Multi-robot collaborative exploration and mapping through Voronoi partition and DRL in unknown environment

Last update: Nov 22, 2022

Overview

Voronoi Multi_Robot Collaborate Exploration

Introduction

In the unknown environment, the cooperative exploration of multiple robots is completed by Voronoi partition and deep reinforcement learning. The decision-making level assigns different target positions to each mobile robot through Voronoi partition and point selection formula to minimize repeated exploration; The path planning layer uses the method based on deep reinforcement learning to make each mobile robot reach the corresponding target position without collision.

Enviroment

parameter	description
system	Ubuntu18.04 ; ROS(Melodic); Phython 2.7
simulator	Gazebo
display	Rviz
simulation car	Turtlebot3(Waffle)
senor	LiDAR
laser range	0.1 - 3.5 m
angle range	-90 - 90
laser numer	24

Run

dependency package

sudo apt-get install ros-melodic-joy ros-melodic-teleop-twist-joy ros-melodic-teleop-twist-keyboard ros-melodic-laser-proc ros-melodic-rgbd-launch ros-melodic-depthimage-to-laserscan ros-melodic-rosserial-arduino ros-melodic-rosserial-python ros-melodic-rosserial-server ros-melodic-rosserial-client ros-melodic-rosserial-msgs ros-melodic-amcl ros-melodic-map-server ros-melodic-move-base ros-melodic-urdf ros-melodic-xacro ros-melodic-compressed-image-transport ros-melodic-rqt-image-view ros-melodic-gmapping ros-melodic-navigation ros-melodic-interactive-markers ros-melodic-multirobot-map-merge

Add

pyyaml、rospkg、pytorch、torchvision、tensorflow 、tensorboard、mpi4py、joblib、gym、pathlib、wandb、Image、setproctitle、imageio

compile & run

> catkin_make 
> source devel/setup.bash
> roslaunch multi_turtlebot3_expore three_turtlebot3_gmapping.launch
> python ddpg_test.py

test

Move & mapping

Comparison of construction effects

Run in other environments

Avoid obstacle

Reference

hanlinniu/turtlebot3_ddpg_collision_avoidance：https://github.com/hanlinniu/turtlebot3_ddpg_collision_avoidance

Multi-robot collaborative exploration and mapping through Voronoi partition and DRL in unknown environment

Related tags

Overview

Voronoi Multi_Robot Collaborate Exploration

Introduction

Enviroment

Run

dependency package

compile & run

test

Move & mapping

Run in other environments

Reference

Owner

PeaceWord

Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch

Pytorch implementation of ProjectedGAN

Pixel Consensus Voting for Panoptic Segmentation (CVPR 2020)

Code for the paper "TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks"

Tensorflow implementation of our method: "Triangle Graph Interest Network for Click-through Rate Prediction".

The official codes of our CVPR2022 paper: A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift

Keras implementation of the GNM model in paper ’Graph-Based Semi-Supervised Learning with Nonignorable Nonresponses‘

Evaluating different engineering tricks that make RL work

Annotated, understandable, and visually interpretable PyTorch implementations of: VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN

Code for the paper: On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Pipeline code for Sequential-GAM(Genome Architecture Mapping).

Mengzi Pretrained Models

Learn about Spice.ai with in-depth samples

This is a pytorch implementation of the NeurIPS paper GAN Memory with No Forgetting.

Doosan robotic arm, simulation, control, visualization in Gazebo and ROS2 for Reinforcement Learning.

Face Transformer for Recognition

Multi-objective constrained optimization for energy applications via tree ensembles

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

Multi-robot collaborative exploration and mapping through Voronoi partition and DRL in unknown environment

Related tags

Overview

Voronoi Multi_Robot Collaborate Exploration

Introduction

Enviroment

Run

dependency package

compile & run

test

Move & mapping

Run in other environments

Reference

Owner

PeaceWord

Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch

Pytorch implementation of ProjectedGAN

Pixel Consensus Voting for Panoptic Segmentation (CVPR 2020)

Code for the paper "TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks"

Tensorflow implementation of our method: "Triangle Graph Interest Network for Click-through Rate Prediction".

The official codes of our CVPR2022 paper: A Differentiable Two-stage Alignment Scheme for Burst Image Reconstruction with Large Shift

Keras implementation of the GNM model in paper ’Graph-Based Semi-Supervised Learning with Nonignorable Nonresponses‘

Evaluating different engineering tricks that make RL work

Annotated, understandable, and visually interpretable PyTorch implementations of: VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN

Code for the paper: On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Pipeline code for Sequential-GAM(Genome Architecture Mapping).

Mengzi Pretrained Models

Learn about Spice.ai with in-depth samples

This is a pytorch implementation of the NeurIPS paper GAN Memory with No Forgetting.

Doosan robotic arm, simulation, control, visualization in Gazebo and ROS2 for Reinforcement Learning.

Face Transformer for Recognition

Multi-objective constrained optimization for energy applications via tree ensembles

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.