kindergarden 0.0.10

A robotics benchmark for physical reasoning.

KinDER

A physical reasoning benchmark for robot learning and planning.

Website

See https://prpl-group.com/kinder-site/ for documentation and tutorials.

Requirements

1. Python >=3.10, <3.13
2. Tested on MacOS 13-15 and Ubuntu 22.04 (but we aim to support most platforms)

Installation

From PyPI

pip install kindergarden                # all environment dependencies
pip install kindergarden[dynamic2d]     # only dynamic2d environments
pip install kindergarden[kinematic2d]   # only kinematic2d environments
pip install kindergarden[kinematic3d]   # only kinematic3d environments
pip install kindergarden[dynamic3d]     # only dynamic3d environments

You can also combine extras: pip install kindergarden[kinematic2d,kinematic3d]

From Source

We strongly recommend uv, but other standard setups work too.

git clone https://github.com/Princeton-Robot-Planning-and-Learning/kindergarden.git
cd kindergarden
uv pip install -e ".[develop]"   # all dependencies + dev tools

Or install only what you need:

uv pip install -e ".[dynamic2d]" # only dynamic2d environments

To check the installation, run ./run_ci_checks.sh. It should complete with all green successes.

Usage Example

Basic Usage (Gym API)

import kinder
kinder.register_all_environments()
env = kinder.make("kinder/Obstruction2D-o3-v0")  # 3 obstructions
obs, info = env.reset()  # procedural generation
action = env.action_space.sample()
next_obs, reward, terminated, truncated, info = env.step(action)
img = env.render()  

Object-Centric States

All environments in KinDER use object-centric states. For example:

from kinder.envs.kinematic2d.obstruction2d import ObjectCentricObstruction2DEnv
env = ObjectCentricObstruction2DEnv(num_obstructions=3)
obs, _ = env.reset(seed=123)
print(obs.pretty_str())

Here, obs is an ObjectCentricState, and the printout is:

############################################################### STATE ###############################################################
type: crv_robot           x         y    theta    base_radius    arm_joint    arm_length    vacuum    gripper_height    gripper_width
-----------------  --------  --------  -------  -------------  -----------  ------------  --------  ----------------  ---------------
robot              0.885039  0.803795  -1.5708            0.1          0.1           0.2         0              0.07             0.01

type: rectangle           x         y    theta    static    color_r    color_g    color_b    z_order      width     height
-----------------  --------  --------  -------  --------  ---------  ---------  ---------  ---------  ---------  ---------
obstruction0       0.422462  0.100001        0         0       0.75        0.1        0.1        100  0.132224   0.0766399
obstruction1       0.804663  0.100001        0         0       0.75        0.1        0.1        100  0.0805652  0.0955062
obstruction2       0.559246  0.100001        0         0       0.75        0.1        0.1        100  0.12608    0.180172

type: target_block          x         y    theta    static    color_r    color_g    color_b    z_order     width    height
--------------------  -------  --------  -------  --------  ---------  ---------  ---------  ---------  --------  --------
target_block          1.20082  0.100001        0         0   0.501961          0   0.501961        100  0.138302  0.155183

type: target_surface           x    y    theta    static    color_r    color_g    color_b    z_order     width    height
----------------------  --------  ---  -------  --------  ---------  ---------  ---------  ---------  --------  --------
target_surface          0.499675    0        0         1   0.501961          0   0.501961        101  0.180286       0.1
#####################################################################################################################################

For compatibility with baselines, the observations provided by the main environments are vectors. It is easy to convert between vectors and object-centric states. For example:

import kinder
kinder.register_all_environments()
env = kinder.make("kinder/Obstruction2D-o3-v0")
vec_obs, _ = env.reset(seed=123)
object_centric_obs = env.observation_space.devectorize(vec_obs)
recovered_vec_obs = env.observation_space.vectorize(object_centric_obs)

Noisy Observation and Action Wrappers

KinDER provides Gymnasium-compatible wrappers for adding stochasticity to observations and actions:

import kinder
kinder.register_all_environments()
env = kinder.make("kinder/Obstruction2D-o3-v0")
env = kinder.NoisyObservation(env, noise_std=0.05)  # Gaussian noise on observations
env = kinder.NoisyAction(env, noise_std=0.01)        # Gaussian noise on actions (clipped to bounds)
obs, info = env.reset(seed=42)

noise_std can be a scalar (uniform across dimensions) or a per-dimension array. NoisyAction automatically clips noisy actions to the action space bounds.

Quick Environment Reference

Environment	Category	Example Environment ID
ClutteredRetrieval2D	Kinematic2D	kinder/ClutteredRetrieval2D-o10-v0
Motion2D	Kinematic2D	kinder/Motion2D-p5-v0
Obstruction2D	Kinematic2D	kinder/Obstruction2D-o4-v0
PushPullHook2D	Kinematic2D	kinder/PushPullHook2D-v0
ClutteredStorage2D	Kinematic2D	kinder/ClutteredStorage2D-b15-v0
StickButton2D	Kinematic2D	kinder/StickButton2D-b10-v0
DynObstruction2D	Dynamic2D	kinder/DynObstruction2D-o3-v0
DynPushPullHook2D	Dynamic2D	kinder/DynPushPullHook2D-o5-v0
DynPushT2D	Dynamic2D	kinder/DynPushT2D-t1-v0
DynScoopPour2D	Dynamic2D	kinder/DynScoopPour2D-o50-v0
Obstruction3D	Kinematic3D	kinder/Obstruction3D-o4-v0
Packing3D	Kinematic3D	kinder/Packing3D-p3-v0
Table3D	Kinematic3D	kinder/Table3D-o3-v0
Transport3D	Kinematic3D	kinder/Transport3D-o2-v0
BaseMotion3D	Kinematic3D	kinder/BaseMotion3D-v0
Shelf3D	Kinematic3D	kinder/Shelf3D-o10-v0
ConstrainedCupboard3D	Dynamic3D	kinder/ConstrainedCupboard3D-o6-v0
SortClutteredBlocks3D	Dynamic3D	kinder/SortClutteredBlocks3D-o20-sort_the_cluttered_blocks_into_bowls-v0
Rearrange3D	Dynamic3D	kinder/Rearrange3D-o2-put_the_boxed_drink_and_the_can_next_to_the_bowl-v0
SweepSimple3D	Dynamic3D	kinder/SweepSimple3D-o50-sweep_the_blocks_to_the_left_side_of_the_kitchen_island-v0
Dynamo3D	Dynamic3D	kinder/Dynamo3D-o1-v0
Tossing3D	Dynamic3D	kinder/Tossing3D-o1-v0
ScoopPour3D	Dynamic3D	kinder/ScoopPour3D-o10-v0
BalanceBeam3D	Dynamic3D	kinder/BalanceBeam3D-o3-v0
SweepIntoDrawer3D	Dynamic3D	kinder/SweepIntoDrawer3D-o5-v0

Contributing

General Guidelines

• All checks must pass before code is merged (see ./run_ci_checks.sh)
• All code goes through the pull request review process

Adding New Environments

Some new environment requests are in Issues. To add a new environment, please see the examples in src/kinder/env. Also consider:

• Environments are registered in src/kinder/__init__.py
• Each environment should have at least one demonstration (see scripts/collect_demos.py)
• After collecting a demonstration, create a video with scripts/generate_demo_video.py, which will be used in the autogenerated documentation