Coder Social home page Coder Social logo

akshastry / rl-drone-dynamic-obstacles Goto Github PK

View Code? Open in Web Editor NEW

This project forked from saimouli/rl-drone-dynamic-obstacles

0.0 1.0 0.0 31.79 MB

Research project involving RL for the dynamic obstacle avoidance using AR drone 2.0 platform

License: MIT License

CMake 1.87% C++ 25.04% Python 36.06% Makefile 0.43% C 2.23% Dockerfile 0.01% HTML 17.36% Jupyter Notebook 17.00%

rl-drone-dynamic-obstacles's Introduction

RL-Drone-Dynamic-Obstacles

Research project involving RL for the dynamic obstacle avoidance using AR drone 2.0 platform

Build instructions

  1. Clone the package into your catkin workspace

  2. We need to use python3 for reinforcement learning packages, but ROS is currently supported for Python2. We need build TF packages additionally to successfully run the code. You might get following errors if you do not build TF packages for python 3. 'ImportError: dynamic module does not define module export function (PyInit__tf2)'

  3. Now once you have cloned the package build it using following command. catkin_make --cmake-args \ -DCMAKE_BUILD_TYPE=Release \ -DPYTHON_EXECUTABLE=/usr/bin/python3 \ -DPYTHON_INCLUDE_DIR=/usr/include/python3.6m \ -DPYTHON_LIBRARY=/usr/lib/x86_64-linux-gnu/libpython3.6m.so You might get following error message while compiling the package. 'fatal error: Python.h: No such file or directory' This is because you might not be using python3.6, so you have to find the version of the python and then replace the python version in the catkin_make command stated above. For me it is python3.5.

Training iterations

1. 10X10 static scene

World file name - /RL-Drone-Dynamic-Obstacles/tum_simulator/cvg_sim_gazebo/worlds/10X10_static.world Launch file - /RL-Drone-Dynamic-Obstacles/tum_simulator/cvg_sim_gazebo/launch/static_without_walls.launch

2. static_without_walls scene

World file name - /RL-Drone-Dynamic-Obstacles/tum_simulator/cvg_sim_gazebo/worlds/static_without_walls.world Launch file - /RL-Drone-Dynamic-Obstacles/tum_simulator/cvg_sim_gazebo/launch/static_without_walls.launch

Required packages

  1. pip install tensorflow-gpu==1.14
  2. pip install -U rospkg
  3. pip install joblib
  4. pip install gym

rl-drone-dynamic-obstacles's People

Contributors

utsavpatel22 avatar saimouli avatar

Watchers

James Cloos 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.