A Survey of Intelligent Sensing Technologies in Autonomous Driving

doi:10.12142/ZTECOM.202103007

ZTE Communications ›› 2021, Vol. 19 ›› Issue (3): 56-63.DOI: 10.12142/ZTECOM.202103007

• Special Topic • Previous Articles Next Articles

A Survey of Intelligent Sensing Technologies in Autonomous Driving

SHAO Hong¹(), XIE Daxiong^1,², HUANG Yihua¹

^1.ZTE Corporation, Shenzhen 518057, China
^2.State Key Laboratory of Mobile Network and Mobile Multimedia, Shenzhen 518057, China

Received:2021-06-22 Online:2021-09-25 Published:2021-10-11
About author:SHAO Hong (shao.hong@zte.com.cn) received his M.S. degree from Harbin Institute of Technology, China and joined ZTE Corporation in 1994. He is currently the leader of the Innovation Team in the Corporation Development Department of ZTE Corporation. His research interests include deep learning, autonomous vehicles and robotics.|XIE Daxiong is currently the chairman of the board of supervisors of ZTE Corporation and the director of State Key Laboratory of Mobile Network and Mobile Multimedia Technology, China. He is a professorate senior engineer and a member of the Mobile and Satellite Expert Group of Communication Science and Technology Commission of Ministry of Industry and Information Technology of China. With ZTE Corporation, he led the successful research and development of CDMA, GoTa, WCDMA and other large-scale digital telecommunication systems.|HUANG Yihua received his M.S. degree from Huazhong University of Science and Technology, China. He is currently the manager of Corporation Development Department of ZTE Corporation. His research interests include new technology innovation, digital transformation and innovation strategy.

Abstract

Abstract:

Intelligent perception technology of sensors in autonomous vehicles has been deeply integrated with the algorithm of autonomous driving. This paper provides a survey of the impact of sensing technologies on autonomous driving, including the intelligent perception reshaping the car architecture from distributed to centralized processing and the common perception algorithms being explored in autonomous driving vehicles, such as visual perception, 3D perception and sensor fusion. The pure visual sensing solutions have shown the powerful capabilities in 3D perception leveraging the latest self-supervised learning progress, compared with light detection and ranging (LiDAR)-based solutions. Moreover, we discuss the trends on end-to-end policy decision models of high-level autonomous driving technologies.

Key words: autonomous vehicles, neuron network, automotive electronics, sensor fusion

SHAO Hong, XIE Daxiong, HUANG Yihua. A Survey of Intelligent Sensing Technologies in Autonomous Driving[J]. ZTE Communications, 2021, 19(3): 56-63.

Figures/Tables 10

Figure 1 Domain and zonal electrical and electronic (E/E) architecture

Figure 2 Basic deep learning model

Figure 3 A practiced mask region based convolutional neural network (Mask R-CNN)

Table 1 YOLO3D network architecture[5]

Layer	Filter	Size	Feature Maps
Conv2d	32	(3, 3)	608×608×2
Maxpooling		(size 2, stride 2)
Conv2d	64	(3, 3)
Maxpooling		(size 2, stride 2)
Conv2d	128	(3, 3)
Conv2d	64	(3, 3)
Conv2d	128	(3, 3)
Maxpooling		(size 2, stride 1)
Conv2d	256	(3, 3)
Conv2d	128	(3, 3)
Conv2d	256	(3, 3)
Maxpooling		(size 2, stride 2)
Conv2d	512	(3, 3)
Conv2d	256	(1,1)
Conv2d	512	(3, 3)
Conv2d	256	(1,1)
Conv2d	512	(3, 3)
Maxpooling		(size 2, stride 2)
Conv2d	1 024	(3, 3)
Conv2d	512	(1, 1)
Conv2d	1 024	(3, 3)
Conv2d	512	(1, 1)
Conv2d	1 024	(3, 3)
Conv2d	1 024	(3, 3)
Conv2d	1 024	(3, 3)
Conv2d	1 024	(3, 3)
Conv2d	1 024	(1,1)	38×38×33
Reshape			38×38×3×11

Figure 4 YOLO3D grid cells, assuming one layer high[5]

Figure 5 Multi-view 3D object detection network (MV3D)[6]

Figure 6 Image-based 3D object detection[7]

Figure 7 A self-supervised learning example with the use of stereo video sequences[8]

Figure 8 A self-supervised learning framework[8]

Figure 9 End-to-end autonomous driving decision-making network

References 12

1	BEBEL J C, HOWARD N, PATEL T. An autonomous system used in the darpa grand challenge [C]//7th International IEEE Conference on Intelligent Transportation Systems. Washington, USA: IEEE, 2004: 487–490. DOI: 10.1109/ITSC.2004.1398948 DOI
2	MARTI E, DE MIGUEL M A, GARCIA F, et al. A review of sensor technologies for perception in automated driving [J]. IEEE intelligent transportation systems magazine, 2019, 11: 94–108. DOI: 10.1109/MITS.2019.2907630 DOI
3	HE K M, GKIOXARI G, DOLLÁR P, et al. Mask R‑CNN [EB/OL]. (2018‑01‑24)[2021‑04‑28].
4	REDMON J, FARHADI A. YOLO9000: better, faster, stronger [EB/OL]. (2016‑12‑25)[2021‑04‑28].
5	ALI W, ABDELKARIM S, ZAHRAN M, et al. YOLO3D: end‑to‑end real‑time 3D oriented object bounding box detection from LiDAR point cloud [EB/OL]. (2018‑08‑07)[2021‑04‑28].
6	CHEN X Z, MA H M, WAN J, et al. Multi‑view 3D object detection network for autonomous driving [C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE, 2017. DOI: 10.1109/CVPR.2017.691 DOI
7	WANG Y, CHAO W‑L, GARG D, et al. Pseudo‑LiDAR from visual depth estimation: bridging the gap in 3D object detection for autonomous driving [EB/OL]. (2020‑02‑22)[2021‑04‑28].
8	ZHAN H Y, GARG R, WEERASEKERA C S, et al. Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction [EB/OL]. (2020‑02‑22)[2021‑04‑28].
9	CUI H, RADOSAVLJEVIC V, F‑CCHOU, et al. Multimodal trajectory predictions for autonomous driving using deep convolutional networks [EB/OL]. (2019‑03‑01)[2021‑04‑28].
10	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [EB/OL]. (2015‑12‑10)[2021‑04‑28].
11	SCHRITTWIESER J, ANTONOGLOU I, HUBERT T, et al. Mastering Atari, Go, chess and shogi by planning with a learned model [J]. Nature, 2020, 588: 604–609. DOI: 10.1038/s41586-020-03051-4 DOI
12	HENAFF M, CANZIANI A, LECUN Y, Model‑predictive policy learning with uncertainty regularization for driving in dense traffic [EB/OL]. (2019‑01‑08)[2021‑04‑28].

A Survey of Intelligent Sensing Technologies in Autonomous Driving

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 12

Related Articles 1

Recommended Articles

Metrics