Curiosity-based Robot Navigation under Uncertainty in Crowded Environments

TL;DR

This paper introduces a curiosity-driven navigation framework for mobile robots operating in crowded, large-scale environments, effectively balancing localization accuracy, crowd avoidance, and human comfort.

Contribution

It proposes a novel curiosity-based approach that integrates uncertainty assessment, crowd density mapping, and human comfort considerations for safe robot navigation.

Findings

The method successfully navigates in crowded environments considering localization uncertainty.

It effectively avoids crowded areas while maintaining human comfort.

The approach demonstrates improved path planning in large-scale, noisy environments.

Abstract

Mobile robots have become more and more popular in large-scale and crowded environments, such as airports, shopping malls, etc. However, due to sparse landmarks and crowd noise, localization in this environment is a great challenge. Furthermore, it is unreliable for the robot to navigate safely in crowds while considering human comfort. Thus, how to navigate safely with localization precision in that environment is a critical problem. To solve this problem, we proposed a curiosity-based framework that can find an effective path with the consideration of human comfort and crowds, localization uncertainty, and the cost-to-go to the target. Three parts are involved in the proposed framework: the distance assessment module, the Curiosity for Positive Content (CPC), namely information-rich areas, and the Curiosity for Negative Content (CNC), namely crowded areas. CPC is introduced when the real-time localization uncertainty evaluation is not satisfied. This factor is predicted through the propagation of uncertainty along the candidate trajectory to provoke the robot to approach localization-referenced landmarks. The Human Comfort and Crowd Density Map (HCCDM) based on the Gaussian Mixture Model (GMM) is established to calculate CNC, which drives the robot to bypass the crowd and consider human comfort. The evaluation is conducted in a series of large-scale and crowded environments. The results show that our method can find a feasible path that can consider the localization uncertainty while simultaneously avoiding the crowded area.