An Interactive Multisensing Framework for Personalized Human Robot Collaboration and Assistive Training Using Reinforcement Learning

Abstract

There is a recent trend of research and applications of Cyber-Physical Systems (CPS) in manufacturing to enhance humanrobot collaboration and production. In this paper, we propose a CPS framework for personalized Human-Robot Collaboration and Training to promote safe human-robot collaboration in manufacturing environments. We propose a human-centric CPS approach that focuses on multimodal human behavior monitoring and assessment, to promote human worker safety and enable human training in Human-Robot Collaboration tasks. We present the architecture of our proposed system, our experimental testbed and our proposed methods for multimodal physiological sensing, human state monitoring and interactive robot adaptation, to enable personalized interaction. CCS Concepts •Human-centered computing ! Human computer interaction (HCI); •Computing methodologies ! Artificial intelligence; •Computer systems organization ! Embedded and cyber-physical systems;

FedStack: Personalized activity monitoring using stacked federated learning

“…The authors discussed how biological behavior is conceptually analogous to options in HRL. Tsiakas et al [38] proposed a human-centric cyberphysical systems (CPS) framework for personalized humanrobot collaboration and training. This framework focuses on monitoring and assessment of human behavior.…”

Patterns for Representing Knowledge Graphs to Communicate Situational Knowledge of Service Robots

“…Firstly, robots based on static systems are hard to adapt to user preferences and intuitively interact with users [18,21]. To address this problem and explore human-friendly systems, some recent research enhanced the accuracy of human-robot knowledge communication by acquiring multi-modal human behavior data or the AR interface [25,35,57].…”

A hybrid model-based evolutionary optimization with passive boundaries for physical human-robot interaction

“…Such modern pHRI features use machine learning and optimization techniques to enhance the robot's capability of co-adapting to a specific user and task [5]- [7], including changes in the robot's apparent impedance [8]- [10]. Although such techniques aim to give the robot a certain degree of autonomy to change its dynamic behavior, the shared autonomy must be limited to ensure the coupled system is safe, reducing the risk of potential injuries [11].…”