Work-related musculoskeletal disorders are one of the dominant sources of disabilities worldwide. Nowadays, when collaborative robots interact with humans in workplaces, intelligent models can help to ensure human comfort and ergonomics.
Image credit: Audi
A recent study introduces a framework for ergonomically intelligent human-robot interaction. It includes posture estimation, assessment, optimization, and correction.
It is shown that the interacting robot is an adequate sensor for continuous posture monitoring and the risk of injuries. The posture is estimated solely from the trajectory of the interacting robot. An accurate, continuous, and differentiable ergonomics assessment model is used to learn upper body ergonomics.
The results of a demo task reveal that postural optimization using the proposed model lowers the risk of injuries.
Ergonomics and human comfort are essential concerns in physical human-robot interaction applications, and common practical methods either fail in estimating the correct posture due to occlusion or suffer from less accurate ergonomics models in their postural optimization methods. Instead, we propose a novel framework for posture estimation, assessment, and optimization for ergonomically intelligent physical human-robot interaction. We show that we can estimate human posture solely from the trajectory of the interacting robot. We propose DULA, a differentiable ergonomics model, and use it in gradient-free postural optimization for physical human-robot interaction tasks such as co-manipulation and teleoperation. We evaluate our framework through human and simulation experiments.
Research paper: Yazdani, A., Sabbagh Novin, R., Merryweather, A., and Hermans, T., “Ergonomically Intelligent Physical Human-Robot Interaction: Postural Estimation, Assessment, and Optimization”, 2021. Link: https://arxiv.org/abs/2108.05971