Towards Metareasoning for Human-Robot Interaction

Abstract

Abstract. This paper proposes a model of metareasoning for HumanRobot Interaction (HRI). Robots' basic abilities for HRI-planning, learning and dialogue-are characterized as three loops in the model, with each spanning ground, object and meta-level. The model provides a conceptualization of HRI and a framework for incremental development of large HRI systems such as service robots by building meta-level functions on top of existing ground/object level components. A case-study focusing on meta-level control shows that the approach is effective and efficient for some application domains. In particular, meta-level control suggests a new opportunity to speed up planning while preserving completeness without any change to object level planners. The experiments also show that, for some basic HRI tasks, there are simple meta-level strategies with performances better than the common strategy in previous work.

A Validated Ontology for Metareasoning in Intelligent Systems

“…Terms per Paper Citations per Paper * (Russell and Wefald 1991) 48 444 (Conitzer and Sandholm 2003) 67 41 (Cox 2005) 63 261 (Anderson and Oates 2007) 36 91 (Schmill et al 2007) 77 21 (Cox and Raja 2008) 55 100 (Chen et al 2013) 37 (Lin et al 2015) 54 46 (Lieder and Griffiths 2017) 37 23 (Ackerman and Thompson 2017) 36 105 (Milli et al 2017) 35 39 (Cserna et al 2017) 34 (Karpas et al 2018) 22 (Farmer 2018) 7 (Madera-Doval 2019) 27 (Houeland and Aamodt 2018) 25 (Parashar et al 2018) 33 (Griffiths et al 2019) 18 29 41 16 (Sung et al 2021) 36…”

Toward Open Knowledge Enabling for Human- Robot Interaction

“…The open knowledge searching module is triggered to obtain relevant pieces of knowledge from open-source knowledge resources. A meta-control mechanism (Chen, Sui, & Ji, 2012) is also needed for the coordination of these modules but is not shown in Figure 1. The robot's sensors include a laser range finder, a stereo camera, and a 2D camera.…”