Need help with cupoch?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

Global Rank
#44,484
Topics of expertise
Location
JAPAN
172 Stars 26 Forks MIT License 236 Commits 7 Opened issues

Description

Robotics with GPU computing

Services available

!
?

Need anything else?

Contributors list

No Data

Robotics with GPU computing

Build Status PyPI version PyPI - Python Version Downloads xscode

Cupoch is a library that implements rapid 3D data processing for robotics using CUDA.

The goal of this library is to implement fast 3D data computation in robot systems. For example, it has applications in SLAM, collision avoidance, path planning and tracking.

Core Features

Installation

This software is tested under 64 Bit Ubuntu Linux 18.04 and CUDA 10.0/10.1/10.2. You can install cupoch using pip.

pip install cupoch

Or install cupoch from source.

git clone https://github.com/neka-nat/cupoch.git --recurse
cd cupoch
mkdir build
cd build
cmake ..; make install-pip-package -j

Installation for Jetson Nano

You can also install cupoch using pip on Jetson Nano. Please set up Jetson using jetcard and install some packages with apt.

sudo apt-get install libxinerama-dev libxcursor-dev libglu1-mesa-dev
pip3 install https://github.com/neka-nat/cupoch/releases/download/v0.1.3/cupoch-0.1.3.0-cp36-cp36m-linux_aarch64.whl

Or you can compile it from source. Update your version of cmake if necessary.

wget https://github.com/Kitware/CMake/releases/download/v3.16.3/cmake-3.16.3.tar.gz
tar zxvf cmake-3.16.3.tar.gz
cd cmake-3.16.3
./bootstrap -- -DCMAKE_USE_OPENSSL=OFF
make && sudo make install
cd ..
git clone https://github.com/neka-nat/cupoch.git --recurse
cd cupoch/
mkdir build
cd build/
export PATH=/usr/local/cuda/bin:$PATH
cmake -DBUILD_GLEW=ON -DBUILD_GLFW=ON -DBUILD_PNG=ON -DBUILD_JSONCPP=ON ..
sudo make install-pip-package

Results

The figure shows Cupoch's point cloud algorithms speedup over Open3D. The environment tested on has the following specs: * Intel Core i7-7700HQ CPU * Nvidia GTX1070 GPU * OMPNUMTHREAD=1

You can get the result by running the example script in your environment.

cd examples/python/basic
python benchmarks.py

speedup

Visual odometry with intel realsense D435

vo

Occupancy grid with intel realsense D435

og

Fast Global Registration

fgr

Point cloud from laser scan

fgr

Collision detection for 2 voxel grids

col

Path finding

pf

Visual odometry with ROS + D435

This demo works in the following environment. * ROS melodic * Python2.7

# Launch roscore and rviz in the other terminals.
cd examples/python/ros
python realsense_rgbd_odometry_node.py

vo

Visualization

| Point Cloud | Triangle Mesh | |-------------|---------------| | | |

| Voxel Grid | Occupancy Grid | Distance Transform | |------------|----------------|--------------------| | | | |

| Graph | Image | |-------|-------| | | |

References

  • CUDA repository forked from Open3D, https://github.com/theNded/Open3D
  • GPU computing in Robotics, https://github.com/JanuszBedkowski/gpucomputingin_robotics
  • Voxel collision comupation for robotics, https://github.com/fzi-forschungszentrum-informatik/gpu-voxels

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.