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

Sara Narteni, Alberto Carlevaro, Zeming Duan, Serge Autexier, Maurizio Mongelli
Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 266:778-780, 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v266-narteni25a, title = {Physics-Aware Conformal Prediction for Deep Learning-based Wheelchair Local Navigation}, author = {Narteni, Sara and Carlevaro, Alberto and Duan, Zeming and Autexier, Serge and Mongelli, Maurizio}, booktitle = {Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {778--780}, year = {2025}, editor = {Nguyen, Khuong An and Luo, Zhiyuan and Papadopoulos, Harris and Löfström, Tuwe and Carlsson, Lars and Boström, Henrik}, volume = {266}, series = {Proceedings of Machine Learning Research}, month = {10--12 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v266/main/assets/narteni25a/narteni25a.pdf}, url = {https://proceedings.mlr.press/v266/narteni25a.html}, 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.} }
Endnote
%0 Conference Paper %T Physics-Aware Conformal Prediction for Deep Learning-based Wheelchair Local Navigation %A Sara Narteni %A Alberto Carlevaro %A Zeming Duan %A Serge Autexier %A Maurizio Mongelli %B Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2025 %E Khuong An Nguyen %E Zhiyuan Luo %E Harris Papadopoulos %E Tuwe Löfström %E Lars Carlsson %E Henrik Boström %F pmlr-v266-narteni25a %I PMLR %P 778--780 %U https://proceedings.mlr.press/v266/narteni25a.html %V 266 %X 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.
APA
Narteni, S., Carlevaro, A., Duan, Z., Autexier, S. & Mongelli, M.. (2025). Physics-Aware Conformal Prediction for Deep Learning-based Wheelchair Local Navigation. Proceedings of the Fourteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 266:778-780 Available from https://proceedings.mlr.press/v266/narteni25a.html.

Related Material