Deep Reinforcement Learning based autonomous navigation for quadcopters using PPO algorithm.

Last update: Nov 11, 2022

Overview

PPO-based Autonomous Navigation for Quadcopters

This repository contains an implementation of Proximal Policy Optimization (PPO) for autonomous navigation in a corridor environment with a quadcopter. There are blocks having circular opening for the drone to go through for each 4 meters. The expectation is that the agent navigates through these openings without colliding with blocks. This project currently runs only on Windows since Unreal environments were packaged for Windows.

🛠️ Libraries & Tools

Overview

The training environment has 9 sections with different textures and hole positions. The agent starts at these sections randomly. The starting point of the agent is also random within a specific region in the yz-plane.

Observation Space

State is in the form of a RGB image taken by the front camera of the agent.
Image shape: 50 x 50 x 3

Action Space

There are 9 discrete actions.

Environment setup to run the codes

#️⃣ 1. Clone the repository

git clone https://github.com/bilalkabas/PPO-based-Autonomous-Navigation-for-Quadcopters

#️⃣ 2. From Anaconda command prompt, create a new conda environment

I recommend you to use Anaconda or Miniconda to create a virtual environment.

conda create -n ppo_drone python==3.8

#️⃣ 3. Install required libraries

Inside the main directory of the repo

conda activate ppo_drone
pip install -r requirements.txt

#️⃣ 4. (Optional) Install Pytorch for GPU

You must have a CUDA supported NVIDIA GPU.

Details for installation

For this project, I used CUDA 11.0 and the following conda installation command to install Pytorch:

conda install pytorch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2 cudatoolkit=11.0 -c pytorch

#️⃣ 4. Edit settings.json

Content of the settings.json should be as below:

The setting.json file is located at Documents\AirSim folder.

{
    "SettingsVersion": 1.2,
    "LocalHostIp": "127.0.0.1",
    "SimMode": "Multirotor",
    "ClockSpeed": 20,
    "ViewMode": "SpringArmChase",
    "Vehicles": {
        "drone0": {
            "VehicleType": "SimpleFlight",
            "X": 0.0,
            "Y": 0.0,
            "Z": 0.0,
            "Yaw": 0.0
        }
    },
    "CameraDefaults": {
        "CaptureSettings": [
            {
                "ImageType": 0,
                "Width": 50,
                "Height": 50,
                "FOV_Degrees": 120
            }
        ]
    }
  }

How to run the training?

Make sure you followed the instructions above to setup the environment.

#️⃣ 1. Download the training environment

Go to the releases and download TrainEnv.zip. After downloading completed, extract it.

#️⃣ 2. Now, you can open up environment's executable file and start the training

So, inside the repository

python main.py

How to run the pretrained model?

Make sure you followed the instructions above to setup the environment. To speed up the training, the simulation runs at 20x speed. You may consider to change the "ClockSpeed" parameter in settings.json to 1.

#️⃣ 1. Download the test environment

Go to the releases and download TestEnv.zip. After downloading completed, extract it.

#️⃣ 2. Now, you can open up environment's executable file and run the trained model

So, inside the repository

python policy_run.py

Training results

The trained model in saved_policy folder was trained for 280k steps.

Test results

The test environment has different textures and hole positions than that of the training environment. For 100 episodes, the trained model is able to travel 17.5 m on average and passes through 4 holes on average without any collision. The agent can pass through at most 9 holes in test environment without any collision.

Author

Bilal Kabas

License

This project is licensed under the GNU Affero General Public License.

You might also like...

Tackling Obstacle Tower Challenge using PPO & A2C combined with ICM.

Obstacle Tower Challenge using Deep Reinforcement Learning Unity Obstacle Tower is a challenging realistic 3D, third person perspective and procedural

5 Feb 10, 2022

Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions.

Episodic Transformers (E.T.) Episodic Transformer for Vision-and-Language Navigation Alexander Pashevich, Cordelia Schmid, Chen Sun Episodic Transform

62 Dec 24, 2022

A clean and robust Pytorch implementation of PPO on continuous action space.

PPO-Continuous-Pytorch I found the current implementation of PPO on continuous action space is whether somewhat complicated or not stable. And this is

56 Dec 16, 2022

PPO Lagrangian in JAX

PPO Lagrangian in JAX This repository implements PPO in JAX. Implementation is tested on the safety-gym benchmark. Usage Install dependencies using th

2 Sep 14, 2022

GndNet: Fast ground plane estimation and point cloud segmentation for autonomous vehicles using deep neural networks.

GndNet: Fast Ground plane Estimation and Point Cloud Segmentation for Autonomous Vehicles. Authors: Anshul Paigwar, Ozgur Erkent, David Sierra Gonzale

114 Dec 29, 2022

Conservative Q Learning for Offline Reinforcement Reinforcement Learning in JAX

CQL-JAX This repository implements Conservative Q Learning for Offline Reinforcement Reinforcement Learning in JAX (FLAX). Implementation is built on

8 Nov 7, 2022

Reinforcement-learning - Repository of the class assignment questions for the course on reinforcement learning

DSE 314/614: Reinforcement Learning This repository containing reinforcement lea

4 Apr 15, 2022

This solves the autonomous driving issue which is supported by deep learning technology. Given a video, it splits into images and predicts the angle of turning for each frame.

Self Driving Car An autonomous car (also known as a driverless car, self-driving car, and robotic car) is a vehicle that is capable of sensing its env

4 Sep 4, 2021

A resource for learning about deep learning techniques from regression to LSTM and Reinforcement Learning using financial data and the fitness functions of algorithmic trading

A tour through tensorflow with financial data I present several models ranging in complexity from simple regression to LSTM and policy networks. The s

195 Dec 7, 2022

Comments

A warning I met during I perform "python policy_run.py"

I have followed each step as suggested by the readme. However, I encounter the problem as follow:

WARNING:tornado.general:Connect error on fd 336: WSAECONNREFUSED WARNING:tornado.general:Connect error on fd 336: WSAECONNREFUSED WARNING:tornado.general:Connect error on fd 336: WSAECONNREFUSED WARNING:tornado.general:Connect error on fd 336: WSAECONNREFUSED WARNING:tornado.general:Connect error on fd 336: WSAECONNREFUSED Traceback (most recent call last): File "policy_run.py", line 14, in env = DummyVecEnv([lambda: Monitor( File "E:\Anaconda\envs\PPO_drone\lib\site-packages\stable_baselines3\common\vec_env\dummy_vec_env.py", line 25, in init self.envs = [fn() for fn in env_fns] File "E:\Anaconda\envs\PPO_drone\lib\site-packages\stable_baselines3\common\vec_env\dummy_vec_env.py", line 25, in self.envs = [fn() for fn in env_fns] File "policy_run.py", line 15, in gym.make( File "E:\Anaconda\envs\PPO_drone\lib\site-packages\gym\envs\registration.py", line 235, in make return registry.make(id, **kwargs) File "E:\Anaconda\envs\PPO_drone\lib\site-packages\gym\envs\registration.py", line 129, in make env = spec.make(kwargs) File "E:\Anaconda\envs\PPO_drone\lib\site-packages\gym\envs\registration.py", line 90, in make env = cls(_kwargs) File "E:\Project\PPO_based_ANfQ\PPO-based-Autonomous-Navigation-for-Quadcopters\scripts\airsim_env.py", line 169, in init super(TestEnv, self).init(ip_address, image_shape, env_config) File "E:\Project\PPO_based_ANfQ\PPO-based-Autonomous-Navigation-for-Quadcopters\scripts\airsim_env.py", line 19, in init self.setup_flight() File "E:\Project\PPO_based_ANfQ\PPO-based-Autonomous-Navigation-for-Quadcopters\scripts\airsim_env.py", line 174, in setup_flight super(TestEnv, self).setup_flight() File "E:\Project\PPO_based_ANfQ\PPO-based-Autonomous-Navigation-for-Quadcopters\scripts\airsim_env.py", line 36, in setup_flight self.drone.reset() File "E:\Project\PPO_based_ANfQ\PPO-based-Autonomous-Navigation-for-Quadcopters\scripts\airsim\client.py", line 26, in reset self.client.call('reset') File "E:\Anaconda\envs\PPO_drone\lib\site-packages\msgpackrpc\session.py", line 41, in call return self.send_request(method, args).get() File "E:\Anaconda\envs\PPO_drone\lib\site-packages\msgpackrpc\future.py", line 43, in get raise self._error msgpackrpc.error.TransportError: Retry connection over the limit

I would be grateful if anyone could tell me how to fix this.

opened by XiAoSSuper 1

Releases(v1.0.0-windows)

v1.0.0-windows(Sep 22, 2021)
Release Notes

The training environment is available.

The test environment is available.

Source code(tar.gz)
Source code(zip)
TestEnv.zip(466.39 MB)
TrainEnv.zip(466.31 MB)

Owner

Bilal Kabas

BSc., Electrical & Electronics Engineering, Undergraduate Researcher: Robotics, Computer Vision, ML & DL

GitHub Repository

Plug and play transformer you can find network structure and official complete code by clicking List

Plug-and-play Module Plug and play transformer you can find network structure and official complete code by clicking List The following is to quickly

8 Mar 27, 2022

How will electric vehicles affect traffic congestion and energy consumption: an integrated modelling approach

EV-charging-impact This repository contains the code that has been used for the Queue modelling for the paper "How will electric vehicles affect traff

7 Nov 30, 2022

Official public repository of paper "Intention Adaptive Graph Neural Network for Category-Aware Session-Based Recommendation"

Intention Adaptive Graph Neural Network (IAGNN) This is the official repository of paper Intention Adaptive Graph Neural Network for Category-Aware Se

9 Nov 22, 2022

An implementation of the efficient attention module.

Efficient Attention An implementation of the efficient attention module. Description Efficient attention is an attention mechanism that substantially

194 Dec 15, 2022

Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch

Segformer - Pytorch Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch. Install $ pip install segformer-pytorch

208 Dec 25, 2022

Weighted K Nearest Neighbors (kNN) algorithm implemented on python from scratch.

kNN_From_Scratch I implemented the k nearest neighbors (kNN) classification algorithm on python. This algorithm is used to predict the classes of new

1 Dec 14, 2021

Code for the preprint "Well-classified Examples are Underestimated in Classification with Deep Neural Networks"

This is a repository for the paper of "Well-classified Examples are Underestimated in Classification with Deep Neural Networks" The implementation and

25 Dec 11, 2022

Experiments with the Robust Binary Interval Search (RBIS) algorithm, a Query-Based prediction algorithm for the Online Search problem.

OnlineSearchRBIS Online Search with Best-Price and Query-Based Predictions This is the implementation of the Robust Binary Interval Search (RBIS) algo

1 Apr 16, 2022

StarGAN v2-Tensorflow - Simple Tensorflow implementation of StarGAN v2

Official Tensorflow implementation Open ! - Clova AI StarGAN v2 — Un-official TensorFlow Implementation [Paper] [Pytorch] : Diverse Image Synthesis f

110 Jul 02, 2022

4st place solution for the PBVS 2022 Multi-modal Aerial View Object Classification Challenge - Track 1 (SAR) at PBVS2022

A Two-Stage Shake-Shake Network for Long-tailed Recognition of SAR Aerial View Objects 4st place solution for the PBVS 2022 Multi-modal Aerial View Ob

5 Nov 09, 2022

Hierarchical Few-Shot Generative Models

Hierarchical Few-Shot Generative Models Giorgio Giannone, Ole Winther This repo contains code and experiments for the paper Hierarchical Few-Shot Gene

6 Dec 12, 2022

Developed an optimized algorithm which finds the most optimal path between 2 points in a 3D Maze using various AI search techniques like BFS, DFS, UCS, Greedy BFS and A*

Developed an optimized algorithm which finds the most optimal path between 2 points in a 3D Maze using various AI search techniques like BFS, DFS, UCS, Greedy BFS and A*. The algorithm was extremely

1 Mar 28, 2022

Deep Reinforcement Learning based autonomous navigation for quadcopters using PPO algorithm.

Related tags

Overview

PPO-based Autonomous Navigation for Quadcopters

🛠️ Libraries & Tools

Overview

Observation Space

Action Space

Environment setup to run the codes

How to run the training?

How to run the pretrained model?

Training results

Test results

Author

License

You might also like...

Tackling Obstacle Tower Challenge using PPO & A2C combined with ICM.

Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions.

A clean and robust Pytorch implementation of PPO on continuous action space.

PPO Lagrangian in JAX

GndNet: Fast ground plane estimation and point cloud segmentation for autonomous vehicles using deep neural networks.

Conservative Q Learning for Offline Reinforcement Reinforcement Learning in JAX

Reinforcement-learning - Repository of the class assignment questions for the course on reinforcement learning

This solves the autonomous driving issue which is supported by deep learning technology. Given a video, it splits into images and predicts the angle of turning for each frame.

A resource for learning about deep learning techniques from regression to LSTM and Reinforcement Learning using financial data and the fitness functions of algorithmic trading

Comments

A warning I met during I perform "python policy_run.py"

Releases(v1.0.0-windows)

v1.0.0-windows(Sep 22, 2021)

Release Notes

Owner

Bilal Kabas

Plug and play transformer you can find network structure and official complete code by clicking List

How will electric vehicles affect traffic congestion and energy consumption: an integrated modelling approach

Official public repository of paper "Intention Adaptive Graph Neural Network for Category-Aware Session-Based Recommendation"

An implementation of the efficient attention module.

Implementation of Segformer, Attention + MLP neural network for segmentation, in Pytorch

Weighted K Nearest Neighbors (kNN) algorithm implemented on python from scratch.

Code for the preprint "Well-classified Examples are Underestimated in Classification with Deep Neural Networks"

Experiments with the Robust Binary Interval Search (RBIS) algorithm, a Query-Based prediction algorithm for the Online Search problem.

StarGAN v2-Tensorflow - Simple Tensorflow implementation of StarGAN v2

4st place solution for the PBVS 2022 Multi-modal Aerial View Object Classification Challenge - Track 1 (SAR) at PBVS2022

Hierarchical Few-Shot Generative Models

Developed an optimized algorithm which finds the most optimal path between 2 points in a 3D Maze using various AI search techniques like BFS, DFS, UCS, Greedy BFS and A*

Large-scale language modeling tutorials with PyTorch

Code for the paper "Implicit Representations of Meaning in Neural Language Models"

Self-Supervised Image Denoising via Iterative Data Refinement

This program will stylize your photos with fast neural style transfer.

Learning to Reconstruct 3D Manhattan Wireframes from a Single Image

pix2pix in tensorflow.js

Iran Open Source Hackathon

Official implementation of "Learning Not to Reconstruct" (BMVC 2021)