Safe Road-Crossing by Autonomous Wheelchairs: a Novel Dataset and its Experimental Evaluation

TL;DR

This paper presents a multi-sensor fusion system for autonomous wheelchairs to safely cross roads, introducing a new dataset and demonstrating improved decision accuracy through experimental evaluation in a lab setting.

Contribution

It introduces a novel multi-sensor fusion approach and a new dataset for safe road-crossing in autonomous wheelchairs, with experimental validation.

Findings

Multi-sensor fusion improves decision accuracy.

The dataset supports further research.

Experimental results show safety benefits.

Abstract

Safe road-crossing by self-driving vehicles is a crucial problem to address in smart-cities. In this paper, we introduce a multi-sensor fusion approach to support road-crossing decisions in a system composed by an autonomous wheelchair and a flying drone featuring a robust sensory system made of diverse and redundant components. To that aim, we designed an analytical danger function based on explainable physical conditions evaluated by single sensors, including those using machine learning and artificial vision. As a proof-of-concept, we provide an experimental evaluation in a laboratory environment, showing the advantages of using multiple sensors, which can improve decision accuracy and effectively support safety assessment. We made the dataset available to the scientific community for further experimentation. The work has been developed in the context of an European project named REXASI-PRO, which aims to develop trustworthy artificial intelligence for social navigation of people with reduced mobility.