Skip to Main content Skip to Navigation
Journal articles

Multi-objective Trajectory Optimization to Improve Ergonomics in Human Motion

Waldez Gomes 1 Pauline Maurice 1 Eloïse Dalin 1 Jean-Baptiste Mouret 1 Serena Ivaldi 1
1 LARSEN - Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : Work-related musculoskeletal disorders are a majorhealth issue often caused by awkward postures. Identifyingand recommending more ergonomic body postures requiresoptimizing the worker’s motion with respect to ergonomicscriteria based on the human kinematic/kinetic state. However,many ergonomics scores assess different risks at different placesof the human body, and therefore, optimizing for only onescore might lead to postures that are either inefficient or thattransfer the risk to a different location. We verified, in two workactivities, that optimizing for a single ergonomics score maylead to motions that degrade scores other than the optimizedone. To address this problem, we propose a multi-objectiveoptimization approach that can find better Pareto-optimal trade-off motions that simultaneously optimize multiple scores. Oursimulation-based approach is also user-specific and can be usedto recommend ergonomic postures to workers with differentbody morphologies. Additionally, it can be used to generateergonomic reference trajectories for robot controllers in human-robot collaboration.
Complete list of metadata
Contributor : Waldez Gomes Connect in order to contact the contributor
Submitted on : Wednesday, October 27, 2021 - 3:24:36 PM
Last modification on : Thursday, October 28, 2021 - 4:09:58 AM


Files produced by the author(s)


  • HAL Id : hal-03281827, version 2


Waldez Gomes, Pauline Maurice, Eloïse Dalin, Jean-Baptiste Mouret, Serena Ivaldi. Multi-objective Trajectory Optimization to Improve Ergonomics in Human Motion. IEEE Robotics and Automation Letters, IEEE inPress. ⟨hal-03281827v2⟩



Record views


Files downloads