Code Monkey home page Code Monkey logo

ragdolltrainer's Introduction

Ragdoll Screenshot

Ragdoll Trainer Unity Project

Active ragdoll training with Unity ML-Agents (PyTorch).

Ragdoll Agent

Based on walker example

The Robot Kyle model from the Unity assets store is used for the ragdoll.

RobotKyleBlend Image

Features:

  • Default Robot Kyle rig replaced with a new rig created in blender. FBX and blend file included.

  • Heuristic function inlcuded to drive the joints by user input (for development testing only).

  • Added stabilizer to hips and spine. The stabilizer applies torque to help ragdoll balance.

  • Added "earlyTraining" bool for initial balance/walking toward target.

  • Added WallsAgent prefab for navigating around obstacles (using Ray Perception Sensor 3D).

  • Added StairsAgent prefab for navigating small and large steps.

  • Added curiosity to yaml to improve walls and stairs training.

Training Process (where bool in parenthesis refers to "earlyTraining" setting):

  • Walking: WalkerAgent (true) -> WalkerAgent (false)
  • Walls: WalkerAgent (true) -> WalkerAgent (false) -> WallsAgent (false)
  • Stairs: WalkerAgent (true) -> StairsAgent (true) -> StairsAgent (false)

ragdolltrainer's People

Contributors

kressdev avatar

Stargazers

Francois Duret avatar avatar avatar avatar BokMuchang avatar avatar Gib Dreyer avatar p3ngu1nZz avatar avatar avatar CodeSmile avatar Sina Fathi-Kazerooni avatar avatar zhangtianyu07 avatar TheBossa avatar CurryPseudo avatar Yangtze avatar Georg Hauschild avatar EX MACHINE GOD avatar avatar owlmo avatar avatar Hefan avatar Ömer Nuri Canaslan avatar Zijian Chen avatar Minseong Kim avatar avatar apexpromgt avatar avatar Dustley avatar shibi avatar Botan Sahin avatar avatar avatar avatar avatar DSJS avatar Cailean Finn avatar jay down avatar Dan Amador avatar avatar avatar 友人A avatar avatar Vittorio La Barbera avatar Ser avatar itachi avatar Mr.Liao avatar Georgii Afanasev avatar Antonio Sousa avatar avatar Matthieu Cherubini avatar Mino_Qin avatar Joowhan Song avatar avatar peter avatar Rainer Strobo avatar pragmascript avatar

Watchers

James Cloos avatar avatar

Forkers

dipayon3d jlankitus gmaf liaoer everlethe iceguan2016 michaelgrabinski ibaanb yangtzehina sidworks01 andy-olshanky deadsg cat-game-research

ragdolltrainer's Issues

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.