Abstract
Contemporary research in human-machine symbiosis has mainly concentrated on enhancing relevant sensory, perceptual, and motor capacities, assuming short-term and nearly momentary interaction sessions. Still, human-machine confluence encompasses an inherent temporal dimension that is typically overlooked. The present work shifts the focus on the temporal and long-lasting aspects of symbiotic human-robot interaction (sHRI). We explore the integration of three time-aware modules, each one focusing on a diverse part of the sHRI timeline. Specifically, the Episodic Memory considers past experiences, the Generative Time Models estimate the progress of ongoing activities, and the Daisy Planner devices plans for the timely accomplishment of goals. The integrated system is employed to coordinate the activities of a multi-agent team. Accordingly, the proposed system (i) predicts human preferences based on past experience, (ii) estimates performance profile and task completion time, by monitoring human activity, and (iii) dynamically adapts multi-agent activity plans to changes in expectation and Human-Robot Interaction (HRI) performance. The system is deployed and extensively assessed in real-world and simulated environments. The obtained results suggest that building upon the unfolding and the temporal properties of team tasks can significantly enhance the fluency of sHRI.
Highlights
Fluent, symbiotic Human-Robot Interaction is an important, yet challenging problem in robotics research as evidenced by the increasing number of published works (Rosenthal et al, 2010; Fernando et al, 2014; Liu et al, 2016; Riccio et al, 2016) and review papers (Coradeschi and Loutfi, 2008; Green et al, 2008; Carrillo and Topp, 2016; Tsarouchi et al, 2016)
In this paper we present the implementation of a composite symbiotic Human-Robot Interaction (sHRI) system, that comprises the aforementioned time-aware cognitive modules
To facilitate temporal predictions by mere observation, we have introduced Generative Time Models (GTMs) (Hourdakis and Trahanias, 2018) that can accurately predict the duration of an unfolding activity. i.e., observation models that provide in real-time estimations of temporal quantities that characterize the activity
Summary
Symbiotic Human-Robot Interaction (sHRI) is an important, yet challenging problem in robotics research as evidenced by the increasing number of published works (Rosenthal et al, 2010; Fernando et al, 2014; Liu et al, 2016; Riccio et al, 2016) and review papers (Coradeschi and Loutfi, 2008; Green et al, 2008; Carrillo and Topp, 2016; Tsarouchi et al, 2016). Despite the significant resources devoted in sHRI, the majority of existing systems consider mainly the spatial aspects of the world without encapsulating the concept of the time dimension. Human-machine confluence encompasses inherent temporal aspects that are often considered only implicitly in robotic applications, with clear negative effects regarding the integration of artificial agents into human environments. Our recent work has addressed artificial temporal cognition, with a focus on human-like time representations and duration processing mechanisms for robots (Maniadakis et al, 2009, 2011; Maniadakis and Trahanias, 2012, 2015)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
