Recent advancements have underscored the exceptional analytical and situational understanding capabilities of Large Language Models (LLMs) in autonomous driving decisions. However, the inherent hallucination issues of LLMs pose significant safety concerns when utilized as standalone decision-making systems. To address these challenges, we propose the Hybrid-Driving framework, which leverages LLMs' situational comprehension and reasoning abilities alongside the specialized driving expertise embedded in knowledge graphs and driving rules, thereby enhancing the safety, robustness, and reliability of autonomous driving decisions. To articulate driving experiences clearly, we introduce the Scenario Evolution Knowledge Graph (SEKG), which integrates scenario prediction and action risk analysis in autonomous driving. By delineating observation areas and defining Time-to-Collision (TTC) levels, we effectively control the number of driving scenario nodes and ensure scenario diversity. Based on the scenario evolution relationships within the SEKG, we predict scenarios and assess associated action risks. Additionally, we implement a rule-filtering mechanism to eliminate unreasonable actions and employ prompt engineering to integrate scenario information, optional actions, and SEKG-based action risk analysis into the LLMs for decision-making. Extensive experiments demonstrate that our approach substantially improves decision success rates compared to using LLMs alone (≥37.5%), as well as surpasses the DiLu framework with LLMs and few-shot driving memory (≥7.5%), and other reinforcement learning methods (≥11%). These results validate the effectiveness of the Hybrid-Driving framework in enhancing LLM reliability for autonomous driving and advocate for its broader application of domain-specific knowledge across other fields.

The generation of adversarial safety-critical scenarios is essential for rigorously evaluating autonomous driving systems, enabling the identification of vulnerabilities and enhancement of system robustness. However, existing methodologies predominantly focus on extreme, unconstrained collision scenarios in which non-player character (NPC) vehicles exhibit unrealistic adversarial behaviors toward the ego vehicle. While such scenarios serve as stress tests, their practical utility is limited due to two key factors: 1) these extreme events are statistically rare in real-world traffic and frequently involve collisions that are physically unavoidable, irrespective of the autonomous vehicle’s decision-making capabilities; and 2) NPC behaviors in these scenarios are often intentionally aggressive (e.g., deliberate rear-end collisions), resulting in liability attribution that predominantly lies with the NPCs rather than exposing meaningful system limitations. Recent efforts to enhance scenario plausibility rely extensively on large-scale real-world traffic datasets, introducing significant computational costs and scalability constraints. To overcome these limitations, we propose a three-layer relative safety region model that partitions the driving environment into zones of varying risk levels. This partitioning increases the likelihood that NPC vehicles will interact within relative safety boundary regions, thus enabling the generation of more realistic and contextually relevant adversarial scenarios without the need for extensive real-world traffic data. We introduce AuthSim, a platform that integrates this safety model with reinforcement learning (RL) to generate both authentic and effective safety-critical scenarios. AuthSim is the first comprehensive approach to address both the authenticity and effectiveness of autonomous driving test scenarios without relying on large-scale traffic data. Empirical results demonstrate that AuthSim outperforms existing methods, achieving a 5.25% improvement in average cut-in distance and a 11.94% increase in average collision interval time compared with the state-of-the-art (SOTA) results, all while maintaining superior efficiency in scenario generation. These findings highlight the potential of AuthSim to produce high-fidelity and efficient test cases for the rigorous evaluation of autonomous driving systems.

Critical scenario generation plays a crucial role in the autonomous driving test by efficiently and effectively identifying various hazardous scenarios to evaluate the multiagent system under test. The performance of existing solution models is hampered by sparse rewards resulting from long time-steps in driving scenarios. Moreover, they fail to guide the generation of more diverse scenarios because of the lack of a fine-grained design. To efficiently and effectively discover various critical scenarios, we propose the MACS method based on multiagent reinforcement learning to guide adversaries foiled the agent under test by replay buffer optimization and objective function design. By adopting the hindsight experience replay method, historical experiences are reused to address the challenge of sparse rewards and improve sample efficiency. Furthermore, we integrate the entropy term into the objective function to explore different driving strategies, thereby leading to the creation of diverse scenarios. We have achieved a new state-of-the-art performance in evaluating rule-based agents using an industrial-grade platform, SMARTS. The experimental results demonstrate that MACS can effectively generate diverse critical scenarios that lead to the failure of the agent under test. We also apply cluster methods, including DBSCAN and TRACLUS, to conduct diversity analysis of the generated scenarios. Besides, we evaluate and improve the reinforcement learning decision algorithm for the vehicle under test with our generated scenarios and give empirical conclusions about its robustness.

Exploring critical scenarios for autonomous driving is a challenging task that requires effectively generating diverse multimodal scenarios from an infinite parameter space. However, most search-based methods encounter the mode collapse problem, leading to the generation of similar concrete scenarios for a given logical scenario. Besides, they require training different models for potentially diverse logical scenarios, which consume considerable time. To tackle these challenges, we propose the Stacked Action Blocks (SAB) framework inspired by reusable modularity in software architecture. In this framework, we extract atomic actions from logical scenarios and train each atomic action using a multimodal model as an action block to mitigate the impact of mode collapse. By reusing these trained action blocks, we compose diverse critical scenarios, thereby reducing training costs. We extensively evaluated our approach in four complex driving scenarios and achieved superior performance in the Critical Scenario Generation (CSG) task compared to heuristic methods and search-based methods. We demonstrate that the independent training of these action blocks that are reusable and modular is an effective way to find diverse multimodal critical driving scenarios. In addition, we show that the driving policy becomes better at avoiding collisions after fine-tuning based on these critical scenarios.

Rare critical scenarios are crucial to verify the performance of autonomous driving in different situations. Critical scenario generation requires the ability of sampling critical combinations from an infinite parameter space in the logical scenario. Existing solutions aim to explore the correlation of action parameters in the initial scenario rather than action sequences. How to model action sequences so that one can further consider the effects of different action parameters is the bottleneck of the problem. In this paper, we solve the problem by proposing the ECSAS framework. Specifically, we first propose a description language, BTScenario, allowing us to model action sequences of scenarios. We then use reinforcement learning to search for combinations of critical action parameters. Several optimizations are proposed to increase efficiency, including action mask and replay buffer. Experimental results show that our model with strong collision ability and effectively outperforms the existing methods on various nontrivial scenarios.

Autonomous driving simulation tests play a crucial role in advancing autonomous driving technology and assessing its level of development. Conducting tests that incorporate traffic flow brings several advantages, including a comprehensive representation of various traffic elements and a close resemblance to real-world driving conditions. Such tests are effective in evaluating the performance of autonomous vehicles under different traffic scenarios. However, traditional traffic flow simulations primarily concentrate on enhancing the overall efficiency of the traffic system, rather than catering specifically to the testing requirements of autonomous vehicles within traffic flow. As a result, there is currently a shortage of comprehensive research summarizing the testing of autonomous vehicles in traffic flow environments. To address this issue, existing traffic models describing specific vehicle behavioral models and traffic flow-based autonomous driving test methods and metrics are first classified and summarized. In addition, future research on traffic flow-based autonomous driving tests is highlighted and discussed. By systematically organizing existing knowledge and highlighting potential avenues for research, this work aims to bridge the gap in understanding and facilitate the progress of autonomous driving testing within traffic flow environments.

The workloads of autonomous driving traffic accident cloud data centers exhibit high variance and uncertainty. Accurate modeling and prediction of the variance and uncertainty of cloud workloads are crucial for the realization of reliable resource management in cloud data centers. Existing solutions are point prediction methods that can not capture the variance and uncertainty of the cloud workloads. In this paper, we propose a workload probabilistic prediction method with deep learning to model and predict the variance and uncertainty of cloud workload. Our method is a hybrid deep learning model which combines exponential smoothing, bidirectional long short-term memory (BLSTM) and quantile regression. First, a cloud workload pre-processing method based on exponential smoothing is proposed to smooth the high variance feature of cloud workloads. Then, a BLSTM based cloud workload algorithm is introduced. Finally, a differentiable quantile loss function is introduced into the prediction model to generate predictions of multiple quantiles. The experimental results on the Google cluster trace show that our method outperforms other four baseline models.

With the rise of big data, the quality of datasets has become a crucial factor affecting the performance of machine learning models. High-quality datasets are essential for the realization of data value. This survey article summarizes the research direction of dataset quality in machine learning, including the definition of related concepts, analysis of quality issues and risks, and a review of dataset quality dimensions and metrics throughout the dataset lifecycle and a review of dataset quality metrics analyzed from a dataset lifecycle perspective and summarized in literatures. Furthermore, this article introduces a comprehensive quality evaluation process, which includes a framework for dataset quality evaluation with dimensions and metrics, computation methods for quality metrics, and assessment models. These studies provide valuable guidance for evaluating dataset quality in the field of machine learning, which can help improve the accuracy, efficiency, and generalization ability of machine learning models, and promote the development and application of artificial intelligence technology.

Cloud workload turning point is either a local peak point standing for workload pressure or a local valley point standing for resource waste. Predicting such critical points is important to give warnings to system managers to take precautionary measures aimed at achieving high resource utilization, quality of service (QoS), and profit of the investment. Existing researches mainly focus more on the workload's future point value prediction only, whereas trend-based turning point prediction is not considered. Moreover, one of the most critical challenges during the prediction is the fact that traditional trend prediction methods which succeed in financial and industrial areas, etc., have a weak ability to represent the cloud features, which means that they cannot describe the highly-variable cloud workloads time series. This article introduces a novel cloud workload turning point prediction approach based on cloud feature-enhanced deep learning. First, we establish a turning point prediction model of cloud server workload considering cloud workload features. Then, a cloud feature-enhanced deep learning model is designed for workload turning point prediction. Experiments on the most famous Google cluster demonstrate the effectiveness of our model compared with state-of-the-art models. To the best of our knowledge, this article is the first systematic research on turning point-based trend prediction of cloud workload time series by cloud feature-enhanced deep learning.

How to evaluate the performance variations of large-scale cloud data centres is challenging due to diverse nature of cloud platforms. Classic methods such as profiling-based evaluating methods tend to only provide global statistics for a system compared with cloud tracing based approaches. However, existing tracing based research lacks a systematic comparative multiview analysis from architecure-view to job-view and task-view, etc.to evaluate cloud performance variations, together with a detailed case study. We introduce MuCoTrAna, a multiview comparative workload traces analysis approach to evaluate the performance variations of large-scale cloud data centres which assists the cloud platform performance managers and big trace analysts. The efficiency of the proposed approach is demonstrated via case studies in Alibaba 2018 trace and Google trace. The multifaceted analysis results of traces reveals the qualitative insights, performance bottlenecks, inferences and adequate suggestions from global view, machine view, job-task view, etc.

Software failures are not rare and fault localizations always an important but laborious activity. Since there is no guarantee that no more than one fault exists in a faulty program, the approach to locate all the faults is necessary. Spectrum-based fault localization techniques collect dynamic program spectra as well as test results of program runs, and estimate the extent of program elements being related to fault(s). A popular solution into generate a ranked list of suspicious candidates, which are checked in order, stopping whenever a fault is found. Such single fault localizers locate one fault in one checking round, terminate, and wait to be triggered by the regression testing to validate the fixing of the located fault. In this paper, we study the manifestation of multiple faults in a program and propose an effective mechanism to indicate their presence. When a fault is reached during the checking round, we use it to interpret the failures observed, and update the indicator to judge whether there remain other faults in the program. Our indicator serves as a stopping criterion of checking the ranked list of suspicious candidates. Our work factories the multiple fault localization problem into developing single-fault localizers and adapting them to multi-fault programs. It both improves the fault localization efficiencies of single-fault localizers, and avoids the ineffective efforts of thoroughly abandoning the many single-fault localizers to develop multi-fault localizers.

Computer architectural complexity is growing so dramatically that auto-tuning application's performance becomes an important approach to take full advantage of hardware's computational potential. In this paper we present a polyhedron model based approach to improve program performance by automatically finding a good sequence of loop optimizations for each program respectively. This approach performs any legal sequence of loop optimizations outside existing compilers based on polyhedral model for program or its part. It evaluates program performance using hardware performance counters and a simplified cache miss equation. It finally produces a sequence to perform loop optimization for a program, or different sequences for different parts of a program. Experiments for SPEC CPU 2006 show that LI data cache miss rate can be decreased by 5%-21% while performance improved by up to 26% when compared with Open64 -03.