7 June 2023 in Transportation Research Part C: Emerging Technologies
23 June 2025 in IEEE Transactions on Intelligent Transportation Systems
Ensuring and improving the safety of autonomous driving systems (ADS) is crucial for deployment of highly automated vehicles, especially in safety-critical events. To address the rarity issue, adversarial scenario generation methods are developed, in which behaviors of traffic participants are manipulated to induce safety-critical events. However, existing methods still face two limitations. First, identification of the adversarial participant directly impacts the effectiveness of the generation. However, complexity of real-world scenarios, with numerous participants and diverse behaviors, makes identification challenging. Second, potential of generated safety-critical scenarios to continuously improve ADS performance remains underexplored. To address these issues, we propose LLM-attacker: a closed-loop adversarial scenario generation framework leveraging large language models (LLMs). Specifically, multiple LLM agents are designed and coordinated to identify optimal attackers. Then, the trajectories of attackers are optimized to generate adversarial scenarios. These scenarios are iteratively refined based on the performance of ADS, forming a feedback loop to improve ADS. Experimental results show that LLM-attacker can create more dangerous scenarios than other methods, and the ADS trained with it achieves a collision rate half that of training with normal scenarios. This indicates the ability of LLM-attacker to test and enhance the safety and robustness of ADS. The framework’s closed-loop design enables continuous scenario evolution compliant with regulatory standards, supporting both safety assurance and policy verification for ADS. Video demonstrations are provided at: https://drive.google.com/file/d/15rROV_ 8LUcc2jXSuSNBHVOHMCFKSn__B/view
2 November 2023 in Transportation Research Part C: Emerging Technologies
23 June 2022 in IEEE Transactions on Intelligent Transportation Systems
Serious Road anomalies caused by bridge approach settlement, pavement rutting, etc., not only seriously affect traffic safety and user experience but also aggravate the damage of road structure. It is more relevant to automated vehicles (AVs) as they are currently not designed to measure the pavement roughness directly. Without prior-collected road anomalies information, AVs’ active suspension control system can only passively reduce the negative impact of road anomalies to a certain extent. This paper proposed a response-type road anomaly detection and evaluation method by collecting the vibration data from AVs. A mechanical estimation model for the height of anomaly (HoA) is constructed to evaluate the degree of road anomaly. Passenger’s comfort is evaluated by three featured indicators: maximal acceleration, weighted root-mean-square acceleration, and jerk A full-car simulation model is programmed based on the Simulink platform to reveal the relationship among road anomalies, comfort, and speed, which helps design a steady driving velocity profile for AVs. The results show that the root-mean-square error of road anomalies estimation is about 0.63cm AVs’ comfort can be improved significantly by employing the proposed steady driving strategies.
25 October 2024 in Transportation Research Part C: Emerging Technologies