Toward Crowd-Sensitive Path Planning

TL;DR

This paper introduces an online algorithm for robots to predict and incorporate crowd densities into path planning, improving navigation efficiency and safety in crowded environments.

Contribution

It presents a novel fast, online crowd density learning method that enhances existing navigation systems for better crowd-aware path planning.

Findings

Robots reach targets faster in crowded scenarios.

Travel distance is reduced with crowd-aware planning.

Collision risks are decreased using the proposed method.

Abstract

If a robot can predict crowds in parts of its environment that are inaccessible to its sensors, then it can plan to avoid them. This paper proposes a fast, online algorithm that learns average crowd densities in different areas. It also describes how these densities can be incorporated into existing navigation architectures. In simulation across multiple challenging crowd scenarios, the robot reaches its target faster, travels less, and risks fewer collisions than if it were to plan with the traditional A* algorithm.