On Transient-Goal Selection for Communication-Aware Robotic Navigation in Large Human-Populated Environments

Robots deployed in large human-populated indoor environments such as shopping malls, airports etc., communicate via wireless networks for enhanced perception and decision making capabilities. Owing to dynamic signal attenuation in such environments, connectivity issues can arise during robotic navigation, causing information flow disruption that can lead to potential danger. Also, the presence of humans also add a layer of temporal signal variation complexities. This work presents an approach for embedding radio signal strength constraints within networked service/social robot navigation in large human-populated environments. We develop a Gaussian Process based online spatio-temporal signal strength prediction model that also aims to take into account the temporal fading arising due to the presence of human crowds. Based on this model, we then devise a transient-goal driven navigation strategy to realize a sub-optimal path towards a known goal, that is aimed at resolving both communication-aware and human-aware planning constraints.