知覚不確かさ下での安全な適応クルーズコントロール:深層アンサンブルとConformal Tubeモデル予測制御によるアプローチ
Safe Adaptive Cruise Control Under Perception Uncertainty: A Deep Ensemble and Conformal Tube Model Predictive Control Approach
RGB画像から深層アンサンブルとConformal Predictionで不確かさを推定し、Conformal Tubeモデル予測制御で適応クルーズコントロールの確率的な安全性を確保する手法を提案した。
著者: Xiao Li, Anouck Girard, Ilya Kolmanovsky
分類: cs.RO, cs.AI, cs.SY, eess.SY
原文アブストラクト
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.
