日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

週刊ニュースレター購読
arXiv:2103.01818

A Safety-Aware Kinodynamic Architecture for Human-Robot Collaboration

A Safety-Aware Kinodynamic Architecture for Human-Robot Collaboration

シェア:XThreadsFacebookLINEはてブBluesky

著者: Andrea Pupa, Mohammad Arrfou, Gildo Andreoni, Cristian Secchi

分類: cs.RO

原文アブストラクト

The new paradigm of human-robot collaboration has led to the creation of shared work environments in which humans and robots work in close contact with each other. Consequently, the safety regulations have been updated addressing these new scenarios. The mere application of these regulations may lead to a very inefficient behavior of the robot. In order to preserve safety for the human operators and allow the robot to reach a desired configuration in a safe and efficient way, a two layers architecture for trajectory planning and scaling is proposed. The first layer calculates the nominal trajectory and continuously adapts it based on the human behavior. The second layer, which explicitly considers the safety regulations, scales the robot velocity and requests for a new trajectory if the robot speed drops. The proposed architecture is experimentally validated on a Pilz PRBT manipulator.