Git Product home page Git Product logo

cybergpt's Introduction

CyberGPT

This repo is based on ChatGPT and AutoGPT to achieve General Robotic System for Field Robotics. Given that the great purge of LLM and commen sense ability for general usage, we aim to bridge the link between ChatGPT and field robotics application.

pitts_large-scale

In this Repo, we will assume the robots cover the basic functional ability in long-term localization and mapping, 3D perception and exploration modules which we developed under the MetaSLAM organization:

  1. AutoMerge, which is a crowdsourced mapping package for multi-agent mapping and localization.
  2. iSimLoc, which is a UAV localization system with Google Satelite Images without GPS.
  3. BioSLAM, which is a lifelong learning system for incremental perception.
  4. MUI-TARE, which is a multi-agent exploration approach.

Our vision is to enhance the Field of robotics ability and help robots to invole into our daily life for more challenging tasks. For the more detail, please refer to our website:

๐Ÿš€ Features

  • Analysis human order and generate sub-goals automatically
  • Analysis environmental feedbacks based on phycial-interaction
  • File storage and summarization with GPT-3.5
  • Long-Term and Short-Term memory management
  • Logistic mapping from function modules with physical behaviurs

๐Ÿ“‹ Requirements

Optional:

  • ElevenLabs Key (If you want the AI to speak)

โš ๏ธ Limitations

This experiment aims to showcase how we can use ChatGPT to enhance Robotics applications, but there are some limitations:

  1. Not a ready work to test under different conditions;
  2. Some functions are missing, such as manipulations, etc;
  3. The current work is heavily relying on AutoGPT, but in the near future, we will reduce the costing for training a small model.

Run tests

To run tests, run the following command:

python -m unittest discover tests

To run tests and see coverage, run the following command:

coverage run -m unittest discover tests

Run linter

This project uses flake8 for linting. To run the linter, run the following command:

flake8 scripts/ tests/

# Or, if you want to run flake8 with the same configuration as the CI:
flake8 scripts/ tests/ --select E303,W293,W291,W292,E305

cybergpt's People

Contributors

prof-pengyin avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.