Group abstraction for assisted navigation of social activities in intelligent environments

Abstract

The ACANTO project is developing robotic assistants to aid the confidence and recovery of older adults. A key requirement of these assistants is aiding with navigation in complex and potentially chaotic environments. Prior work has addressed this for a single user, using a single robotic assistant in an intelligent environment. However, for therapeutic purposes, ACANTO supports social groups and group activities. ACANTO's robotic assistants must therefore be able to plan the motion of groups of older adults walking together. This requires an efficient navigation solution that can handle large numbers of users and that can operate rapidly on embedded computing devices. To increase user confidence, the solution must encourage group cohesion without trying to impose its own rigid structure; it must try to maintain the natural (de facto) group structure despite unpredictable behaviours and environmental conditions. Our on-the-fly group motion planner addresses these challenges by: using intelligent environment information to develop behavioural traces, clustering traces to determine groups, constructing a predictive model of the groups as a whole, and finding an optimal suggested trajectory using Statistical Model Checking. In this work we describe our proposed approach in detail and validate some of its novel aspects on the ETH Zürich pedestrian motion dataset.

Location-aware systems or location-based services: a survey with applications to CoViD-19 contact tracking

“…Accordingly, the more specific problem is a problem of optimizing the route with respect to a number of contextual factors including factors of personal preferences or specific narratives [ 124 ] that allow a structuring of the information contents associated with each location and has been studied early as an example of an LAS application [ 164 ]. A more recent example demonstrates that not only individual navigation strategies, but also navigation of groups can be supported [ 61 ].…”

Increasing user confidence in intelligent environments

“…Last but not least, in the third paper [21], Given-Wilson, Legay, Sedwards, and Zendra propose the ACANTO project to develop robotic assistants helping older adults engaged in therapeutic activities to navigate through complex physical environments. A key contribution of ACANTO is that it addresses navigation in multi-user, multi-robot environments.…”

Intelligent environments with entangled quality properties

“…It is particularly difficult to decide which are the most important quality properties to be fulfilled in an IE. In this last decade, some researchers of the IE field have focussed their contributions on addressing specific quality goals [ 10 – 18 ]. However, there are fewer contributions analyzing the interactions between those quality properties, and how they should be balanced with others in real consumer-oriented developments.…”