Skip to main content Skip to main navigation

Publication

Physics-Aware Conformal Prediction for Deep Learning-based Wheelchair Local Navigation

Sara Narteni; Alberto Carlevaro; Zeming Duan; Serge Autexier; Maurizio Mongelli
In: Khuong An Nguyen; Zhiyuan Luo; Harris Papadopoulos; Tuwe Löfström; Lars Carlsson; Henrik Boström (Hrsg.). Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications. Symposium in Conformal and Probabilistic Prediction with Applications (COPA-2025), September 10-12, London, United Kingdom, Pages 778-780, Proceedings of Machine Learning Research (PMLR), Vol. 266, PMLR, 9/2025.

Abstract

When dealing with conformal prediction for real-world artificial intelligence applications, it is necessary to ensure its physical feasibility. In this work, we propose to tackle this problem for an autonomous wheelchair guided by a deep neural network for local navigation. We adapt the conformal sets to be compliant with the wheelchair’s kinematics, enhancing their efficiency while preserving coverage guarantees.

Projects

More links