2017 IEEE Intelligent Vehicles Symposium (IV)最新文献_第4页

Road grades and tire forces estimation using two-stage extended Kalman filter in a delayed interconnected cascade structure 在延迟互联级联结构中使用两阶段扩展卡尔曼滤波器估计道路等级和轮胎力

2017 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2017-06-11 DOI: 10.1109/IVS.2017.7995707

R. Cordeiro, A. M. Ribeiro, J. Azinheira, A. Victorino, Paulo A. V. Ferreira, E. Paiva, S. S. Bueno

引用次数: 8

Deep learning algorithm for autonomous driving using GoogLeNet

2017 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2017-06-11 DOI: 10.1109/IVS.2017.7995703

Mohammed Al-Qizwini, Iman Barjasteh, Hothaifa Al-Qassab, H. Radha

{"title":"Deep learning algorithm for autonomous driving using GoogLeNet","authors":"Mohammed Al-Qizwini, Iman Barjasteh, Hothaifa Al-Qassab, H. Radha","doi":"10.1109/IVS.2017.7995703","DOIUrl":"https://doi.org/10.1109/IVS.2017.7995703","url":null,"abstract":"In this paper, we consider the Direct Perception approach for autonomous driving. Previous efforts in this field focused more on feature extraction of the road markings and other vehicles in the scene rather than on the autonomous driving algorithm and its performance under realistic assumptions. Our main contribution in this paper is introducing a new, more robust, and more realistic Direct Perception framework and corresponding algorithm for autonomous driving. First, we compare the top 3 Convolutional Neural Networks (CNN) models in the feature extraction competitions and test their performance for autonomous driving. The experimental results showed that GoogLeNet performs the best in this application. Subsequently, we propose a deep learning based algorithm for autonomous driving, and we refer to our algorithm as GoogLenet for Autonomous Driving (GLAD). Unlike previous efforts, GLAD makes no unrealistic assumptions about the autonomous vehicle or its surroundings, and it uses only five affordance parameters to control the vehicle as compared to the 14 parameters used by prior efforts. Our simulation results show that the proposed GLAD algorithm outperforms previous Direct Perception algorithms both on empty roads and while driving with other surrounding vehicles.","PeriodicalId":143367,"journal":{"name":"2017 IEEE Intelligent Vehicles Symposium (IV)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127795024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 169

Traffic signal timing optimization in connected vehicles environment 车联网环境下交通信号配时优化

2017 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2017-06-11 DOI: 10.1109/IVS.2017.7995896

Wan Li, X. Ban

引用次数: 19

Mono-vision based moving object detection in complex traffic scenes 基于单视觉的复杂交通场景运动目标检测

2017 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2017-06-11 DOI: 10.1109/IVS.2017.7995857

V. Fremont, S. R. Florez, Bihao Wang

引用次数: 6

PCE-SLAM: A real-time simultaneous localization and mapping using LiDAR data PCE-SLAM:利用激光雷达数据进行实时同步定位和制图

2017 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2017-06-11 DOI: 10.1109/IVS.2017.7995960

Pragya Agrawal, Asif Iqbal, Brittney Russell, M. K. Hazrati, Vinay Kashyap, F. Akhbari

{"title":"PCE-SLAM: A real-time simultaneous localization and mapping using LiDAR data","authors":"Pragya Agrawal, Asif Iqbal, Brittney Russell, M. K. Hazrati, Vinay Kashyap, F. Akhbari","doi":"10.1109/IVS.2017.7995960","DOIUrl":"https://doi.org/10.1109/IVS.2017.7995960","url":null,"abstract":"This paper describes a real-time design, implementation and validation of a LiDAR-based Simultaneous Localization and Mapping solution for intelligent vehicles. We propose a two-step Sweep-to-Sweep Motion Estimation and Sweep-to-Map Registration framework that compensates for the distortion of the point cloud, estimates the vehicle's motion and generates a 3D map of the world. The rotating motion of LiDAR and the longitudinal motion of the vehicle together create an inherent distortion in relative motions observed in each scan per sweep. Hence applying the same translation and rotation values to the entire sweep does not guarantee the optimum estimation for LiDAR's relative motion from sweep to sweep. Therefore, the key idea in this paper is to obtain accurate localization of the vehicle by processing LiDAR sweep in a batch-wise fashion followed by 3D Map Registration using Iterative Closest Point (ICP). To reduce drift in localization ICP utilizes local map information in a radius of about 100m from the position of vehicle. Our main contribution is to introduce an innovative CPU-only pipeline for simultaneous localization and mapping that runs real-time on Intel architecture. We have tested our algorithm by processing every sweep from Velodyne VLP-16 LiDAR at about 50ms on vehicle moving at speeds up-to 25mph in urban roads and parking lot structures. Our algorithm has been evaluated on KITTI datasets for city and suburban roads with an average relative position error of around 1%.","PeriodicalId":143367,"journal":{"name":"2017 IEEE Intelligent Vehicles Symposium (IV)","volume":"293 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131301362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

Generalizable intention prediction of human drivers at intersections 人类驾驶员在十字路口的广义意图预测

2017 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2017-06-11 DOI: 10.1109/IVS.2017.7995948

Derek J. Phillips, T. Wheeler, Mykel J. Kochenderfer

引用次数: 129

Deep reinforcement learning-based vehicle energy efficiency autonomous learning system 基于深度强化学习的车辆能效自主学习系统

2017 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2017-06-11 DOI: 10.1109/IVS.2017.7995880

Xuewei Qi, Yadan Luo, Guoyuan Wu, K. Boriboonsomsin, M. Barth

引用次数: 49

Velocity and shape from tightly-coupled LiDAR and camera 从激光雷达和相机紧密耦合的速度和形状

2017 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2017-06-11 DOI: 10.1109/IVS.2017.7995699

Mohammad Hossein Daraei, Anh Vu, R. Manduchi

引用次数: 15

Incremental Cross-Modality deep learning for pedestrian recognition 基于增量跨模态深度学习的行人识别

2017 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2017-06-11 DOI: 10.1109/IVS.2017.7995771

D. Pop, A. Rogozan, F. Nashashibi, A. Bensrhair

{"title":"Incremental Cross-Modality deep learning for pedestrian recognition","authors":"D. Pop, A. Rogozan, F. Nashashibi, A. Bensrhair","doi":"10.1109/IVS.2017.7995771","DOIUrl":"https://doi.org/10.1109/IVS.2017.7995771","url":null,"abstract":"In spite of the large number of existing methods, pedestrian detection remains an open challenge. In recent years, deep learning classification methods combined with multi-modality images within different fusion schemes have achieved the best performance. It was proven that the late-fusion scheme outperforms both direct and intermediate integration of modalities for pedestrian recognition. Hence, in this paper, we focus on improving the late-fusion scheme for pedestrian classification on the Daimler stereo vision data set. Each image modality, Intensity, Depth and Flow, is classified by an independent Convolutional Neural Network (CNN), the outputs of which are then fused by a Multi-layer Perceptron (MLP) before the recognition decision. We propose different methods based on Cross-Modality deep learning of CNNs: (1) a correlated model where a unique CNN is trained with Intensity, Depth and Flow images for each frame, (2) an incremental model where a CNN is trained with the first modality images frames, then a second CNN, initialized by transfer learning on the first one is trained on the second modality images frames, and finally a third CNN initialized on the second one, is trained on the last modality images frames. The experiments show that the incremental cross-modality deep learning of CNNs improves classification performances not only for each independent modality classifier, but also for the multi-modality classifier based on late-fusion. Different learning algorithms are also investigated.","PeriodicalId":143367,"journal":{"name":"2017 IEEE Intelligent Vehicles Symposium (IV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115548803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 13

Automotive LIDAR objects detection and classification algorithm using the belief theory 基于信念理论的汽车激光雷达目标检测与分类算法

2017 IEEE Intelligent Vehicles Symposium (IV) Pub Date : 2017-06-11 DOI: 10.1109/IVS.2017.7995806

Valentin Magnier, D. Gruyer, J. Godelle

{"title":"Automotive LIDAR objects detection and classification algorithm using the belief theory","authors":"Valentin Magnier, D. Gruyer, J. Godelle","doi":"10.1109/IVS.2017.7995806","DOIUrl":"https://doi.org/10.1109/IVS.2017.7995806","url":null,"abstract":"In Autonomous driving applications, the LIDAR is becoming one of the key sensors for the perception of the environment. Indeed its work principle which is based on distance ranging using a laser beam scanning the environment allows highly accurate measurements. Among sensors commonly used in autonomous driving applications, which are cameras, RADARs and LIDARs, the LIDAR is the most suited to estimate the shape of objects. However, for the moment, LIDARs dedicated to pure automotive application have only up to four measurement layers (4 laser beams scanning the environment at different height). Hence objects detection algorithm have to rely on very few layers to detected and classify the type of objects perceived on the road scene, that makes them specific. In this paper we will present an Detection and Tracking of Moving Objects (DATMO) algorithm featuring an object-type classification based on the belief theory. This algorithm is specific to automotive application therefore, the classification of perceived vehicles is between bike, car and truck. At the end of this paper we will present an application of this algorithm in real-world context.","PeriodicalId":143367,"journal":{"name":"2017 IEEE Intelligent Vehicles Symposium (IV)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121508464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 33