Installation on Ubuntu

Installing voxblox++ on Ubuntu 16.04 or 18.04

Prerequisites

Install ROS following the instructions at the ROS installation page. The full install (ros-kinetic-desktop-full, ros-melodic-desktop-full) are recommended.

Make sure to source your ROS setup.bash script by following the instructions on the ROS installation page.

Requirements

• gcc>=5.2 (required for C++14 support)
• CMake 3.8 or later
• Python 2.7 (required for ROS support)
• protobuf>=3.0 (required for tensorflow)
• Numpy, skimage, scipy, Pillow, cython, h5py
• Keras 2.0.8+
• TensorFlow 1.3+

Install dependencies

sudo apt update
sudo apt install python-dev python-pip python-wstool

sudo pip2 install 'protobuf>=3.0.0a3'
sudo pip2 install tensorflow-gpu # If GPU is available, else tensorflow 

Install voxblox++

In your terminal, define the installed ROS version and name of the catkin workspace to use:

export ROS_VERSION=kinetic # (Ubuntu 16.04: kinetic, Ubuntu 18.04: melodic)
export CATKIN_WS=~/catkin_ws

If you don't have a catkin workspace yet, create a new one:

mkdir -p $CATKIN_WS/src && cd $CATKIN_WS
catkin init
catkin config --extend /opt/ros/$ROS_VERSION --merge-devel 
catkin config --cmake-args -DCMAKE_CXX_STANDARD=14 -DCMAKE_BUILD_TYPE=Release
wstool init src

Clone the voxblox_plusplus repository over HTTPS (no Github account required):

cd $CATKIN_WS/src
git clone --recurse-submodules https://github.com/ethz-asl/voxblox-plusplus.git

Alternatively, clone over SSH (Github account required):

cd $CATKIN_WS/src
git clone --recurse-submodules git@github.com:ethz-asl/voxblox-plusplus.git

Automatically fetch dependencies:

wstool merge -t . voxblox-plusplus/dependencies.rosinstall
wstool update

Build and source the voxblox++ packages:

catkin build mask_rcnn_ros depth_segmentation gsm_node
source ../devel/setup.bash # (bash shell: ../devel/setup.bash,  zsh shell: ../devel/setup.zsh)