Human motion prediction improves robot safety and efficiency
Human Motion Prediction for Human-Robot Collaboration
Robotics
Summary
Predicting how people will move helps robots work more safely and smoothly near humans. The paper compares three ways to guess human motion, checking which works best for robots sharing space with people. These predictions help robots plan their moves better to avoid accidents and keep tasks running efficiently. The authors tested methods based on environmental patterns, transformer models, and graph-based neural networks.
What this means in practice
- •For robotics engineers: Improve planning algorithms by using tested methods to anticipate human motions during shared tasks.
- •For warehouse automation teams: Implement motion prediction to help robots avoid human workers dynamically, boosting safety in busy warehouses.
Authors
Placido Falqueto, Elena Basei, Edoardo Lamon, Giovanni Perantoni, Matteo Saveriano, Daniele Fontanelli, Luigi Palopoli
Abstract
This paper compares three human motion prediction methods - GMM-based clustering, TransFusion, and Graph-Mixer - evaluating their effectiveness in human-robot collaboration. These predictions are valuable for improving robot motion planning by anticipating human movements and enhancing safety and efficiency in dynamic environments.