Implementation:Haosulab ManiSkill DrawTriangle

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

Overview

Concrete implementation of the triangle drawing task environment in ManiSkill.

Description

The DrawTriangleEnv instantiates a table with a white canvas and a robot with a stick that must trace a triangle outline. The robot draws red lines by placing colored dots on the canvas. Key parameters include MAX_DOTS=300, BRUSH_RADIUS=0.01, and a success THRESHOLD of 0.025.

Registered as DrawTriangle-v1 with max_episode_steps=300. The supported robot is panda_stick (PandaStick). The reward mode is "sparse" and success is measured by how well drawn points cover the goal triangle edges within the distance threshold.

Randomizations include the triangle position on the xy-plane and its z-rotation in range [0, 2*pi]. The triangle is constructed from three vertices connected by line segments.

Usage

Use this environment for learning geometric drawing behaviors. It provides a simpler target shape compared to DrawSVG, making it a good starting point for drawing task research.

Code Reference

Source Location

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

Signature

@register_env("DrawTriangle-v1", max_episode_steps=300)
class DrawTriangleEnv(BaseEnv):
    SUPPORTED_REWARD_MODES = ["sparse"]
    SUPPORTED_ROBOTS: ["panda_stick"]
    agent: PandaStick
    MAX_DOTS = 300
    BRUSH_RADIUS = 0.01
    THRESHOLD = 0.025

Import

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

I/O Contract

Inputs

Name	Type	Required	Description
obs_mode	str	No	Observation mode
reward_mode	str	No	Reward mode: "sparse"
control_mode	str	No	Control mode for panda_stick robot

Outputs

Name	Type	Description
obs	dict/array	Observation including TCP pose and triangle goal positions
reward	float	Sparse reward based on coverage of triangle edges
terminated	bool	Whether episode ended by success/failure
truncated	bool	Whether episode hit max steps (300)
info	dict	Contains success flag and coverage metrics

Usage Examples

Basic Usage

import gymnasium as gym
import mani_skill.envs

env = gym.make("DrawTriangle-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