Towards Explainable and Trustworthy Autonomous Physical Systems

被引:1
|
作者
Omeiza, Daniel [1 ]
Anjomshoae, Sule [2 ]
Kollnig, Konrad [1 ]
Camburu, Oana-Maria [1 ,3 ]
Framling, Kary [2 ]
Kunze, Lars [4 ]
机构
[1] Univ Oxford, Oxford, England
[2] Umea Univ, Umea, Sweden
[3] Alan Turing Inst, London, England
[4] Univ Oxford, Oxford Robot Inst, Oxford, England
基金
英国工程与自然科学研究理事会;
关键词
Explainability; trust; collaboration; human-machine interaction;
D O I
10.1145/3411763.3441338
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The safe deployment of autonomous physical systems in real-world scenarios requires them to be explainable and trustworthy, especially in critical domains. In contrast with 'black-box' systems, explainable and trustworthy autonomous physical systems will lend themselves to easy assessments by system designers and regulators. This promises to pave ways for easy improvements that can lead to enhanced performance, and as well, increased public trust. In this one-day virtual workshop, we aim to gather a globally distributed group of researchers and practitioners to discuss the opportunities and social challenges in the design, implementation, and deployment of explainable and trustworthy autonomous physical systems, especially in a post-pandemic era. Interactions will be fostered through panel discussions and a series of spotlight talks. To ensure lasting impact of the workshop, we will conduct a pre-workshop survey which will examine the public perception of the trustworthiness of autonomous physical systems. Further, we will publish a summary report providing details about the survey as well as the identified challenges resulting from the workshop's panel discussions.
引用
收藏
页数:3
相关论文
共 50 条
  • [1] Towards Trustworthy AI for Autonomous Systems
    Bride, Hadrien
    Dong, Jin Song
    Hou, Zhe
    Mahony, Brendan
    Oxenham, Martin
    [J]. FORMAL METHODS AND SOFTWARE ENGINEERING, ICFEM 2018, 2018, 11232 : 407 - 411
  • [2] Towards Trustworthy Autonomous Systems: Taxonomies and Future Perspectives
    Flammini, Francesco
    Alcaraz, Cristina
    Bellini, Emanuele
    Marrone, Stefano
    Lopez, Javier
    Bondavalli, Andrea
    [J]. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING, 2024, 12 (02) : 601 - 614
  • [3] Towards Trustworthy Autonomous Systems via Conversations and Explanations
    Gyevnar, Balint
    [J]. THIRTY-EIGTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 21, 2024, : 23389 - 23390
  • [4] Towards Trustworthy Smart Cyber-Physical Systems
    David, M. W.
    Yerkes, C. R.
    Simmons, M. E.
    Franceschini, W.
    [J]. INFORMATION AND COMMUNICATIONS SECURITY, ICICS 2016, 2016, 9977 : 392 - 399
  • [5] AI assurance: towards trustworthy, explainable, safe, and ethical AI
    Wang, Jialei
    Fu, Li
    [J]. AI & SOCIETY, 2023,
  • [6] Towards Self-Explainable Cyber-Physical Systems
    Blumreiter, Mathias
    Greenyer, Joel
    Garcia, Francisco Javier Chiyah
    Kloes, Verena
    Schwammberger, Maike
    Sommer, Christoph
    Vogelsang, Andreas
    Wortmann, Andreas
    [J]. 2019 ACM/IEEE 22ND INTERNATIONAL CONFERENCE ON MODEL DRIVEN ENGINEERING LANGUAGES AND SYSTEMS COMPANION (MODELS-C 2019), 2019, : 543 - 548
  • [7] Trustworthy Autonomous Systems Through Verifiability
    Mousavi, Mohammad Reza
    Cavalcanti, Ana
    Fisher, Michael
    Dennis, Louise
    Hierons, Rob
    Kaddouh, Bilal
    Law, Effie Lai-Chong
    Richardson, Rob
    Ringer, Jan Oliver
    Tyukin, Ivan
    Woodcock, Jim
    [J]. COMPUTER, 2023, 56 (02) : 40 - 47
  • [8] Trustworthy Execution in Untrustworthy Autonomous Systems
    Halasz, David
    Shandilya, Suyash
    Buhnova, Barbora
    [J]. 2023 IEEE 22ND INTERNATIONAL CONFERENCE ON TRUST, SECURITY AND PRIVACY IN COMPUTING AND COMMUNICATIONS, TRUSTCOM, BIGDATASE, CSE, EUC, ISCI 2023, 2024, : 1766 - 1773
  • [9] Solutions to the routing problem: towards trustworthy autonomous vehicles
    László Z. Varga
    [J]. Artificial Intelligence Review, 2022, 55 : 5445 - 5484
  • [10] Solutions to the routing problem: towards trustworthy autonomous vehicles
    Varga, Laszlo Z.
    [J]. ARTIFICIAL INTELLIGENCE REVIEW, 2022, 55 (07) : 5445 - 5484