Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving
- 1 September 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (18) , 43540-43553
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62272028)
- Central Government Guiding Local Scientific and Technological Development Fund of Shanxi Province (YDZJSX2025D029)
This publication has 31 references indexed in Scilit:
- Adversarial traffic scene generation considering harm, rarity, and ambiguity for autonomous driving testingTransportation Research Part C: Emerging Technologies, 2025
- VLM-RL: A unified vision language models and reinforcement learning framework for safe autonomous drivingTransportation Research Part C: Emerging Technologies, 2025
- Adversarial machine learning: a review of methods, tools, and critical industry sectorsArtificial Intelligence Review, 2025
- Highway autonomous vehicle decision-making method based on prior knowledge and improved experience replay reinforcement learning algorithmExpert Systems with Applications, 2025
- Robust lane change decision for autonomous vehicles in mixed traffic: A safety-aware multi-agent adversarial reinforcement learning approachTransportation Research Part C: Emerging Technologies, 2025
- Deep learning adversarial attacks and defenses in autonomous vehicles: a systematic literature review from a safety perspectiveArtificial Intelligence Review, 2024
- Data poisoning attacks in intelligent transportation systems: A surveyTransportation Research Part C: Emerging Technologies, 2024
- Recent advances in reinforcement learning-based autonomous driving behavior planning: A surveyTransportation Research Part C: Emerging Technologies, 2024
- Human as AI mentor: Enhanced human-in-the-loop reinforcement learning for safe and efficient autonomous drivingCommunications in Transportation Research, 2024
- Trustworthy autonomous driving via defense-aware robust reinforcement learning against worst-case observational perturbationsTransportation Research Part C: Emerging Technologies, 2024