Explainability of Deep Vision-Based Autonomous Driving Systems: Review and Challenges View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2022-08-07

AUTHORS

Éloi Zablocki, Hédi Ben-Younes, Patrick Pérez, Matthieu Cord

ABSTRACT

This survey reviews explainability methods for vision-based self-driving systems trained with behavior cloning. The concept of explainability has several facets and the need for explainability is strong in driving, a safety-critical application. Gathering contributions from several research fields, namely computer vision, deep learning, autonomous driving, explainable AI (X-AI), this survey tackles several points. First, it discusses definitions, context, and motivation for gaining more interpretability and explainability from self-driving systems, as well as the challenges that are specific to this application. Second, methods providing explanations to a black-box self-driving system in a post-hoc fashion are comprehensively organized and detailed. Third, approaches from the literature that aim at building more interpretable self-driving systems by design are presented and discussed in detail. Finally, remaining open-challenges and potential future research directions are identified and examined. More... »

PAGES

2425-2452

References to SciGraph publications

  • 2020-08-28. Towards Photo-Realistic Facial Expression Manipulation in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2018-10-06. Learning to Anonymize Faces for Privacy Preserving Action Detection in COMPUTER VISION – ECCV 2018
  • 2017-09-13. A Deeper Look at Dataset Bias in DOMAIN ADAPTATION IN COMPUTER VISION APPLICATIONS
  • 2021-09-10. Crowdsourcing Evaluation of Saliency-Based XAI Methods in MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES. APPLIED DATA SCIENCE TRACK
  • 2014-04-30. Why did my car just do that? Explaining semi-autonomous driving actions to improve driver understanding, trust, and performance in INTERNATIONAL JOURNAL ON INTERACTIVE DESIGN AND MANUFACTURING (IJIDEM)
  • 2018-01-28. Visual interpretability for deep learning: a survey in FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING
  • 2019-10-11. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2016-11-08. VQA: Visual Question Answering in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2020-02-24. Layout2image: Image Generation from Layout in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2020-11-07. Optical Flow Distillation: Towards Efficient and Stable Video Style Transfer in COMPUTER VISION – ECCV 2020
  • 2014. Visualizing and Understanding Convolutional Networks in COMPUTER VISION – ECCV 2014
  • 2018-10-09. Textual Explanations for Self-Driving Vehicles in COMPUTER VISION – ECCV 2018
  • 2020-11-09. Traffic Accident Benchmark for Causality Recognition in COMPUTER VISION – ECCV 2020
  • 2018-10-06. VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions in COMPUTER VISION – ECCV 2018
  • 2018-03-07. Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2020-10-07. Flow-edge Guided Video Completion in COMPUTER VISION – ECCV 2020
  • 2015-05-27. Deep learning in NATURE
  • 1985. A Critical View of Driver Behavior Models: What Do We Know, What Should We Do? in HUMAN BEHAVIOR AND TRAFFIC SAFETY
  • 2018-10-06. Recycle-GAN: Unsupervised Video Retargeting in COMPUTER VISION – ECCV 2018
  • 2007. Stanley: The Robot That Won the DARPA Grand Challenge in THE 2005 DARPA GRAND CHALLENGE
  • 2018-10-06. Image Inpainting for Irregular Holes Using Partial Convolutions in COMPUTER VISION – ECCV 2018
  • 2018-10-09. Grounding Visual Explanations in COMPUTER VISION – ECCV 2018
  • 2016-09-21. DeepRED – Rule Extraction from Deep Neural Networks in DISCOVERY SCIENCE
  • 2017-03-12. Anticipating Accidents in Dashcam Videos in COMPUTER VISION – ACCV 2016
  • 2017-09-11. Psychological roadblocks to the adoption of self-driving vehicles in NATURE HUMAN BEHAVIOUR
  • 2020-12-04. Trajectron++: Dynamically-Feasible Trajectory Forecasting with Heterogeneous Data in COMPUTER VISION – ECCV 2020
  • 2017-08-29. Ask Your Neurons: A Deep Learning Approach to Visual Question Answering in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2016-09-17. Generating Visual Explanations in COMPUTER VISION – ECCV 2016
  • 2016-09-16. Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering in COMPUTER VISION – ECCV 2016
  • 2020-11-03. Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations in COMPUTER VISION – ECCV 2020
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s11263-022-01657-x

    DOI

    http://dx.doi.org/10.1007/s11263-022-01657-x

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1150059587


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Valeo.ai, Paris, France", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Valeo.ai, Paris, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zablocki", 
            "givenName": "\u00c9loi", 
            "id": "sg:person.014443655745.21", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014443655745.21"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Valeo.ai, Paris, France", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Valeo.ai, Paris, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Ben-Younes", 
            "givenName": "H\u00e9di", 
            "id": "sg:person.014623625220.68", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014623625220.68"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Valeo.ai, Paris, France", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "Valeo.ai, Paris, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "P\u00e9rez", 
            "givenName": "Patrick", 
            "id": "sg:person.016077665647.41", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016077665647.41"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Sorbonne Universit\u00e9, Paris, France", 
              "id": "http://www.grid.ac/institutes/grid.462844.8", 
              "name": [
                "Valeo.ai, Paris, France", 
                "Sorbonne Universit\u00e9, Paris, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Cord", 
            "givenName": "Matthieu", 
            "id": "sg:person.015061626535.00", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015061626535.00"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s11263-018-1070-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101368668", 
              "https://doi.org/10.1007/s11263-018-1070-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-019-01228-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1121715269", 
              "https://doi.org/10.1007/s11263-019-01228-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01228-1_8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107463289", 
              "https://doi.org/10.1007/978-3-030-01228-1_8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-020-01361-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1130416673", 
              "https://doi.org/10.1007/s11263-020-01361-8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-73429-1_1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1005100400", 
              "https://doi.org/10.1007/978-3-540-73429-1_1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-017-1038-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091379710", 
              "https://doi.org/10.1007/s11263-017-1038-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-58610-2_42", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1131472273", 
              "https://doi.org/10.1007/978-3-030-58610-2_42"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01252-6_6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107454764", 
              "https://doi.org/10.1007/978-3-030-01252-6_6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1631/fitee.1700808", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1101554124", 
              "https://doi.org/10.1631/fitee.1700808"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/s41562-017-0202-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091539616", 
              "https://doi.org/10.1038/s41562-017-0202-6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s12008-014-0227-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1011424006", 
              "https://doi.org/10.1007/s12008-014-0227-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-58539-6_37", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1132402600", 
              "https://doi.org/10.1007/978-3-030-58539-6_37"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01234-2_34", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107454598", 
              "https://doi.org/10.1007/978-3-030-01234-2_34"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01216-8_17", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107502565", 
              "https://doi.org/10.1007/978-3-030-01216-8_17"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01246-5_38", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107454651", 
              "https://doi.org/10.1007/978-3-030-01246-5_38"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-86517-7_27", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1141001967", 
              "https://doi.org/10.1007/978-3-030-86517-7_27"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1038/nature14539", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1010020120", 
              "https://doi.org/10.1038/nature14539"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-46307-0_29", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1084847747", 
              "https://doi.org/10.1007/978-3-319-46307-0_29"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-020-01300-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1125104704", 
              "https://doi.org/10.1007/s11263-020-01300-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-46493-0_1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047909927", 
              "https://doi.org/10.1007/978-3-319-46493-0_1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-54190-7_9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1084701070", 
              "https://doi.org/10.1007/978-3-319-54190-7_9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-58571-6_32", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1132444853", 
              "https://doi.org/10.1007/978-3-030-58571-6_32"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4613-2173-6_19", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1030596974", 
              "https://doi.org/10.1007/978-1-4613-2173-6_19"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01216-8_35", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107502585", 
              "https://doi.org/10.1007/978-3-030-01216-8_35"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-10590-1_53", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1032233097", 
              "https://doi.org/10.1007/978-3-319-10590-1_53"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-58347-1_2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091585520", 
              "https://doi.org/10.1007/978-3-319-58347-1_2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-58592-1_25", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1132262385", 
              "https://doi.org/10.1007/978-3-030-58592-1_25"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-46478-7_28", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019481205", 
              "https://doi.org/10.1007/978-3-319-46478-7_28"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-58523-5_40", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1133092198", 
              "https://doi.org/10.1007/978-3-030-58523-5_40"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-016-0966-6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020955997", 
              "https://doi.org/10.1007/s11263-016-0966-6"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2022-08-07", 
        "datePublishedReg": "2022-08-07", 
        "description": "This survey reviews explainability methods for vision-based self-driving systems trained with behavior cloning. The concept of explainability has several facets and the need for explainability is strong in driving, a safety-critical application. Gathering contributions from several research fields, namely computer vision, deep learning, autonomous driving, explainable AI (X-AI), this survey tackles several points. First, it discusses definitions, context, and motivation for gaining more interpretability and explainability from self-driving systems, as well as the challenges that are specific to this application. Second, methods providing explanations to a black-box self-driving system in a post-hoc fashion are comprehensively organized and detailed. Third, approaches from the literature that aim at building more interpretable self-driving systems by design are presented and discussed in detail. Finally, remaining open-challenges and potential future research directions are identified and examined.", 
        "genre": "article", 
        "id": "sg:pub.10.1007/s11263-022-01657-x", 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1032807", 
            "issn": [
              "0920-5691", 
              "1573-1405"
            ], 
            "name": "International Journal of Computer Vision", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "10", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "130"
          }
        ], 
        "keywords": [
          "self-driving systems", 
          "concept of explainability", 
          "autonomous driving systems", 
          "safety-critical applications", 
          "computer vision", 
          "deep learning", 
          "Explainable AI", 
          "explainability methods", 
          "potential future research directions", 
          "autonomous driving", 
          "behavior cloning", 
          "more interpretability", 
          "explainability", 
          "driving system", 
          "deep vision", 
          "future research directions", 
          "research directions", 
          "research field", 
          "vision", 
          "driving", 
          "system", 
          "interpretability", 
          "AI", 
          "applications", 
          "learning", 
          "challenges", 
          "method", 
          "concept", 
          "design", 
          "context", 
          "need", 
          "definition", 
          "fashion", 
          "detail", 
          "motivation", 
          "point", 
          "field", 
          "direction", 
          "survey", 
          "contribution", 
          "facets", 
          "literature", 
          "review", 
          "explanation", 
          "cloning"
        ], 
        "name": "Explainability of Deep Vision-Based Autonomous Driving Systems: Review and Challenges", 
        "pagination": "2425-2452", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1150059587"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s11263-022-01657-x"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s11263-022-01657-x", 
          "https://app.dimensions.ai/details/publication/pub.1150059587"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-12-01T06:45", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/article/article_954.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1007/s11263-022-01657-x"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s11263-022-01657-x'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s11263-022-01657-x'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11263-022-01657-x'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11263-022-01657-x'


     

    This table displays all metadata directly associated to this object as RDF triples.

    247 TRIPLES      21 PREDICATES      99 URIs      61 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s11263-022-01657-x schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nd3605363c53a4f25beaa1d348d48f416
    4 schema:citation sg:pub.10.1007/978-1-4613-2173-6_19
    5 sg:pub.10.1007/978-3-030-01216-8_17
    6 sg:pub.10.1007/978-3-030-01216-8_35
    7 sg:pub.10.1007/978-3-030-01228-1_8
    8 sg:pub.10.1007/978-3-030-01234-2_34
    9 sg:pub.10.1007/978-3-030-01246-5_38
    10 sg:pub.10.1007/978-3-030-01252-6_6
    11 sg:pub.10.1007/978-3-030-58523-5_40
    12 sg:pub.10.1007/978-3-030-58539-6_37
    13 sg:pub.10.1007/978-3-030-58571-6_32
    14 sg:pub.10.1007/978-3-030-58592-1_25
    15 sg:pub.10.1007/978-3-030-58610-2_42
    16 sg:pub.10.1007/978-3-030-86517-7_27
    17 sg:pub.10.1007/978-3-319-10590-1_53
    18 sg:pub.10.1007/978-3-319-46307-0_29
    19 sg:pub.10.1007/978-3-319-46478-7_28
    20 sg:pub.10.1007/978-3-319-46493-0_1
    21 sg:pub.10.1007/978-3-319-54190-7_9
    22 sg:pub.10.1007/978-3-319-58347-1_2
    23 sg:pub.10.1007/978-3-540-73429-1_1
    24 sg:pub.10.1007/s11263-016-0966-6
    25 sg:pub.10.1007/s11263-017-1038-2
    26 sg:pub.10.1007/s11263-018-1070-x
    27 sg:pub.10.1007/s11263-019-01228-7
    28 sg:pub.10.1007/s11263-020-01300-7
    29 sg:pub.10.1007/s11263-020-01361-8
    30 sg:pub.10.1007/s12008-014-0227-2
    31 sg:pub.10.1038/nature14539
    32 sg:pub.10.1038/s41562-017-0202-6
    33 sg:pub.10.1631/fitee.1700808
    34 schema:datePublished 2022-08-07
    35 schema:datePublishedReg 2022-08-07
    36 schema:description This survey reviews explainability methods for vision-based self-driving systems trained with behavior cloning. The concept of explainability has several facets and the need for explainability is strong in driving, a safety-critical application. Gathering contributions from several research fields, namely computer vision, deep learning, autonomous driving, explainable AI (X-AI), this survey tackles several points. First, it discusses definitions, context, and motivation for gaining more interpretability and explainability from self-driving systems, as well as the challenges that are specific to this application. Second, methods providing explanations to a black-box self-driving system in a post-hoc fashion are comprehensively organized and detailed. Third, approaches from the literature that aim at building more interpretable self-driving systems by design are presented and discussed in detail. Finally, remaining open-challenges and potential future research directions are identified and examined.
    37 schema:genre article
    38 schema:isAccessibleForFree true
    39 schema:isPartOf N2773ccc3622e4c23b262b4edcedaf5fd
    40 Nf39e0d1ea539411fa8cd84a60ca4cef5
    41 sg:journal.1032807
    42 schema:keywords AI
    43 Explainable AI
    44 applications
    45 autonomous driving
    46 autonomous driving systems
    47 behavior cloning
    48 challenges
    49 cloning
    50 computer vision
    51 concept
    52 concept of explainability
    53 context
    54 contribution
    55 deep learning
    56 deep vision
    57 definition
    58 design
    59 detail
    60 direction
    61 driving
    62 driving system
    63 explainability
    64 explainability methods
    65 explanation
    66 facets
    67 fashion
    68 field
    69 future research directions
    70 interpretability
    71 learning
    72 literature
    73 method
    74 more interpretability
    75 motivation
    76 need
    77 point
    78 potential future research directions
    79 research directions
    80 research field
    81 review
    82 safety-critical applications
    83 self-driving systems
    84 survey
    85 system
    86 vision
    87 schema:name Explainability of Deep Vision-Based Autonomous Driving Systems: Review and Challenges
    88 schema:pagination 2425-2452
    89 schema:productId N0e8f4e96c138474883b779e74a8e09b1
    90 Nd6500d6b49074bfaacb5f23092182d35
    91 schema:sameAs https://app.dimensions.ai/details/publication/pub.1150059587
    92 https://doi.org/10.1007/s11263-022-01657-x
    93 schema:sdDatePublished 2022-12-01T06:45
    94 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    95 schema:sdPublisher N519dcf8afafc40a18941c192292dd6a1
    96 schema:url https://doi.org/10.1007/s11263-022-01657-x
    97 sgo:license sg:explorer/license/
    98 sgo:sdDataset articles
    99 rdf:type schema:ScholarlyArticle
    100 N0e8f4e96c138474883b779e74a8e09b1 schema:name dimensions_id
    101 schema:value pub.1150059587
    102 rdf:type schema:PropertyValue
    103 N2773ccc3622e4c23b262b4edcedaf5fd schema:volumeNumber 130
    104 rdf:type schema:PublicationVolume
    105 N519dcf8afafc40a18941c192292dd6a1 schema:name Springer Nature - SN SciGraph project
    106 rdf:type schema:Organization
    107 N81779f1a08074fe1aa916903c963b5e7 rdf:first sg:person.016077665647.41
    108 rdf:rest Na130980c17d740b1b2ad57ff9e25d20b
    109 Na130980c17d740b1b2ad57ff9e25d20b rdf:first sg:person.015061626535.00
    110 rdf:rest rdf:nil
    111 Na357ce8b256240b58fa8152039a37ed3 rdf:first sg:person.014623625220.68
    112 rdf:rest N81779f1a08074fe1aa916903c963b5e7
    113 Nd3605363c53a4f25beaa1d348d48f416 rdf:first sg:person.014443655745.21
    114 rdf:rest Na357ce8b256240b58fa8152039a37ed3
    115 Nd6500d6b49074bfaacb5f23092182d35 schema:name doi
    116 schema:value 10.1007/s11263-022-01657-x
    117 rdf:type schema:PropertyValue
    118 Nf39e0d1ea539411fa8cd84a60ca4cef5 schema:issueNumber 10
    119 rdf:type schema:PublicationIssue
    120 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    121 schema:name Information and Computing Sciences
    122 rdf:type schema:DefinedTerm
    123 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    124 schema:name Artificial Intelligence and Image Processing
    125 rdf:type schema:DefinedTerm
    126 sg:journal.1032807 schema:issn 0920-5691
    127 1573-1405
    128 schema:name International Journal of Computer Vision
    129 schema:publisher Springer Nature
    130 rdf:type schema:Periodical
    131 sg:person.014443655745.21 schema:affiliation grid-institutes:None
    132 schema:familyName Zablocki
    133 schema:givenName Éloi
    134 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014443655745.21
    135 rdf:type schema:Person
    136 sg:person.014623625220.68 schema:affiliation grid-institutes:None
    137 schema:familyName Ben-Younes
    138 schema:givenName Hédi
    139 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014623625220.68
    140 rdf:type schema:Person
    141 sg:person.015061626535.00 schema:affiliation grid-institutes:grid.462844.8
    142 schema:familyName Cord
    143 schema:givenName Matthieu
    144 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015061626535.00
    145 rdf:type schema:Person
    146 sg:person.016077665647.41 schema:affiliation grid-institutes:None
    147 schema:familyName Pérez
    148 schema:givenName Patrick
    149 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016077665647.41
    150 rdf:type schema:Person
    151 sg:pub.10.1007/978-1-4613-2173-6_19 schema:sameAs https://app.dimensions.ai/details/publication/pub.1030596974
    152 https://doi.org/10.1007/978-1-4613-2173-6_19
    153 rdf:type schema:CreativeWork
    154 sg:pub.10.1007/978-3-030-01216-8_17 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107502565
    155 https://doi.org/10.1007/978-3-030-01216-8_17
    156 rdf:type schema:CreativeWork
    157 sg:pub.10.1007/978-3-030-01216-8_35 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107502585
    158 https://doi.org/10.1007/978-3-030-01216-8_35
    159 rdf:type schema:CreativeWork
    160 sg:pub.10.1007/978-3-030-01228-1_8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107463289
    161 https://doi.org/10.1007/978-3-030-01228-1_8
    162 rdf:type schema:CreativeWork
    163 sg:pub.10.1007/978-3-030-01234-2_34 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107454598
    164 https://doi.org/10.1007/978-3-030-01234-2_34
    165 rdf:type schema:CreativeWork
    166 sg:pub.10.1007/978-3-030-01246-5_38 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107454651
    167 https://doi.org/10.1007/978-3-030-01246-5_38
    168 rdf:type schema:CreativeWork
    169 sg:pub.10.1007/978-3-030-01252-6_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107454764
    170 https://doi.org/10.1007/978-3-030-01252-6_6
    171 rdf:type schema:CreativeWork
    172 sg:pub.10.1007/978-3-030-58523-5_40 schema:sameAs https://app.dimensions.ai/details/publication/pub.1133092198
    173 https://doi.org/10.1007/978-3-030-58523-5_40
    174 rdf:type schema:CreativeWork
    175 sg:pub.10.1007/978-3-030-58539-6_37 schema:sameAs https://app.dimensions.ai/details/publication/pub.1132402600
    176 https://doi.org/10.1007/978-3-030-58539-6_37
    177 rdf:type schema:CreativeWork
    178 sg:pub.10.1007/978-3-030-58571-6_32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1132444853
    179 https://doi.org/10.1007/978-3-030-58571-6_32
    180 rdf:type schema:CreativeWork
    181 sg:pub.10.1007/978-3-030-58592-1_25 schema:sameAs https://app.dimensions.ai/details/publication/pub.1132262385
    182 https://doi.org/10.1007/978-3-030-58592-1_25
    183 rdf:type schema:CreativeWork
    184 sg:pub.10.1007/978-3-030-58610-2_42 schema:sameAs https://app.dimensions.ai/details/publication/pub.1131472273
    185 https://doi.org/10.1007/978-3-030-58610-2_42
    186 rdf:type schema:CreativeWork
    187 sg:pub.10.1007/978-3-030-86517-7_27 schema:sameAs https://app.dimensions.ai/details/publication/pub.1141001967
    188 https://doi.org/10.1007/978-3-030-86517-7_27
    189 rdf:type schema:CreativeWork
    190 sg:pub.10.1007/978-3-319-10590-1_53 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032233097
    191 https://doi.org/10.1007/978-3-319-10590-1_53
    192 rdf:type schema:CreativeWork
    193 sg:pub.10.1007/978-3-319-46307-0_29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084847747
    194 https://doi.org/10.1007/978-3-319-46307-0_29
    195 rdf:type schema:CreativeWork
    196 sg:pub.10.1007/978-3-319-46478-7_28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019481205
    197 https://doi.org/10.1007/978-3-319-46478-7_28
    198 rdf:type schema:CreativeWork
    199 sg:pub.10.1007/978-3-319-46493-0_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047909927
    200 https://doi.org/10.1007/978-3-319-46493-0_1
    201 rdf:type schema:CreativeWork
    202 sg:pub.10.1007/978-3-319-54190-7_9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084701070
    203 https://doi.org/10.1007/978-3-319-54190-7_9
    204 rdf:type schema:CreativeWork
    205 sg:pub.10.1007/978-3-319-58347-1_2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091585520
    206 https://doi.org/10.1007/978-3-319-58347-1_2
    207 rdf:type schema:CreativeWork
    208 sg:pub.10.1007/978-3-540-73429-1_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005100400
    209 https://doi.org/10.1007/978-3-540-73429-1_1
    210 rdf:type schema:CreativeWork
    211 sg:pub.10.1007/s11263-016-0966-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020955997
    212 https://doi.org/10.1007/s11263-016-0966-6
    213 rdf:type schema:CreativeWork
    214 sg:pub.10.1007/s11263-017-1038-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091379710
    215 https://doi.org/10.1007/s11263-017-1038-2
    216 rdf:type schema:CreativeWork
    217 sg:pub.10.1007/s11263-018-1070-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1101368668
    218 https://doi.org/10.1007/s11263-018-1070-x
    219 rdf:type schema:CreativeWork
    220 sg:pub.10.1007/s11263-019-01228-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1121715269
    221 https://doi.org/10.1007/s11263-019-01228-7
    222 rdf:type schema:CreativeWork
    223 sg:pub.10.1007/s11263-020-01300-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1125104704
    224 https://doi.org/10.1007/s11263-020-01300-7
    225 rdf:type schema:CreativeWork
    226 sg:pub.10.1007/s11263-020-01361-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1130416673
    227 https://doi.org/10.1007/s11263-020-01361-8
    228 rdf:type schema:CreativeWork
    229 sg:pub.10.1007/s12008-014-0227-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1011424006
    230 https://doi.org/10.1007/s12008-014-0227-2
    231 rdf:type schema:CreativeWork
    232 sg:pub.10.1038/nature14539 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010020120
    233 https://doi.org/10.1038/nature14539
    234 rdf:type schema:CreativeWork
    235 sg:pub.10.1038/s41562-017-0202-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091539616
    236 https://doi.org/10.1038/s41562-017-0202-6
    237 rdf:type schema:CreativeWork
    238 sg:pub.10.1631/fitee.1700808 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101554124
    239 https://doi.org/10.1631/fitee.1700808
    240 rdf:type schema:CreativeWork
    241 grid-institutes:None schema:alternateName Valeo.ai, Paris, France
    242 schema:name Valeo.ai, Paris, France
    243 rdf:type schema:Organization
    244 grid-institutes:grid.462844.8 schema:alternateName Sorbonne Université, Paris, France
    245 schema:name Sorbonne Université, Paris, France
    246 Valeo.ai, Paris, France
    247 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...