiq 2F-85 adaptive gripper in ManiSkill environments.

Description

The FloatingRobotiq2F85Gripper is a Robotiq 2F-85 adaptive gripper mounted on a 6-DOF floating base. It has 12 total DOF: 6 root joints, 2 active outer knuckle joints (left/right_outer_knuckle_joint) with mimic control, and 4 passive finger joints (inner knuckle and inner finger joints). Self-collisions are disabled. The gripper uses very high stiffness (1e5) and damping (1e3) with a low force limit (0.1) and friction (0.05). Mechanical constraints for the Robotiq gripper are created via SAPIEN drives in _after_loading_articulation. Provides keyframes for open_facing_down, open_facing_up, and open_facing_side.

uid: floating_robotiq_2f_85_gripper

URDF path: {ASSET_DIR}/robots/robotiq_2f/floating_robotiq_2f_85.urdf

Supported control modes: pd_joint_pos, pd_joint_delta_pos

Usage

Use FloatingRobotiq2F85Gripper for grasping tasks requiring an adaptive gripper that conforms to object shape. The floating base allows free positioning in 3D. Suitable for grasping research, particularly when the arm kinematics are not needed and focus is on grasp strategy.

Code Reference

Source Location

Signature

@register_agent(asset_download_ids=["robotiq_2f"])
class FloatingRobotiq2F85Gripper(BaseAgent):
    uid = "floating_robotiq_2f_85_gripper"
    urdf_path = f"{ASSET_DIR}/robots/robotiq_2f/floating_robotiq_2f_85.urdf"
    disable_self_collisions = True
    root_joint_names = ["root_x_axis_joint", ..., "root_z_rot_joint"]
    keyframes = dict(
        open_facing_down=Keyframe(...), open_facing_up=Keyframe(...), open_facing_side=Keyframe(...)
    )

Import

from mani_skill.agents.robots.floating_robotiq_2f_85_gripper.floating_robotiq_2f_85_gripper import FloatingRobotiq2F85Gripper

I/O Contract

Inputs

Name Type Required Description
(inherited from BaseAgent)

Outputs

Name Type Description
robot agent FloatingRobotiq2F85Gripper Configured floating Robotiq gripper with base, finger mimic, and passive controllers

Usage Examples

Creating Environment with Robot

import gymnasium as gym
import mani_skill.envs

env = gym.make("PickCube-v1", robot_uids="floating_robotiq_2f_85_gripper")
obs, info = env.reset()

Related Pages

Page Connections

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