Probabilistic Modelling for Trustworthy Artificial Intelligence in Drone-Supported Autonomous Wheelchairs

In this work, we address the potential of probabilistic modelling approaches for ensuring trustworthy AI in sensing subsystems within drone-supported autonomous wheelchairs. The combination of drones and autonomous wheelchairs provides an innovative solution for enhancing mobility and independence of motionimpaired people. However, safety is a critical concern when deploying such systems in real-world scenarios. To address this challenge, probabilistic models can be used to capture uncertainty and nonstationarity in the environment and sensory system, enabling the device to make informed decisions while ensuring safe autonomy. The approach is being developed in the context of a recently started European project named REXASI-PRO, which addresses the modelling methodology, tools, reference architecture, design and implementation guidelines. In the project, relevant indoor and outdoor navigation use cases are addressed to demonstrate the effectiveness of the proposed approach in providing trustworthy autonomous wheelchairs in real-world environments.

Automated summary

In this paper, the potential of probabilistic modelling approaches for ensuring trustworthy AI in drone-supported autonomous wheelchairs' sensing subsystems is addressed. Probabilistic models can capture uncertainty and nonstationarity in the environment and sensory system, enabling informed decisions and safe autonomy. The approach is being developed in a European project named REXASI-PRO, which focuses on modelling methodology, tools, reference architecture, design, and implementation guidelines. Different use cases are considered to demonstrate the effectiveness of the proposed approach in providing trustworthy autonomous wheelchairs in real-world environments.