Table of Contents
This project aims to address the problem of mapping an underwater structure by a team of co-robots. Our approach includes underwater state estimation, 3D motion planning underwater and limited bandwidth communications We use stereo camera and sonar as the primary sensors.
We have tested the library in Ubuntu 16.04 and 18.04, but it should be easy to compile in other platforms. This is an example of how to list things you need to use the software and how to install them.
We use the new thread and chrono functionalities of C++11.
sudo apt install cmake
We use OpenCV to manipulate images and features. Download and install instructions can be found at: http://opencv.org. Required at leat 2.4.3. Tested with OpenCV 2.4.11 and OpenCV 3.2.
We use pybind11 to creat Python bindings of existing c++ code. Download and install instructions can be found at:: https://github.com/pybind/pybind11.
sudo apt install libeigen3-dev
We highly recommend installing a miniconda or Anaconda environment (note: python>=3.6 is required). Once you have Anaconda installed, here are the instructions.
- Clone the repository:
git clone https://github.com/wwtx9/AVP_Binding.git AVP_Binding
- Build and compire AVP library
cd AVP_Binding
mkdir build
cmake ..
make
- Setup python virtual environment with conda
# We require python>=3.6 and cmake>=3.10
conda create -n AVP python=3.6 cmake=3.14.0
conda activate AVP
- Install the AVP Library for your python project to import
pip install .
#After that, now your can import AVP_Binding as m in your python script
-
Download the dataset (grayscale images) from http://www.cvlibs.net/datasets/kitti/eval_odometry.php
-
Run test script
# Assuming we're still within AVP conda environment
python test.py