Implementation:Haosulab ManiSkill PlugCharger

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

Overview

Concrete implementation of the charger plugging task environment in ManiSkill.

Description

The PlugChargerEnv requires a robot to pick up a charger and insert it into a receptacle on the table. Both the charger and receptacle have randomized positions and rotations on the XY plane.

Registered as PlugCharger-v1 with max_episode_steps=200. The supported robot is panda_wristcam (PandaWristCam). Reward modes include "normalized_dense", "dense", "sparse", and "none".

Randomizations include the charger position/rotation on the table and the receptacle position/rotation. The human render camera pose is fixed relative to the receptacle. Success is determined by the charger being properly inserted into the receptacle.

Usage

Use this environment for precision insertion research. The task requires accurate alignment of the charger prongs with the receptacle slots, testing both grasping and fine alignment skills.

Code Reference

Source Location

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

Signature

@register_env("PlugCharger-v1", max_episode_steps=200)
class PlugChargerEnv(BaseEnv):
    SUPPORTED_ROBOTS = ["panda_wristcam"]
    agent: Union[PandaWristCam]

Import

import gymnasium as gym
import mani_skill.envs
env = gym.make("PlugCharger-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 Panda robot

Outputs

Name	Type	Description
obs	dict/array	Observation including TCP pose, charger pose, receptacle pose
reward	float	Dense reward based on grasping, alignment, and insertion
terminated	bool	Whether episode ended by success
truncated	bool	Whether episode hit max steps (200)
info	dict	Contains success flag

Usage Examples

Basic Usage

import gymnasium as gym
import mani_skill.envs

env = gym.make("PlugCharger-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