/ README.md
README.md
1  2  3  4 [](https://opensource.org/licenses/BSD-3-Clause) 5 6 # Cartesian Controllers 7 This package provides a set of Cartesian `motion`, `force` and `compliance controllers` for the `ros2_control` framework. 8 The controllers are meant for `joint position` and `joint velocity` interfaces on the manipulators. 9 As a unique selling point, they use fast forward dynamics simulations of 10 virtually conditioned twins of the real setup as a solver for the inverse kinematics problem. 11 Integrating from joint accelerations to joint velocities and joint positions 12 gives them a delay-free, noise suppressing, and an inherently more stable contact behavior than conventional 13 *Admittance* controllers. 14 The controllers from this package are designed to trade smooth and stable behavior for accuracy where 15 appropriate, and behave physically plausible for targets outside the robots reach. 16 The package is for users who require interfaces to direct task space control 17 without the need for collision checking. 18 19 The **ROS1** version is [here](https://github.com/fzi-forschungszentrum-informatik/cartesian_controllers/tree/ros1). Also see [this talk at ROSCon'19](https://vimeo.com/378682968) and [these 20 slides](https://roscon.ros.org/2019/talks/roscon2019_cartesiancontrollers.pdf) 21 to get a brief overview. 22 23 ## Why this package? 24 Users may refer to `MoveIt` for end-effector motion planning, but 25 integrating a full planning stack is often unnecessary for simple applications. 26 Additionally, there are a lot of use cases where direct control in task space is mandatory: 27 dynamic following of target poses, such as **visual servoing**, **teleoperation**, **Cartesian teaching,** or 28 any form of **closed loop control with external sensors** for physical interactions with environments, such as **Machine Learning** applications. 29 This package provides such a controller suite for the [ros2_control](https://control.ros.org/master/index.html) framework. 30 31 ## Installation 32 Switch into the `src` folder of your current ROS2 workspace and 33 ```bash 34 git clone -b ros2 https://github.com/fzi-forschungszentrum-informatik/cartesian_controllers.git 35 rosdep install --from-paths ./ --ignore-src -y 36 cd .. 37 colcon build --packages-skip cartesian_controller_simulation cartesian_controller_tests --cmake-args -DCMAKE_BUILD_TYPE=Release 38 ``` 39 This builds the `cartesian_controllers` without its simulation environment. 40 The simulation is mostly relevant if you are just getting to know the `cartesian_controllers` and want to inspect how things work. 41 You can install it according to this [readme](cartesian_controller_simulation/README.md). 42 43 Now source your workspace again and you are ready to go. 44 45 ## Getting started 46 This assumes you have the `cartesian_controller_simulation` package installed. 47 In a sourced terminal, call 48 ```bash 49 ros2 launch cartesian_controller_simulation simulation.launch.py 50 ``` 51 52 This will start a simulated world in which you can inspect 53 and try things. Here are some quick tutorials with further details: 54 - [Solver details](resources/doc/Solver_details.md) 55 - [Cartesian motion controller](cartesian_motion_controller/README.md) 56 - [Cartesian force controller](cartesian_force_controller/README.md) 57 - [Cartesian compliance controller](cartesian_compliance_controller/README.md) 58 - [Cartesian controller handles](cartesian_controller_handles/README.md) 59 - [Teleoperation](cartesian_controller_utilities/README.md) 60 - [Example on Universal Robots](https://github.com/stefanscherzinger/cartesian_controllers_universal_robots/tree/ros2) 61 62 ## Citation and further reading 63 If you use the *cartesian_controllers* in your research projects, please 64 consider citing our initial idea of the forward dynamics-based control 65 approach ([Paper](https://ieeexplore.ieee.org/document/8206325)): 66 ```bibtex 67 @InProceedings{FDCC, 68 Title = {Forward Dynamics Compliance Control (FDCC): A new approach to cartesian compliance for robotic manipulators}, 69 Author = {S. Scherzinger and A. Roennau and R. Dillmann}, 70 Booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, 71 Year = {2017}, 72 Pages = {4568-4575}, 73 Doi = {10.1109/IROS.2017.8206325} 74 } 75 76 ``` 77 78 If you are interested in more details, have a look at 79 - *Inverse Kinematics with Forward Dynamics Solvers for Sampled Motion Tracking* ([Paper](https://arxiv.org/pdf/1908.06252.pdf)) 80 - *Virtual Forward Dynamics Models for Cartesian Robot Control* ([Paper](https://arxiv.org/pdf/2009.11888.pdf)) 81 - *Contact Skill Imitation Learning for Robot-Independent Assembly Programming* ([Paper](https://arxiv.org/pdf/1908.06272.pdf)) 82 - *Human-Inspired Compliant Controllers for Robotic Assembly* ([PhD Thesis](https://publikationen.bibliothek.kit.edu/1000139834), especially Chapter 4) 83 84 Here's an application of imitation learning for force-controlled assembly on a UR10e 85 - *Learning Human-Inspired Force Strategies for Robotic Assembly* ([Paper](https://arxiv.org/abs/2303.12440))