Learning by demonstration techniques are becoming popular in human-robot collaboration (HRC) because they allow exploiting the versatility of collaborative robots. In this context, Dynamic Motion Primitives (DMPs) are a standard method for allowing human operators to easily teach tasks to robots. However, DMPs do not guarantee compliance with ISO/TS 15066 safety standards. This work addresses these issues by introducing a control pipeline that adapts DMPs through an optimization problem to ensure compliance with the Speed and Separation Monitoring (SSM) safety mode. The approach has been experimentally validated in a real scenario, where a UR5e robot and a human operator collaborate on a polishing task.
A Novel DMPs Based Approach to Comply ISO/TS 15066 / Pupa, A.; Di Vittorio, F.; Secchi, C.. - 36:(2025), pp. 48-54. ( 16th European Robotics Forum, ERF 2025 deu 2025) [10.1007/978-3-031-89471-8_8].
A Novel DMPs Based Approach to Comply ISO/TS 15066
Pupa A.
;Secchi C.
2025
Abstract
Learning by demonstration techniques are becoming popular in human-robot collaboration (HRC) because they allow exploiting the versatility of collaborative robots. In this context, Dynamic Motion Primitives (DMPs) are a standard method for allowing human operators to easily teach tasks to robots. However, DMPs do not guarantee compliance with ISO/TS 15066 safety standards. This work addresses these issues by introducing a control pipeline that adapts DMPs through an optimization problem to ensure compliance with the Speed and Separation Monitoring (SSM) safety mode. The approach has been experimentally validated in a real scenario, where a UR5e robot and a human operator collaborate on a polishing task.
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
