M. Abou-Hussein, Stefan H. Müller-Weinfurtner, J. Boedecker
{"title":"端到端网络中的多模态时空信息用于汽车转向预测","authors":"M. Abou-Hussein, Stefan H. Müller-Weinfurtner, J. Boedecker","doi":"10.1109/ICRA.2019.8794410","DOIUrl":null,"url":null,"abstract":"We study the end-to-end steering problem using visual input data from an onboard vehicle camera. An empirical comparison between spatial, spatio-temporal and multimodal models is performed assessing each concept’s performance from two points of evaluation. First, how close the model is in predicting and imitating a real-life driver’s behavior, second, the smoothness of the predicted steering command. The latter is a newly proposed metric. Building on our results, we propose a new recurrent multimodal model. The suggested model has been tested on a custom dataset recorded by BMW, as well as the public dataset provided by Udacity. Results show that it outperforms previously released scores. Further, a steering correction concept from off-lane driving through the inclusion of correction frames is presented. We show that our suggestion leads to promising results empirically.","PeriodicalId":6730,"journal":{"name":"2019 International Conference on Robotics and Automation (ICRA)","volume":"16 1","pages":"8641-8647"},"PeriodicalIF":0.0000,"publicationDate":"2019-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Multimodal Spatio-Temporal Information in End-to-End Networks for Automotive Steering Prediction\",\"authors\":\"M. Abou-Hussein, Stefan H. Müller-Weinfurtner, J. Boedecker\",\"doi\":\"10.1109/ICRA.2019.8794410\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We study the end-to-end steering problem using visual input data from an onboard vehicle camera. An empirical comparison between spatial, spatio-temporal and multimodal models is performed assessing each concept’s performance from two points of evaluation. First, how close the model is in predicting and imitating a real-life driver’s behavior, second, the smoothness of the predicted steering command. The latter is a newly proposed metric. Building on our results, we propose a new recurrent multimodal model. The suggested model has been tested on a custom dataset recorded by BMW, as well as the public dataset provided by Udacity. Results show that it outperforms previously released scores. Further, a steering correction concept from off-lane driving through the inclusion of correction frames is presented. We show that our suggestion leads to promising results empirically.\",\"PeriodicalId\":6730,\"journal\":{\"name\":\"2019 International Conference on Robotics and Automation (ICRA)\",\"volume\":\"16 1\",\"pages\":\"8641-8647\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-05-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 International Conference on Robotics and Automation (ICRA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICRA.2019.8794410\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 International Conference on Robotics and Automation (ICRA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICRA.2019.8794410","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Multimodal Spatio-Temporal Information in End-to-End Networks for Automotive Steering Prediction
We study the end-to-end steering problem using visual input data from an onboard vehicle camera. An empirical comparison between spatial, spatio-temporal and multimodal models is performed assessing each concept’s performance from two points of evaluation. First, how close the model is in predicting and imitating a real-life driver’s behavior, second, the smoothness of the predicted steering command. The latter is a newly proposed metric. Building on our results, we propose a new recurrent multimodal model. The suggested model has been tested on a custom dataset recorded by BMW, as well as the public dataset provided by Udacity. Results show that it outperforms previously released scores. Further, a steering correction concept from off-lane driving through the inclusion of correction frames is presented. We show that our suggestion leads to promising results empirically.