Implementation:Haosulab ManiSkill Draw

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

Overview

Concrete implementation of the free drawing base task environment in ManiSkill.

Description

The TableTopFreeDrawEnv provides a table with a white canvas and a robot with a stick that draws red lines. This environment is primarily a reference implementation for building custom drawing tasks. Drawing is simulated by placing cylinder-shaped dots on the canvas surface when the brush (robot TCP) is close enough.

Registered as TableTopFreeDraw-v1 with max_episode_steps=1000. The supported robot is panda_stick (PandaStick). The reward mode is "none" only, as there is no specific drawing objective.

Key parameters: MAX_DOTS=1010 (total ink), DOT_THICKNESS=0.003, CANVAS_THICKNESS=0.02, BRUSH_RADIUS=0.01, BRUSH_COLORS=0.8, 0.2, 0.2, 1. No randomizations or success conditions are defined.

Usage

Use this environment as a starting point for creating custom drawing tasks. It demonstrates the painting mechanism and can be extended by subclasses (e.g., DrawTriangle, DrawSVG) that add specific target shapes and success conditions.

Code Reference

Source Location

• Repository: Haosulab_ManiSkill
• File: mani_skill/envs/tasks/drawing/draw.py

Signature

@register_env("TableTopFreeDraw-v1", max_episode_steps=1000)
class TableTopFreeDrawEnv(BaseEnv):
    SUPPORTED_REWARD_MODES = ["none"]
    SUPPORTED_ROBOTS: ["panda_stick"]
    agent: PandaStick
    MAX_DOTS = 1010
    BRUSH_RADIUS = 0.01

Import

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

I/O Contract

Inputs

Name	Type	Required	Description
obs_mode	str	No	Observation mode
reward_mode	str	No	Reward mode: "none"
control_mode	str	No	Control mode for panda_stick robot

Outputs

Name	Type	Description
obs	dict/array	Observation including TCP pose
reward	float	Always 0 (no reward)
terminated	bool	Whether episode ended
truncated	bool	Whether episode hit max steps (1000)
info	dict	Empty dict (no evaluation metrics)

Usage Examples

Basic Usage

import gymnasium as gym
import mani_skill.envs

env = gym.make("TableTopFreeDraw-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