The aim of the Wellcome / EPSRC CME - Pillar 3 on “Trustworthy Artificial Intelligence for Sensory-rich Surgical Robotics” is to lay the foundations of a sustainable programme leading to surgical robot autonomy in collaborative human-robot teams. The team will advance the field across four directions feeding in this ambition: Trustworthy AI, computational ultrasonography, knowledge extraction from connected medical devices, and sensory-rich human-machine interfaces.
This pages serves as a curated list of open-source software developped, maintained, or simply useful for members of the pillar.
- lbr_fri_ros2_stack: ROS 2 packages for the KUKA LBR, including communication to the real robot via the Fast Robot Interface (FRI) and Gazebo simulation support.
- optas: An optimization-based task specification library for task and motion planning (TAMP), trajectory optimization, forward/inverse kinematics, and model predictive control in Python. Also, see paper.
- FRI-Client-SDK_Python: Library for the FRI library that controls the KUKA LBR robot arm in Python.
- FRI-Client-SDK_Cpp: C++ FRI library including CMake files for controlling the KUKA LBR robot arm.
- geomagic_touch_x_ros_driver: ROS package for control of 3D Systems Geomagic Touch X.
- eff_wrench: ROS 2 node for estimating end-effector wrench.
- spectrumdevice: Python library for communicating with digitisers manufactured by Spectrum Instrumentation.
- pymagewell: a Python library for interfacing with Magewell ProCapture frame grabbers.
- torch-content-area: A PyTorch tool kit for estimating the circular content area in endoscopic footage.
- semi-synthetic: Image compositing for segmentation of surgical tools without manual annotations.
- list-of-surgical-tool-datasets: List of surgical tool datasets organised by task.
- videosum: Simple video summarisation Python package.
- latentplot: Python package to plot the latent space of a set of images with different methods.
- oflibpytorch: Python package to manipulate, operate on, and combine optical flow fields, differentiable for the use in deep learning networks
- synapi: Python package to deal with Synapse datasets in a more convenient way.
- PyTorchFromCPPTest: A simple example repository illustrating how to call PyTorch (python) from c++.
- torchmaxflow: PyTorch-based implementation of Max-flow/Min-cut (graphcut) for 2D/3D data.
- grabcut: GrabCut implementation that works seamlessly for C++ and Python.
- MONAI: AI Toolkit for Healthcare Imaging.