Skip to main content

No project description provided

Project description

neverwhere: Hyper-Realistic Visual Locomotion Benchmark
pypi

pip install neverwhere   ⬝   visit  https://neverwhere.readthedocs.org  for documentation

neverwhere is a hyper realistic visual benchmark for legged locomotion.

Installation

You can install neverwhere with pip:

pip install -U 'neverwhere[all]'
  • add setup for the dataset.

Here is an example that loads a URDF file and displays it in the browser. For a more comprehensive list of examples, please refer to the examples page.

from neverwhere import make

env = make("Cones-BCS-v1")

env.reset()
for _ in range(1000):
    random_action = env.action_space.sample()
    env.step(random_action)
    ego_view = env.render("rgb_array")

To get a quick overview of what you can do with neverwhere, check out the following:

  • take a look at the example gallery here
  • or try to take a look at this demo with a Unitree Go1 robot in front of a flight of stairs here

For a comprehensive list of visualization components, please refer to the API documentation on Components.

For a comprehensive list of data types, please refer to the API documentation on Data Types.

Contributing to Documentation and Features

Documentation is a crucial part of the neverwhere ecosystem. To contribute to documentation and usage examples, simply:

pip install -e '.[all]'
make docs

This should fire up an http server at the port 8888, and you can view the documentation at http://localhost:8888.

About Us

neverwhere is built by researchers at MIT and UCSD in fields including robotics, computer vision, and computer graphics.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

neverwhere-0.0.1rc1-py3-none-any.whl (4.0 kB view details)

Uploaded Python 3

File details

Details for the file neverwhere-0.0.1rc1-py3-none-any.whl.

File metadata

File hashes

Hashes for neverwhere-0.0.1rc1-py3-none-any.whl
Algorithm Hash digest
SHA256 d95051e009b61c695a03ab59b77a18764e7a9385c2c3d339a33adbb46732c030
MD5 2fc66e37a607a6e31b0d598baaece19d
BLAKE2b-256 45a7926816e911c81613c8b8b1472f8afdcae014c9bf6753ecb77dd4095dbece

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page