Towards User-Awareness in Human-Robot Collaboration for Future Cyber-Physical Systems

Abstract

Cyber-Physical Systems constitute one of the core concepts in Industry 4.0 aiming at realizing production systems that combine the efforts from human workers, robots and intelligent entities. This is particularly true in Human-Robot Collaboration manufacturing where a tight peer-to-peer interaction between humans and (intelligent) autonomous robots is necessary. Such production systems need a holistic integration along different levels of abstraction and coordination for deploying effective and safe control solutions. We propose the use of novel Artificial Intelligence technologies to enhance flexibility and adaptability of these collaborative systems. Our aim is to advance the classical human-aware paradigm that considers the worker as an anonymous acting entity, in favour of a user-aware paradigm, that considers a worker as profiled user characterized with a number of specific features influencing the "shape" of the collaboration.

Design of Advanced Human–Robot Collaborative Cells for Personalized Human–Robot Collaborations

“…It is worth stressing that the proposed framework is intended as a flexible toolkit of modules to be used based on the application requirements. For example, in a preliminary version of the framework [10], we addressed a use case inspired by the automotive industry. In that case, we did not use online Action and Motion planning because the application required a heavy-duty robot to perform slow and repetitive trajectories.…”

“…In addition, human-aware paradigms usually consider a one-fits-all solution, considering the human an anonymous agent. Here, we go beyond this concept and propose a user-centric methodology to shape the robots' behavior based on the specific characteristics of a single user (e.g., age, skills, experience) and preferences (e.g., left-handed vs. right-handed) [10], i.e., implementing personalized robot behavior that can better serve the human operator and, potentially, increase the technology perception and acceptance. Therefore, we propose the integration of planning, perception and communication into a unified technological framework.…”

Enhanced Cognition for Adaptive Human-Robot Collaboration

“…The tight integration of these two modules support higher levels of flexibility and adaptability of the whole HRC cell [14]. On the one hand it supports dynamic reconfiguration of planning models according to the known physical configuration of a HRC cells and skills/features of the "acting agents" that take part to collaborative processes [5], [14], [15]. On the other hand, it supports online detection of relevant situations and events triggering automatic adaptation of robot behaviors.…”

“…The environment cognition, the knowledge base and the task planner modules have been integrated into a ROS-based control architecture in order to support the collaborative production scenario depicted in Figure 1(c) 5 . Figure 2 shows the integration scheme of the developed modules.…”

“…Modern and future CPSs should increasingly take into account the human factor which is crucial to design efficient, safe and acceptable synergetic interactions between human and artificial actors [4]. This is especially true in Human-Robot Collaboration (HRC) scenarios where higher levels of flexibility and adaptability are necessary to dynamically adapt control policies to production needs as well as different skills and features of workers that take part in collaborative processes [5], [6].…”