Safe mobility support system using crowd mapping and avoidance route planning using VLM

TL;DR

This paper presents a novel framework combining Vision-Language Models and Gaussian Process Regression to generate dynamic crowd-density maps, enabling autonomous robots to navigate safely in crowded environments.

Contribution

It introduces an innovative integration of VLM and GPR for real-time crowd mapping and route planning in autonomous robot navigation.

Findings

Robots successfully avoided static obstacles and dynamic crowds in real-world campus trials.

The approach improved navigation safety and adaptability in crowded environments.

Experimental results demonstrated effective crowd-density recognition and route planning.

Abstract

Autonomous mobile robots offer promising solutions for labor shortages and increased operational efficiency. However, navigating safely and effectively in dynamic environments, particularly crowded areas, remains challenging. This paper proposes a novel framework that integrates Vision-Language Models (VLM) and Gaussian Process Regression (GPR) to generate dynamic crowd-density maps (``Abstraction Maps'') for autonomous robot navigation. Our approach utilizes VLM's capability to recognize abstract environmental concepts, such as crowd densities, and represents them probabilistically via GPR. Experimental results from real-world trials on a university campus demonstrated that robots successfully generated routes avoiding both static obstacles and dynamic crowds, enhancing navigation safety and adaptability.