A framework for evaluating human driver models using neuroimaging

Christopher Strong, Kaylene Stocking, Jingqi Li, Tianjiao Zhang, Jack Gallant, Claire Tomlin
Proceedings of the 6th Annual Learning for Dynamics & Control Conference, PMLR 242:1565-1578, 2024.

Abstract

Driving is a complex task which requires synthesizing multiple senses, safely reasoning about the behavior of others, and adapting to a constantly changing environment. Failures of human driving models can become failures of vehicle safety features or autonomous driving systems that rely on their predictions. Although there has been a variety of work to model human drivers, it can be challenging to determine to what extent they truly resemble the humans they attempt to mimic. The development of improved human driver models can serve as a step towards better vehicle safety. In order to better compare and develop driver models, we propose going beyond driving behavior to examine how well these models reflect the cognitive activity of human drivers. In particular, we compare features extracted from human driver models with brain activity as measured by functional magnetic resonance imaging. We demonstrate this approach on three human driver models with brain activity data from two human subjects. We find that model predictive control is a better fit for driver brain activity than classic non-predictive models, which is in good agreement with previous works that obtain better predictions of human driving behavior using model predictive control.

Cite this Paper

BibTeX
@InProceedings{pmlr-v242-strong24b, title = {A framework for evaluating human driver models using neuroimaging}, author = {Strong, Christopher and Stocking, Kaylene and Li, Jingqi and Zhang, Tianjiao and Gallant, Jack and Tomlin, Claire}, booktitle = {Proceedings of the 6th Annual Learning for Dynamics & Control Conference}, pages = {1565--1578}, year = {2024}, editor = {Abate, Alessandro and Cannon, Mark and Margellos, Kostas and Papachristodoulou, Antonis}, volume = {242}, series = {Proceedings of Machine Learning Research}, month = {15--17 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v242/strong24b/strong24b.pdf}, url = {https://proceedings.mlr.press/v242/strong24b.html}, abstract = {Driving is a complex task which requires synthesizing multiple senses, safely reasoning about the behavior of others, and adapting to a constantly changing environment. Failures of human driving models can become failures of vehicle safety features or autonomous driving systems that rely on their predictions. Although there has been a variety of work to model human drivers, it can be challenging to determine to what extent they truly resemble the humans they attempt to mimic. The development of improved human driver models can serve as a step towards better vehicle safety. In order to better compare and develop driver models, we propose going beyond driving behavior to examine how well these models reflect the cognitive activity of human drivers. In particular, we compare features extracted from human driver models with brain activity as measured by functional magnetic resonance imaging. We demonstrate this approach on three human driver models with brain activity data from two human subjects. We find that model predictive control is a better fit for driver brain activity than classic non-predictive models, which is in good agreement with previous works that obtain better predictions of human driving behavior using model predictive control.} }
Endnote
%0 Conference Paper %T A framework for evaluating human driver models using neuroimaging %A Christopher Strong %A Kaylene Stocking %A Jingqi Li %A Tianjiao Zhang %A Jack Gallant %A Claire Tomlin %B Proceedings of the 6th Annual Learning for Dynamics & Control Conference %C Proceedings of Machine Learning Research %D 2024 %E Alessandro Abate %E Mark Cannon %E Kostas Margellos %E Antonis Papachristodoulou %F pmlr-v242-strong24b %I PMLR %P 1565--1578 %U https://proceedings.mlr.press/v242/strong24b.html %V 242 %X Driving is a complex task which requires synthesizing multiple senses, safely reasoning about the behavior of others, and adapting to a constantly changing environment. Failures of human driving models can become failures of vehicle safety features or autonomous driving systems that rely on their predictions. Although there has been a variety of work to model human drivers, it can be challenging to determine to what extent they truly resemble the humans they attempt to mimic. The development of improved human driver models can serve as a step towards better vehicle safety. In order to better compare and develop driver models, we propose going beyond driving behavior to examine how well these models reflect the cognitive activity of human drivers. In particular, we compare features extracted from human driver models with brain activity as measured by functional magnetic resonance imaging. We demonstrate this approach on three human driver models with brain activity data from two human subjects. We find that model predictive control is a better fit for driver brain activity than classic non-predictive models, which is in good agreement with previous works that obtain better predictions of human driving behavior using model predictive control.
APA
Strong, C., Stocking, K., Li, J., Zhang, T., Gallant, J. & Tomlin, C.. (2024). A framework for evaluating human driver models using neuroimaging. Proceedings of the 6th Annual Learning for Dynamics & Control Conference, in Proceedings of Machine Learning Research 242:1565-1578 Available from https://proceedings.mlr.press/v242/strong24b.html.

Related Material