How to Cite
Abstract
[1] A key concept for navigational algorithms for self-driving vehicles is the necessity to be explainable. This leads to the requirement for transparent algorithms. Understandably, this requirement describes the ability of a system to understand the underlying principles involved in the navigational decisions being made. This article clearly demonstrates the importance of these requirements in the context of future architectures for assisted and autonomous driving. The proposed architecture completely decouples control law from an auxiliary system model, thus providing explainability via the system’s transfer functions. In the literature, there are a few of works which study such issues.
References
F. Hussain, R. Hussain, and E. Hossain, "Explainable Artificial Intelligence (XAI): An Engineering Perspective," 2021. [PDF]
S. Zhao, Y. Li, J. Ma, Z. Xing et al., "Research on imaging method of driver's attention area based on deep neural network," 2022. ncbi.nlm.nih.gov
A. F. T. Winfield, S. Booth, L. A. Dennis, T. Egawa et al., "IEEE P7001: A Proposed Standard on Transparency," 2021. ncbi.nlm.nih.gov
S. Atakishiyev, M. Salameh, H. Yao, and R. Goebel, "Towards Safe, Explainable, and Regulated Autonomous Driving," 2021. [PDF]
S. Atakishiyev, M. Salameh, and R. Goebel, "Safety Implications of Explainable Artificial Intelligence in End-to-End Autonomous Driving," 2024. [PDF]
Tatineni, Sumanth. "Deep Learning for Natural Language Processing in Low-Resource Languages." International Journal of Advanced Research in Engineering and Technology (IJARET) 11.5 (2020): 1301-1311.
Vemoori, Vamsi. "Comparative Assessment of Technological Advancements in Autonomous Vehicles, Electric Vehicles, and Hybrid Vehicles vis-à-vis Manual Vehicles: A Multi-Criteria Analysis Considering Environmental Sustainability, Economic Feasibility, and Regulatory Frameworks." Journal of Artificial Intelligence Research 1.1 (2021): 66-98.
Mahammad Shaik. “Reimagining Digital Identity: A Comparative Analysis of Advanced Identity Access Management (IAM) Frameworks Leveraging Blockchain Technology for Enhanced Security, Decentralized Authentication, and Trust-Centric Ecosystems”. Distributed Learning and Broad Applications in Scientific Research, vol. 4, June 2018, pp. 1-22, https://dlabi.org/index.php/journal/article/view/2.
Tatineni, Sumanth. "Enhancing Fraud Detection in Financial Transactions using Machine Learning and Blockchain." International Journal of Information Technology and Management Information Systems (IJITMIS) 11.1 (2020): 8-15.
H. S. Kim and I. Joe, "An XAI method for convolutional neural networks in self-driving cars," 2022. ncbi.nlm.nih.gov
A. Halilovic and S. Krivic, "Understanding Path Planning Explanations," 2023. [PDF]
R. Kashefi, L. Barekatain, M. Sabokrou, and F. Aghaeipoor, "Explainability of Vision Transformers: A Comprehensive Review and New Perspectives," 2023. [PDF]
S. Ellen Haupt, W. Chapman, S. V. Adams, C. Kirkwood et al., "Towards implementing artificial intelligence post-processing in weather and climate: proposed actions from the Oxford 2019 workshop," 2021. ncbi.nlm.nih.gov
A. John Karran, T. Demazure, A. Hudon, S. Senecal et al., "Designing for Confidence: The Impact of Visualizing Artificial Intelligence Decisions," 2022. ncbi.nlm.nih.gov
H. Zheng, Z. Zang, S. Yang, and R. Mangharam, "Towards Explainability in Modular Autonomous Vehicle Software," 2022. [PDF]
D. Omeiza, H. Webb, M. Jirotka, and L. Kunze, "Explanations in Autonomous Driving: A Survey," 2021. [PDF]
Y. Guan, H. Liao, Z. Li, G. Zhang et al., "World Models for Autonomous Driving: An Initial Survey," 2024. [PDF]
S. Atakishiyev, M. Salameh, H. Yao, and R. Goebel, "Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions," 2021. [PDF]