Joint Navigation in Commander/Robot Teams: Dialog and Task Performance When Vision is Bandwidth-Limited

Abstract

The prospect of human commanders teaming with mobile robots "smart enough" to undertake joint exploratory tasks-especially tasks that neither commander nor robot could perform alone-requires novel methods of preparing and testing human-robot teams for these ventures prior to real-time operations. In this paper, we report work-in-progress that maintains face validity of selected configurations of resources and people, as would be available in emergency circumstances. More specifically, from an off-site post, we ask human commanders (C) to perform an exploratory task in collaboration with a remotely located human robot-navigator (Rn) who controls the navigation of, but cannot see the physical robot (R). We impose network bandwidth restrictions in two mission scenarios comparable to real circumstances by varying the availability of sensor, image, and video signals to Rn, in effect limiting the human Rn to function as an automation stand-in. To better understand the capabilities and language required in such configurations, we constructed multi-modal corpora of time-synced dialog, video, and LIDAR files recorded during task sessions. We can now examine commander/robot dialogs while replaying what C and Rn saw, to assess their task performance under these varied conditions. This work is licenced under a Creative Commons Attribution 4.0 International License. Page numbers and proceedings footer are added by the organizers. License details: http://creativecommons.org/licenses/by/4.0/

Formalizing and evaluating requirements of perception systems for automated vehicles using spatio-temporal perception logic

“…Comprehensive surveys and comparisons of reasoning methods about topology and time are provided by Dylla et al (2017); Aiello et al (2007). Spatio-temporal logics and calculi are also frequently used in robotics for human-robot communication (Kress-Gazit and Pappas (2010); Summers-Stay et al (2014)) and for specifying and verifying properties of AV (Linker and Hilscher (2013); Loos et al (2011)). All the aforementioned works that deal with topology and time primarily focus on deductive reasoning, theorem proving, knowledge representation, axiomatization, and, in some cases, planning.…”

Formalizing and Evaluating Requirements of Perception Systems for Automated Vehicles using Spatio-Temporal Perception Logic

“…Comprehensive surveys and comparisons of reasoning methods about topology and time are provided [20], [37]. Spatio-temporal logics and calculi are also frequently used in robotics for human-robot communication [38], [39] and for specifying and verifying properties of AV [40], [41]. All the aforementioned works that deal with topology and time primarily focus on deductive reasoning, theorem proving, knowledge representation, axiomatization, and -in some cases -planning.…”