RhuMAn - Rapid Human Manipulability Assessment

Rapid Human-Manipulability Assessment is a tool for muscular & ergonomics rapid assessment

Library

RhuMAn concept

Developed by
License
MIT license (MIT)

Main Characteristic

RHuMAn (Rapid Human-Manipulability Assessment): A tool for collaborative AI applications that allows the computation of a human comfort quality index distribution in the workspace. RHuMAn draws upon extensive offline analysis of human biomechanics capabilities with ergonomics assessment from industrial-standard directives to produce an efficient online comfort-quality assessment that can be quickly tailored to specific tasks and purposes.

Research areas
Collaborative AI Physical AI
Technical Categories
Robotics and automation
Last updated
27.05.2021 - 09:32
Detailed Description

Language of the library: Other, Multiplatform

Install and run: To start using download a database of OpenSim based biomechanics assessment, available at:

git clone -b OpenSimData git@gitlab.com:figueredo/rHuMAn.git

A typical usage of RHuMAn is to analyze motion performance and to design physical human-robot collaborative planners that take human-informed features into account. A simple example is also provided to introduce users on the usage of the tool.

More information: The aims of RHuMAn is to provide an easy-to-use platform that integrates kinematics, muscular-activity assessment and ergonomy-based metrics to non-experts. To this aim, RHuMAn simplifies biomechanics and ergonomics analysis making it straightforward for users from different backgrounds. The tool also provides a database of biomechanics parameters extracted from OpenSim and a tool that enables anyone to extract different parameters (for a different model and anthropometry features).

The rHuMAn (Rapid Human-Manipulability Assessment) tool provides

  • a human kinematics model according to biomechanics literature;
  • tools to analyze upper-limb muscular activity from task-space forces and accelerations;
  • assessment of ergonomics according to postural rapid techniques (e.g., RULA);
  • a dataset with biomechanics parameters for the upper-limb (e.g., muscle-length, muscle maximum isometric force, moment-arm between muscles and joints);
  • a framework to integrate ergonomics and muscular-based metrics into manipulability distributions.
  • visualization assessment.

External links:

Trustworthy AI
rHuMAn is a library that facilitates the use and development of human manipulation performance metrics in terms of biomechanics and ergonomy-based metrics. Its aim is to help the AI and robotics communities to design human-aware tools and algorithms. Notice however that safety and trustworthy AI should be guaranteed by the user and designer. As stated in the license, this software is provided "as is", without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose and noninfringement. In no event shall the authors or copyright holders be liable for any claim, damages or other liability, whether in an action of contract, tor or otherwise, arising from out of or in connection with the software or the use or other dealings in the software.
GDPR Requirements
rHuMAn library does not collect or use any personal data from users, hence GDPR does not apply