How to Cite
Abstract
In this chapter, we thoroughly examine and meticulously evaluate the diverse range of innovative methods that have been extensively discussed and analyzed in prominent recent studies. Our primary focus revolves around the noble objective of enhancing transparency in the context of automated vehicles, with a particular emphasis on cutting-edge vision-based systems. By delving into the depths of this captivating subject matter, we aim to unravel the intricacies and complexities associated with this fascinating field of research, elucidating the various nuances and subtleties that have emerged on the forefront of technological advancements. Through a meticulous exploration of these methods, we aspire to contribute towards the further development and progression of transparency in automated vehicles, paving the way for a future that is not only safer but also more intelligently interconnected.
Autonomous vehicles (AVs) decision making abilities are governed by machine learning models, which are black boxes characterized by the lack of transparency in their decision-making process. However, transparency in the decision-making approach is of paramount importance to promote user confidence, especially when dealing with vehicles performing critical and safety-related tasks. Techniques, also known as explainable AI, have been proposed to help end-users better understand why AI systems make a specific choice, hence promoting improved engagement and trust.
References
R. Guidotti et al., "A Survey of Methods for Explaining Black Box Models," IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 5, pp. 1955-1969, May 2018.
R. Caruana et al., "Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission," Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, NSW, Australia, 2015, pp. 1721-1730.
M. T. Ribeiro, S. Singh, and C. Guestrin, "Why Should I Trust You?: Explaining the Predictions of Any Classifier," Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 1135-1144.
A. L. Mille, G. Lena, and F. Yvon, "Explanation in Artificial Intelligence: Insights from the Social Sciences," Artificial Intelligence, vol. 267, pp. 1-38, 2019.
M. T. Ribeiro, S. Singh, and C. Guestrin, "Anchors: High-Precision Model-Agnostic Explanations," Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA, 2017, pp. 3338-3347.
S. Lundberg and S. Lee, "A Unified Approach to Interpreting Model Predictions," Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA, 2017, pp. 4765-4774.
T. Miller, "Explanation in Artificial Intelligence: Insights from the Social Sciences," Artificial Intelligence, vol. 267, pp. 1-38, 2019.
M. Sundararajan, A. Taly, and Q. Yan, "Axiomatic Attribution for Deep Networks," Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, 2017, pp. 3319-3328.
K. Simonyan, A. Vedaldi, and A. Zisserman, "Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps," arXiv preprint arXiv:1312.6034, 2013.
Tatineni, Sumanth. "Cloud-Based Business Continuity and Disaster Recovery Strategies." International Research Journal of Modernization in Engineering, Technology, and Science5.11 (2023): 1389-1397.
Vemori, Vamsi. "From Tactile Buttons to Digital Orchestration: A Paradigm Shift in Vehicle Control with Smartphone Integration and Smart UI–Unveiling Cybersecurity Vulnerabilities and Fortifying Autonomous Vehicles with Adaptive Learning Intrusion Detection Systems." African Journal of Artificial Intelligence and Sustainable Development3.1 (2023): 54-91.
Shaik, Mahammad, Leeladhar Gudala, and Ashok Kumar Reddy Sadhu. "Leveraging Artificial Intelligence for Enhanced Identity and Access Management within Zero Trust Security Architectures: A Focus on User Behavior Analytics and Adaptive Authentication." Australian Journal of Machine Learning Research & Applications 3.2 (2023): 1-31.
Tatineni, Sumanth. "Security and Compliance in Parallel Computing Cloud Services." International Journal of Science and Research (IJSR) 12.10 (2023): 972-1977.
J. C. Carvalho et al., "Explainable Artificial Intelligence for Predictive Maintenance," 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), Rhodes, Greece, 2020, pp. 1-6.
J. J. A. Pereira et al., "Explainable Artificial Intelligence for the Prediction of Depressive Symptoms in Older Adults," IEEE Journal of Biomedical and Health Informatics, vol. 24, no. 3, pp. 724-732, 2020.
A. Stumpf, "Interpretability, or How to Explain AI Models," XRDS: Crossroads, The ACM Magazine for Students, vol. 24, no. 3, pp. 32-35, 2018.
S. D. Jain, A. Agarwal, and S. K. Dhurandher, "Explainable AI: A Review," 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Kharagpur, India, 2020, pp. 1-6.
T. N. K. Venkata and M. V. Malathy, "Interpretable Machine Learning Models for Healthcare," 2020 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Bangalore, India, 2020, pp. 1-6.
S. J. Pan and Q. Yang, "A Survey on Transfer Learning," IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, Oct. 2010.
R. Guidotti et al., "A Survey of Methods for Explaining Black Box Models," IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 5, pp. 1955-1969, May 2018.
M. Sundararajan, A. Taly, and Q. Yan, "Axiomatic Attribution for Deep Networks," Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, 2017, pp. 3319-3328.