Dynamic Adaptability in Human-Robot Collaboration for Industrial Assembly: A Behaviour Tree Based Task Execution

Sharath Chandra Akkaladevi, Matthias Propst, Kapil Deshpande, Michael Hofmann, Andreas Pichler, Panagiotis Sapoutzoglou, Athena Zacharia, Dimitrios Kalogeras, Maria Pateraki

Abstract: This work deals with the intricacies of human-robot collaboration (HRC) within industrial settings, with a focus on achieving seamless interaction through a skill-based robot task execution engine. The proposed framework intricately orchestrates the dynamic interplay between the perception and acting/reacting layers in the context of human-robot collaboration, with a specific emphasis on the role of Behavior Trees (BTs) in both task execution and deviation handling. The Behavior Tree-based Task Execution (BTE) is seamlessly integrated into the acting/reacting layer, collaborating synergistically with the perception layer, which includes robot proprioception and object localization modules. This integration facilitates the efficient detection and handling of deviations, particularly those arising from failures during robotic manipulation (grasping), ensuring real-time responsiveness to environmental changes in collaborative assembly tasks. Real-world experiments conducted on a car door assembly line serve as practical demonstrations of the proposed framework’s adaptability to address deviations in dynamic environments.