Towards Perception-based Collision Avoidance for UAVs when Guiding the Visually Impaired

TL;DR

This paper presents a perception-based collision avoidance system for UAVs assisting visually impaired individuals, integrating local obstacle avoidance with global GPS-based planning, validated in real outdoor scenarios.

Contribution

It introduces a multi DNN framework for obstacle avoidance tailored for UAVs guiding visually impaired people in urban environments.

Findings

Feasibility demonstrated in campus scenarios

Effective obstacle avoidance near vehicles and crowds

Integration of local and global planning enhances navigation

Abstract

Autonomous navigation by drones using onboard sensors combined with machine learning and computer vision algorithms is impacting a number of domains, including agriculture, logistics, and disaster management. In this paper, we examine the use of drones for assisting visually impaired people (VIPs) in navigating through outdoor urban environments. Specifically, we present a perception-based path planning system for local planning around the neighborhood of the VIP, integrated with a global planner based on GPS and maps for coarse planning. We represent the problem using a geometric formulation and propose a multi DNN based framework for obstacle avoidance of the UAV as well as the VIP. Our evaluations conducted on a drone human system in a university campus environment verifies the feasibility of our algorithms in three scenarios; when the VIP walks on a footpath, near parked vehicles, and in a crowded street.