MLMapping(Multilayer Mapping Kit)

Introduction

MLMapping is a multilayer mapping framework designed for autonomous UAV navigation applications. In this framework, we divided the map into three layers: awareness, local, and global. The awareness map is constructed on the cylindrical coordinate, which enables fast raycasting. The local map is a probability-based volumetric map. The global map adopts dynamic memory management, allocating memory for the active mapping area, and recycling the memory from the inactive mapping area. The framework supports different kinds of map outputs for the global or local path planners.

Videos:

Fast Raycasting	Large Scale Mapping	Autonomous UAV Navigation

Publications

Chen, S., Chen, H., Chang, C. W., & Wen, C. Y. (2021). Multilayer Mapping Kit for Autonomous UAV Navigation. IEEE Access.

Compile

Clone this repository to catkin src folder say: ~/catkin_ws/src

cd ~/catkin_ws/src
git clone https://github.com/HKPolyU-UAV/MLMapping.git

Install 3rd Part library

cd catkin_ws/src/MLMapping/3rdPartLib/
./install3rdPartLib.sh

Compile

cd ~/catkin_ws/
catkin_make

Verify Using Provided Dataset

Download the Large Scale Mapping Dataset into the bag folder
decompress the rosbag

rosbag decompress corridor.bag

run

roslaunch mlmapping rviz.launch
roslaunch mlmapping mlmapping_bag_l515_t265.launch

Maintainer

Shengyang Chen(Dept.ME,PolyU): shengyang.chen@connect.polyu.hk