Introspection of DNN-Based Perception Functions in Automated Driving Systems: State-of-the-Art and Open Research Challenges

被引:2
作者
Yatbaz, Hakan Yekta [1 ]
Dianati, Mehrdad [1 ,2 ]
Woodman, Roger [1 ]
机构
[1] Univ Warwick, WMG, Coventry CV4 7AL, England
[2] Queens Univ Belfast, Sch Elect Elect Engn & Comp Sci EEECS, Belfast BT7 1NN, North Ireland
关键词
Introspection; automated driving systems; perception errors; safety; deep learning; SEMANTIC SEGMENTATION; CLASSIFICATION; PERFORMANCE; FAILURES; DATASETS; VISION; SAFE;
D O I
10.1109/TITS.2023.3315070
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Automated driving systems (ADSs) aim to improve the safety, efficiency and comfort of future vehicles. To achieve this, ADSs use sensors to collect raw data from their environment. This data is then processed by a perception subsystem to create semantic knowledge of the world around the vehicle. State-of-the-art ADSs' perception systems often use deep neural networks for object detection and classification, thanks to their superior performance compared to classical computer vision techniques. However, deep neural network-based perception systems are susceptible to errors, e.g., failing to correctly detect other road users such as pedestrians. For a safety-critical system such as ADS, these errors can result in accidents leading to injury or even death to occupants and road users. Introspection of perception systems in ADS refers to detecting such perception errors to avoid system failures and accidents. Such safety mechanisms are crucial for ensuring the trustworthiness of ADSs. Motivated by the growing importance of the subject in the field of autonomous and automated vehicles, this paper provides a comprehensive review of the techniques that have been proposed in the literature as potential solutions for the introspection of perception errors in ADSs. We classify such techniques based on their main focus, e.g., on object detection, classification and localisation problems. Furthermore, this paper discusses the pros and cons of existing methods while identifying the research gaps and potential future research directions.
引用
收藏
页码:1112 / 1130
页数:19
相关论文
共 131 条
  • [21] Ghost Target Detection in 3D Radar Data using Point Cloud based Deep Neural Network
    Chamseddine, Mahdi
    Rambach, Jason
    Stricker, Didier
    Wasenmueller, Oliver
    [J]. 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 10398 - 10403
  • [22] Chan R., 2021, P NEUR INF PROC SYST, V1
  • [23] Entropy Maximization and Meta Classification for Out-of-Distribution Detection in Semantic Segmentation
    Chan, Robin
    Rottmann, Matthias
    Gottschalk, Hanno
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 5108 - 5117
  • [24] Che T, 2021, AAAI CONF ARTIF INTE, V35, P7002
  • [25] Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
    Chen, Liang-Chieh
    Zhu, Yukun
    Papandreou, George
    Schroff, Florian
    Adam, Hartwig
    [J]. COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 : 833 - 851
  • [26] XGBoost: A Scalable Tree Boosting System
    Chen, Tianqi
    Guestrin, Carlos
    [J]. KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, : 785 - 794
  • [27] Cheng CH, 2019, DES AUT TEST EUROPE, P300, DOI [10.23919/date.2019.8714971, 10.23919/DATE.2019.8714971]
  • [28] Corbiere C., 2019, P ADV NEUR INF PROC, P1
  • [29] Pixel-wise Anomaly Detection in Complex Driving Scenes
    Di Biase, Giancarlo
    Blum, Hermann
    Siegwart, Roland
    Cadena, Cesar
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 16913 - 16922
  • [30] Dosovitskiy A., 2021, ICLR