AnyGrasp

code

paper

1.安装 MinkowskiEngine

安装MinkowskiEngine时可能会有些问题，因为要求的环境比较旧，有些库的版本较低，参考/issues/594，/issues/596，/issues/543

首先按commit进行修改

export TORCH_CUDA_ARCH_LIST="8.9"
export CUDA_HOME=/usr/local/cuda-12.1
export MAX_JOBS=2

安装依赖：

conda install openblas-devel -c anaconda

我的conda环境：

Package                       Version
----------------------------- --------------
actionlib                     1.14.0
angles                        1.9.13
base_local_planner            1.17.3
bondpy                        1.8.6
camera-calibration            1.17.0
camera-calibration-parsers    1.12.0
catkin                        0.8.10
controller-manager            0.20.0
controller-manager-msgs       0.20.0
cv-bridge                     1.16.2
diagnostic-analysis           1.11.0
diagnostic-common-diagnostics 1.11.0
diagnostic-updater            1.11.0
dynamic-reconfigure           1.7.3
filelock                      3.16.1
fsspec                        2024.12.0
gazebo_plugins                2.9.2
gazebo_ros                    2.9.2
gencpp                        0.7.0
geneus                        3.0.0
genlisp                       0.4.18
genmsg                        0.6.0
gennodejs                     2.0.2
genpy                         0.6.15
image-geometry                1.16.2
interactive-markers           1.12.0
Jinja2                        3.1.5
joint-state-publisher         1.15.1
joint-state-publisher-gui     1.15.1
laser_geometry                1.6.7
MarkupSafe                    3.0.2
message-filters               1.17.0
MinkowskiEngine               0.5.4
moveit-commander              1.1.16
moveit-core                   1.1.16
moveit-python                 0.4.5
moveit-ros-planning-interface 1.1.16
moveit-ros-visualization      1.1.16
moveit-task-constructor-core  0.1.3
mpmath                        1.3.0
networkx                      3.4.2
numpy                         2.2.1
nvidia-cublas-cu12            12.1.3.1
nvidia-cuda-cupti-cu12        12.1.105
nvidia-cuda-nvrtc-cu12        12.1.105
nvidia-cuda-runtime-cu12      12.1.105
nvidia-cudnn-cu12             8.9.2.26
nvidia-cufft-cu12             11.0.2.54
nvidia-curand-cu12            10.3.2.106
nvidia-cusolver-cu12          11.4.5.107
nvidia-cusparse-cu12          12.1.0.106
nvidia-nccl-cu12              2.20.5
nvidia-nvjitlink-cu12         12.6.85
nvidia-nvtx-cu12              12.1.105
pillow                        11.1.0
pip                           24.2
python-qt-binding             0.4.4
qt-dotgraph                   0.4.2
qt-gui                        0.4.2
qt-gui-cpp                    0.4.2
qt-gui-py-common              0.4.2
resource_retriever            1.12.7
rosbag                        1.17.0
rosboost-cfg                  1.15.8
rosclean                      1.15.8
roscreate                     1.15.8
rosgraph                      1.17.0
roslaunch                     1.17.0
roslib                        1.15.8
roslint                       0.12.0
roslz4                        1.17.0
rosmake                       1.15.8
rosmaster                     1.17.0
rosmsg                        1.17.0
rosnode                       1.17.0
rosparam                      1.17.0
rospy                         1.17.0
rosservice                    1.17.0
rostest                       1.17.0
rostopic                      1.17.0
rosunit                       1.15.8
roswtf                        1.17.0
rqt_action                    0.4.9
rqt_bag                       0.5.1
rqt_bag_plugins               0.5.1
rqt-console                   0.4.12
rqt_dep                       0.4.12
rqt_graph                     0.4.14
rqt_gui                       0.5.3
rqt_gui_py                    0.5.3
rqt-image-view                0.4.17
rqt_launch                    0.4.9
rqt-logger-level              0.4.12
rqt-moveit                    0.5.11
rqt_msg                       0.4.10
rqt_nav_view                  0.5.7
rqt_plot                      0.4.13
rqt_pose_view                 0.5.11
rqt_publisher                 0.4.10
rqt_py_common                 0.5.3
rqt_py_console                0.4.10
rqt-reconfigure               0.5.5
rqt-robot-dashboard           0.5.8
rqt-robot-monitor             0.5.15
rqt_robot_steering            0.5.12
rqt-runtime-monitor           0.5.10
rqt-rviz                      0.7.0
rqt_service_caller            0.4.10
rqt_shell                     0.4.11
rqt_srv                       0.4.9
rqt-tf-tree                   0.6.4
rqt_top                       0.4.10
rqt_topic                     0.4.13
rqt_web                       0.4.10
rviz                          1.14.25
sensor-msgs                   1.13.1
setuptools                    59.6.0
smach                         2.5.2
smach-ros                     2.5.2
smclib                        1.8.6
srdfdom                       0.6.4
sympy                         1.13.3
tf                            1.13.2
tf-conversions                1.13.2
tf2-geometry-msgs             0.7.7
tf2-kdl                       0.7.7
tf2-py                        0.7.7
tf2-ros                       0.7.7
topic-tools                   1.17.0
torch                         2.3.1+cu121
torchaudio                    2.3.1+rocm6.0
torchvision                   0.18.1+rocm6.0
trac_ik_python                1.6.6
triton                        2.3.1
typing_extensions             4.12.2
urdfdom-py                    0.4.6
wheel                         0.44.0
xacro                         1.14.18

安装 MinkowskiEngine:

python setup.py install --blas_include_dirs=${CONDA_PREFIX}/include --blas=openblas

安装如果出现有关numpy.distutils的报错包装低版本的库就可以了(setuptools)。

安装成功：

2.安装其他依赖

git clone https://github.com/graspnet/anygrasp_sdk.git
pip install -r requirements.txt

其中和grasp最相关的是 graspnetAPI，我在install的过程安装不成功graspnetAPI，于是我便单独源码安装了。

3.安装 graspnetAPI

pip install graspnetAPI

or (the way for me)

git clone https://github.com/graspnet/graspnetAPI.git
cd graspnetAPI
pip install .

这一步也会安装挺多依赖，见上图中的install_requires。

如果在安装graspnetAPI时遇到某些库安装不成功可以先单独安装该库，邻近版本有时候也是可以的，可以多试试（e.g. 我安装numpy1.20.3没有成功，但是我安装numpy1.21.1是成功的，后面也是可以成功应用anygrasp的）。

4.安装 pointnet2

cd /anygrasp_sdk/pointnet2/
python setup.py install

5. AnyGrasp Detection Demo

grasp_detection

获取到的个人license要放到此目录下并重命名为“license”

6. AnyGrasp Tracking Demo

grasp_tracking

获取到的个人license要放到此目录下并重命名为“license”