This paper proposes a scheme for letting a human interact with a generic robot in a natural manner. Based on the concept of natural user interfaces, the proposed methods exploit recognition of the users’ forearm motion to produce commands for the robotic system. High-level commands are provided based on gesture recognition, and velocity commands are computed for the robot by mapping, in a natural manner, the motion of the user’s forearm. The method is proposed in a general manner, and is then instantiated considering two different robotic systems, namely a quadrotor and a wheeled mobile robot. Usability of the system is evaluated with experiments involving users.
A General Approach to Natural Human-Robot Interaction / Sabattini, Lorenzo; Villani, Valeria; Secchi, Cristian; Fantuzzi, Cesare. - 7:(2019), pp. 61-67. (Intervento presentato al convegno 10th International Workshop on Human-Friendly Robotics (HFR 2017) tenutosi a Napoli nel November 6-7, 2017).
A General Approach to Natural Human-Robot Interaction
Lorenzo Sabattini;Valeria Villani;Cristian Secchi;Cesare Fantuzzi
2019
Abstract
This paper proposes a scheme for letting a human interact with a generic robot in a natural manner. Based on the concept of natural user interfaces, the proposed methods exploit recognition of the users’ forearm motion to produce commands for the robotic system. High-level commands are provided based on gesture recognition, and velocity commands are computed for the robot by mapping, in a natural manner, the motion of the user’s forearm. The method is proposed in a general manner, and is then instantiated considering two different robotic systems, namely a quadrotor and a wheeled mobile robot. Usability of the system is evaluated with experiments involving users.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