Skip to content

uwgraphics/relaxed_ik_core

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RangedIK Core

Implementation of our ICRA'23 paper: RangedIK: An Optimization-Based Robot Motion Generation Method for Ranged-Goal Tasks

[Pre-print] [Supplementary Video] [Presentation Video] [Poster]

Introduction

RangedIK is a real-time motion synthesis method that exploits range flexibility to satisfy multiple kinematic requirements. RangedIK is particularly suitable for applications that allow some tolerance, such as wielding where the tool is allowed to rotate along its principle axis. For more information, please refer to our paper.

The RelaxedIK Family

RangedIK extends RelaxedIK by leveraging the flexibility afforded by tolerances. Also, RangedIK is recently maintained and works with more recent rust versions.

CollisionIK extends RelaxedIK by avoiding collisions with static or dynamic obstacles in the environment.

We provide a series of wrappers for our tools to be used in various platform or software.

ROS1 ROS2 WebAssembly Coppeliasim Mujoco
RangedIK link link link x x
CollisionIK link x x x x
RelaxedIK link x x link link

Getting Started

  1. Install Rust
  2. Compile:
    cargo build
    The compiled library is at /target/debug/librelaxed_ik_lib.so
  3. Run a small demo:
    cargo run --bin relaxed_ik_bin

Use your own robot

  1. Place your robot's URDF under configs/urdfs/
  2. Make a setting file. Examples are under configs/example_settings

Python wrapper

wrappers/python_wrapper.py provides a python wrapper, which is used by both the ROS 1 wrapper and ROS 2 wrapper. relaxed_ik_ros1/scripts/relaxed_ik_rust.py provides an example of using the python wrapper.

JavaScript (WebAssembly) wrapper

Online demo

  1. Install Rust
  2. cargo install wasm-pack
    • if there is a linker 'cc' not found error, run sudo apt install gcc
    • if it complains about openssl, on Ubuntu install it by sudo apt-get install libssl-dev pkg-config openssl. For windows, download and install perl.
  3. Compile to WebAssembly
    wasm-pack build --target web
    
  4. relaxed-ik-web-demo provides an example of running relaxed-ik in browser.

Supplementary Video

YouTube video link

Citation

If you use RangedIK, please cite our ICRA paper: RangedIK: An Optimization-based Robot Motion Generation Method for Ranged-Goal Tasks

@article{wang2023rangedik,
  title={RangedIK: An Optimization-based Robot Motion Generation Method for Ranged-Goal Tasks},
  author={Wang, Yeping and Praveena, Pragathi and Rakita, Daniel and Gleicher, Michael},
  booktitle={2023 IEEE International Conference on Robotics and Automation (ICRA)},
  pages={9700-9706},
  year={2023}
}

If you use RelaxedIK, please cite our RSS paper: RelaxedIK: Real-time Synthesis of Accurate and Feasible Robot Arm Motion

@INPROCEEDINGS{Rakita-RSS-18, 
    AUTHOR    = {Daniel Rakita AND Bilge Mutlu AND Michael Gleicher}, 
    TITLE     = {{RelaxedIK: Real-time Synthesis of Accurate and Feasible Robot Arm Motion}}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2018}, 
    ADDRESS   = {Pittsburgh, Pennsylvania}, 
    MONTH     = {June}, 
    DOI       = {10.15607/RSS.2018.XIV.043} 
}

If you use CollisionIK (RelaxedIK with environment collision avoidance), please cite our ICRA paper: CollisionIK: A Per-Instant Pose Optimization Method for Generating Robot Motions with Environment Collision Avoidance

@inproceedings{rakita2021collisionik,
  title={Collisionik: A per-instant pose optimization method for generating robot motions with environment collision avoidance},
  author={Rakita, Daniel and Shi, Haochen and Mutlu, Bilge and Gleicher, Michael},
  booktitle={2021 IEEE International Conference on Robotics and Automation (ICRA)},
  pages={9995--10001},
  year={2021},
  organization={IEEE}
}

If you use our solver for a robot teleoperation interface, also consider citing our prior work that shows the effectiveness of RelaxedIK in this setting: A Motion Retargeting Method for Effective Mimicry-based Teleoperation of Robot Arms

@inproceedings{rakita2017motion,
  title={A motion retargeting method for effective mimicry-based teleoperation of robot arms},
  author={Rakita, Daniel and Mutlu, Bilge and Gleicher, Michael},
  booktitle={Proceedings of the 2017 ACM/IEEE International Conference on Human-Robot Interaction},
  pages={361--370},
  year={2017},
  organization={ACM}
}

or An Autonomous Dynamic Camera Method for Effective Remote Teleoperation

@inproceedings{rakita2018autonomous,
  title={An autonomous dynamic camera method for effective remote teleoperation},
  author={Rakita, Daniel and Mutlu, Bilge and Gleicher, Michael},
  booktitle={Proceedings of the 2018 ACM/IEEE International Conference on Human-Robot Interaction},
  pages={325--333},
  year={2018},
  organization={ACM}
}