Soft-Robot Control Environment (gym-softrobot)

Gymnasium environments for soft-robot control, powered by PyElastica. The package includes bio-inspired soft-slender-robot simulations.

Installation

gym-softrobot requires Python 3.12 or newer.

pip install gym-softrobot

Quick start

import gymnasium as gym
import gym_softrobot  # Registers the environments.

env = gym.make("SoftPendulum-v0")
observation, info = env.reset(seed=42)

terminated = truncated = False
while not (terminated or truncated):
    action = env.action_space.sample()
    observation, reward, terminated, truncated, info = env.step(action)

env.close()

List the registered environments:

python -m gym_softrobot.debug.registry

See the documentation for environment IDs, API conventions, and rendering notes.

Development

uv sync --all-groups
uv run pre-commit install

Citation

@misc{gym_softrobot,
  author = {Chia-Hsien Shih and Seung Hyun Kim and Mattia Gazzola},
  title = {Soft Robotics Environment for Gymnasium},
  year = {2026},
  publisher = {GitHub},
  howpublished = {\url{https://github.com/skim0119/gym-softrobot}}
}

Author