Relational Activity Processes for Modeling Concurrent Cooperation

Marc Toussaint (1) , Thibaut Munzer (2) , Yoan Mollard (2) , Li Yang Wu (1) , Ngo Anh Anh Vien (1) , Manuel Lopes (2)

1 MLR - Machine Learning and Robotics [Stuttgart]
2 Flowers - Flowing Epigenetic Robots and Systems

In human-robot collaboration, multi-agent domains , or single-robot manipulation with multiple end-effectors, the activities of the involved parties are naturally concurrent. Such domains are also naturally relational as they involve objects, multiple agents, and models should generalize over objects and agents. We propose a novel formalization of relational concurrent activity processes that allows us to transfer methods from standard relational MDPs, such as Monte-Carlo planning and learning from demonstration, to concurrent cooperation domains. We formally compare the formulation to previous propositional models of concurrent decision making and demonstrate planning and learning from demonstration methods on a real-world human-robot assembly task.

Domaines: Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]; Robotique [cs.RO]

Marc Toussaint, Thibaut Munzer, Yoan Mollard, Li Yang Wu, Ngo Anh Anh Vien, et al.. Relational Activity Processes for Modeling Concurrent Cooperation. International Conference on Robotics and Automation, May 2016, Stockholm, Sweden. pp.5505 - 5511, ⟨10.1109/ICRA.2016.7487765⟩. ⟨hal-01399247⟩