Minimally Invasive Social Navigation

TL;DR

This paper introduces a flow field representation of crowds for robot navigation, aiming to minimize human disturbance, and presents an algorithmic framework with promising experimental results.

Contribution

It proposes a novel flow field approach for social navigation that reduces invasiveness, enhancing computational efficiency and safety in robot-human interactions.

Findings

Flow field representation effectively models crowd movement.

The proposed algorithm reduces invasiveness in navigation.

Experimental results demonstrate improved navigation performance.

Abstract

Integrating mobile robots into human society involves the fundamental problem of navigation in crowds. This problem has been studied by considering the behaviour of humans at the level of individuals, but this representation limits the computational efficiency of motion planning algorithms. We explore the idea of representing a crowd as a flow field, and propose a formal definition of path quality based on the concept of invasiveness; a robot should attempt to navigate in a way that is minimally invasive to humans in its environment. We develop an algorithmic framework for path planning based on this definition and present experimental results that indicate its effectiveness. These results open new algorithmic questions motivated by the flow field representation of crowds and are a necessary step on the path to end-to-end implementations.