Xiao Li, H. Eric Tseng, Anouck Girard, Ilya Kolmanovsky
{"title":"感知不确定性下的自动驾驶:基于深度集合的自适应巡航控制","authors":"Xiao Li, H. Eric Tseng, Anouck Girard, Ilya Kolmanovsky","doi":"arxiv-2403.15577","DOIUrl":null,"url":null,"abstract":"Autonomous driving depends on perception systems to understand the\nenvironment and to inform downstream decision-making. While advanced perception\nsystems utilizing black-box Deep Neural Networks (DNNs) demonstrate human-like\ncomprehension, their unpredictable behavior and lack of interpretability may\nhinder their deployment in safety critical scenarios. In this paper, we develop\nan Ensemble of DNN regressors (Deep Ensemble) that generates predictions with\nquantification of prediction uncertainties. In the scenario of Adaptive Cruise\nControl (ACC), we employ the Deep Ensemble to estimate distance headway to the\nlead vehicle from RGB images and enable the downstream controller to account\nfor the estimation uncertainty. We develop an adaptive cruise controller that\nutilizes Stochastic Model Predictive Control (MPC) with chance constraints to\nprovide a probabilistic safety guarantee. We evaluate our ACC algorithm using a\nhigh-fidelity traffic simulator and a real-world traffic dataset and\ndemonstrate the ability of the proposed approach to effect speed tracking and\ncar following while maintaining a safe distance headway. The\nout-of-distribution scenarios are also examined.","PeriodicalId":501062,"journal":{"name":"arXiv - CS - Systems and Control","volume":"28 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Autonomous Driving With Perception Uncertainties: Deep-Ensemble Based Adaptive Cruise Control\",\"authors\":\"Xiao Li, H. Eric Tseng, Anouck Girard, Ilya Kolmanovsky\",\"doi\":\"arxiv-2403.15577\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Autonomous driving depends on perception systems to understand the\\nenvironment and to inform downstream decision-making. While advanced perception\\nsystems utilizing black-box Deep Neural Networks (DNNs) demonstrate human-like\\ncomprehension, their unpredictable behavior and lack of interpretability may\\nhinder their deployment in safety critical scenarios. In this paper, we develop\\nan Ensemble of DNN regressors (Deep Ensemble) that generates predictions with\\nquantification of prediction uncertainties. In the scenario of Adaptive Cruise\\nControl (ACC), we employ the Deep Ensemble to estimate distance headway to the\\nlead vehicle from RGB images and enable the downstream controller to account\\nfor the estimation uncertainty. We develop an adaptive cruise controller that\\nutilizes Stochastic Model Predictive Control (MPC) with chance constraints to\\nprovide a probabilistic safety guarantee. We evaluate our ACC algorithm using a\\nhigh-fidelity traffic simulator and a real-world traffic dataset and\\ndemonstrate the ability of the proposed approach to effect speed tracking and\\ncar following while maintaining a safe distance headway. The\\nout-of-distribution scenarios are also examined.\",\"PeriodicalId\":501062,\"journal\":{\"name\":\"arXiv - CS - Systems and Control\",\"volume\":\"28 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Systems and Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2403.15577\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Systems and Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2403.15577","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Autonomous Driving With Perception Uncertainties: Deep-Ensemble Based Adaptive Cruise Control
Autonomous driving depends on perception systems to understand the
environment and to inform downstream decision-making. While advanced perception
systems utilizing black-box Deep Neural Networks (DNNs) demonstrate human-like
comprehension, their unpredictable behavior and lack of interpretability may
hinder their deployment in safety critical scenarios. In this paper, we develop
an Ensemble of DNN regressors (Deep Ensemble) that generates predictions with
quantification of prediction uncertainties. In the scenario of Adaptive Cruise
Control (ACC), we employ the Deep Ensemble to estimate distance headway to the
lead vehicle from RGB images and enable the downstream controller to account
for the estimation uncertainty. We develop an adaptive cruise controller that
utilizes Stochastic Model Predictive Control (MPC) with chance constraints to
provide a probabilistic safety guarantee. We evaluate our ACC algorithm using a
high-fidelity traffic simulator and a real-world traffic dataset and
demonstrate the ability of the proposed approach to effect speed tracking and
car following while maintaining a safe distance headway. The
out-of-distribution scenarios are also examined.