Agent's Cooperation Levels to Enhance Human-Robot Teaming - Laboratoire d’Automatique, de Mécanique et d’Informatique Industrielles et Humaines Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Agent's Cooperation Levels to Enhance Human-Robot Teaming

Résumé

Effective cooperation between human operators and robots is essential for the accomplishment of crucial tasks in tough and dangerous contexts, such as search and rescue operations. While autonomous robots excel at moving through dangerous conditions, human decisions made on the basis of global knowledge and experience, are still required to adapt to unforeseen events. We used a Human-Machine Cooperation model to address this topic. The model proposes the definitions to analyze the Know-How-to-Operate and Know-How-to-Cooperate competencies of the teaming agents, in relation to the different phases of a shared task. On this basis, we designed four cooperation levels for the team with the addition of an intelligent assistant system (IAS) agent. As a proof-of-concept, these levels have been implemented for evaluation purposes in a team composed of one human, one IAS, and two robots. In our study we demonstrated the practical implementation of the proposed cooperation levels within a human-robot team, emphasizing the Intelligent Assistance System (IAS) agent's ability to improve cooperation and task efficiency in hazardous environments.
Fichier principal
Vignette du fichier
TULA_AAMAS_ARMS_2024.pdf (1.12 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04571571 , version 1 (08-05-2024)

Licence

Identifiants

  • HAL Id : hal-04571571 , version 1

Citer

Sridath Tula, Marie-Pierre Pacaux-Lemoine, Emmanuelle Grislin-Le Strugeon, Paulo Eduardo Santos, Anna Ma-Wyatt, et al.. Agent's Cooperation Levels to Enhance Human-Robot Teaming. Workshop ARMS (Autonomous Robots and Multirobot Systems), 23rd Inter. Conference on Autonomous Agents and Multiagent Systems (AAMAS'24), May 2024, Auckland, New Zealand. ⟨hal-04571571⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More