Safe Adaptive Cruise Control Under Perception Uncertainty: A Deep Ensemble and Conformal Tube Model Predictive Control Approach

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Xiao, Girard, Anouck, Kolmanovsky, Ilya
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912144977559552
author Li, Xiao
Girard, Anouck
Kolmanovsky, Ilya
author_facet Li, Xiao
Girard, Anouck
Kolmanovsky, Ilya
contents Autonomous driving heavily relies on perception systems to interpret the environment for decision-making. To enhance robustness in these safety critical applications, this paper considers a Deep Ensemble of Deep Neural Network regressors integrated with Conformal Prediction to predict and quantify uncertainties. In the Adaptive Cruise Control setting, the proposed method performs state and uncertainty estimation from RGB images, informing the downstream controller of the DNN perception uncertainties. An adaptive cruise controller using Conformal Tube Model Predictive Control is designed to ensure probabilistic safety. Evaluations with a high-fidelity simulator demonstrate the algorithm's effectiveness in speed tracking and safe distance maintaining, including in Out-Of-Distribution scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2412_03792
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Safe Adaptive Cruise Control Under Perception Uncertainty: A Deep Ensemble and Conformal Tube Model Predictive Control Approach
Li, Xiao
Girard, Anouck
Kolmanovsky, Ilya
Robotics
Artificial Intelligence
Systems and Control
Autonomous driving heavily relies on perception systems to interpret the environment for decision-making. To enhance robustness in these safety critical applications, this paper considers a Deep Ensemble of Deep Neural Network regressors integrated with Conformal Prediction to predict and quantify uncertainties. In the Adaptive Cruise Control setting, the proposed method performs state and uncertainty estimation from RGB images, informing the downstream controller of the DNN perception uncertainties. An adaptive cruise controller using Conformal Tube Model Predictive Control is designed to ensure probabilistic safety. Evaluations with a high-fidelity simulator demonstrate the algorithm's effectiveness in speed tracking and safe distance maintaining, including in Out-Of-Distribution scenarios.
title Safe Adaptive Cruise Control Under Perception Uncertainty: A Deep Ensemble and Conformal Tube Model Predictive Control Approach
topic Robotics
Artificial Intelligence
Systems and Control
url https://arxiv.org/abs/2412.03792