Test automation brings the potential to reduce costs and human effort, but several aspects of software testing remain challenging to automate. One such example is automated performance testing to find performance breaking points. Current approaches to tackle automated generation of performance test cases mainly involve using source code or system model analysis or use-case based techniques. However, source code and system models might not always be available at testing time. On the other hand, if the optimal performance testing policy for the intended objective in a testing process instead could be learned by the testing system, then test automation without advanced performance models could be possible. Furthermore, the learned policy could later be reused for similar software systems under test, thus leading to higher test efficiency. We propose SaFReL, a self-adaptive fuzzy reinforcement learning-based performance testing framework. SaFReL learns the optimal policy to generate performance test cases through an initial learning phase, then reuses it during a transfer learning phase, while keeping the learning running and updating the policy in the long term. Through multiple experiments on a simulated environment, we demonstrate that our approach generates the target performance test cases for different programs more efficiently than a typical testing process, and performs adaptively without access to source code and performance models.
Hierarchical Decision-Making for Autonomous Navigation: Integrating Deep Reinforcement Learning and Fuzzy Logic in Four-Wheel Independent Steering and Driving Systems
School of Automation, Central South University（自动化学院，中南大学）
Technical University of Munich（慕尼黑工业大学）；Siemens AG（西门子股份公司）
Autonomously training interpretable control strategies, called policies, using pre-existing plant trajectory data is of great interest in industrial applications. Fuzzy controllers have been used in industry for decades as interpretable and efficient system controllers. In this study, we introduce a fuzzy genetic programming (GP) approach called fuzzy GP reinforcement learning (FGPRL) that can select the relevant state features, determine the size of the required fuzzy rule set, and automatically adjust all the controller parameters simultaneously. Each GP individual's fitness is computed usin…
The kind of closed-loop verification likely to be required for autonomous vehicle (AV) safety testing is beyond the reach of traditional test methodologies and discrete verification. Validation puts the autonomous vehicle system to the test in scenarios or situations that the system would likely encounter in everyday driving after its release. These scenarios can either be controlled directly in a physical (closed-course proving ground) or virtual (simulation of predefined scenarios) environment, or they can arise spontaneously during operation in the real world (open-road testing or simulatio…
Stanford University（斯坦福大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems. Real-world vehicle testing is commonly employed for autonomous vehicle validation, but the costs and time requirements are high. Consequently, simulation-driven methods such as Adaptive Stress Testing (AST) have been proposed to aid in validation. AST formulates the problem of finding the most likely failure scenarios as a Markov decision process, which can be solved using reinforcement learning. In practice, AST tends to find scenarios where failure is unavoidable and tends to repeatedly…
Modeling difficulty, time-varying model, and uncertain external inputs are the main challenges for energy management of fuel cell hybrid electric vehicles. In the paper, a fuzzy reinforcement learning-based energy management strategy for fuel cell hybrid electric vehicles is proposed to reduce fuel consumption, maintain the batteries' long-term operation, and extend the lifetime of the fuel cells system. Fuzzy Q-learning is a model-free reinforcement learning that can learn itself by interacting with the environment, so there is no need for modeling the fuel cells system. In addition, frequent…
Stanford University（斯坦福大学）；Carnegie Mellon University Silicon Valley（卡内基梅隆大学硅谷校区）
This paper presents a method for testing the decision making systems of autonomous vehicles. Our approach involves perturbing stochastic elements in the vehicle's environment until the vehicle is involved in a collision. Instead of applying direct Monte Carlo sampling to find collision scenarios, we formulate the problem as a Markov decision process and use reinforcement learning algorithms to find the most likely failure scenarios. This paper presents Monte Carlo Tree Search (MCTS) and Deep Reinforcement Learning (DRL) solutions that can scale to large environments. We show that DRL can find …
Fuzzy Inference System for Test Case Prioritization in Software Testing
School of Information Technology and Engineering（信息技术与工程学院）；Kazakh-British Technical University（哈萨克斯坦-英国技术大学）；Faculty of Information Technology（信息技术学院）
Combinatorial interaction testing is an important software testing technique that has seen lots of recent interest. It can reduce the number of test cases needed by considering interactions between combinations of input parameters. Empirical evidence shows that it effectively detects faults, in particular, for highly configurable software systems. In real-world software testing, the input variables may vary in how strongly they interact, variable strength combinatorial interaction testing (VS-CIT) can exploit this for higher effectiveness. The generation of variable strength test suites is a n…
Testing of autonomous systems is extremely important as many of them are both safety-critical and security-critical. The architecture and mechanism of such systems are fundamentally different from traditional control software, which appears to operate in more structured environments and are explicitly instructed according to the system design and implementation. To gain a better understanding of autonomous systems practice and facilitate research on testing of such systems, we conducted an exploratory study by synthesizing academic literature with a focus group discussion and interviews with i…
Autonomous driving has shown great potential to reform modern transportation. Yet its reliability and safety have drawn a lot of attention and concerns. Compared with traditional software systems, autonomous driving systems (ADSs) often use deep neural networks in tandem with logic-based modules. This new paradigm poses unique challenges for software testing. Despite the recent development of new ADS testing techniques, it is not clear to what extent those techniques have addressed the needs of ADS practitioners. To fill this gap, we present the first comprehensive study to identify the curren…
Two is Better Than One: Digital Siblings to Improve Autonomous Driving Testing
Università della Svizzera italiana (USI)（瑞士意大利语区大学）；Technical University of Munich（慕尼黑工业大学）；fortiss GmbH（fortiss有限公司）；Università degli Studi di Udine（乌迪内大学）
DENSO AUTOMOTIVE Deutschland GmbH（电装汽车德国有限公司）；State Key Laboratory of Computer Science, ISCAS（中国科学院计算技术研究所计算机科学国家重点实验室）
Continuous engineering of autonomous driving functions commonly requires deploying vehicles in road testing to obtain inputs that cause problematic decisions. Although the discovery leads to producing an improved system, it also challenges the foundation of testing using equivalence classes and the associated relative test coverage criterion. In this paper, we propose believed equivalence, where the establishment of an equivalence class is initially based on expert belief and is subject to a set of available test cases having a consistent valuation. Upon a newly encountered test case that brea…
Testing autonomous vehicles (AVs) requires complex oracles to determine if the AVs behavior conforms with specifications and humans' expectations. Available open source oracles are tightly embedded in the AV simulation software and are developed and implemented in an ad hoc way. We propose a domain specific language that enables defining oracles independent of the AV solutions and the simulator. A testing analyst can encode safety, liveness, timeliness and temporal properties in our language. To show the expressiveness of our language we implement three different types of available oracles. We…
Heriot-Watt University（赫瑞-瓦特大学）；City, University of London（伦敦大学城市学院）
There is an urgent societal need to assess whether autonomous vehicles (AVs) are safe enough. From published quantitative safety and reliability assessments of AVs, we know that, given the goal of predicting very low rates of accidents, road testing alone requires infeasible numbers of miles to be driven. However, previous analyses do not consider any knowledge prior to road testing - knowledge which could bring substantial advantages if the AV design allows strong expectations of safety before road testing. We present the advantages of a new variant of Conservative Bayesian Inference (CBI), w…
On the Need for a Statistical Foundation in Scenario-Based Testing of Autonomous Vehicles
WMG, University of Warwick（沃里克大学工学院）；Department of Computer Science, Chalmers University of Technology & University of Gothenburg（查尔姆斯理工大学计算机科学系）；Centre for Software Reliability, City St George’s, University of London（伦敦大学城市圣乔治学院软件可靠性中心）
University of Virginia（弗吉尼亚大学）；Columbia University（哥伦比亚大学）
Recent advances in Deep Neural Networks (DNNs) have led to the development of DNN-driven autonomous cars that, using sensors like camera, LiDAR, etc., can drive without any human intervention. Most major manufacturers including Tesla, GM, Ford, BMW, and Waymo/Google are working on building and testing different types of autonomous vehicles. The lawmakers of several US states including California, Texas, and New York have passed new legislation to fast-track the process of testing and deployment of autonomous vehicles on their roads. However, despite their spectacular progress, DNNs, just like …
Autonomous driving has gained much attention from both industry and academia. Currently, Deep Neural Networks (DNNs) are widely used for perception and control in autonomous driving. However, several fatal accidents caused by autonomous vehicles have raised serious safety concerns about autonomous driving models. Some recent studies have successfully used the metamorphic testing technique to detect thousands of potential issues in some popularly used autonomous driving models. However, prior study is limited to a small set of metamorphic relations, which do not reflect rich, real-world traffic…
It is hard to test autonomous robot (AR) software because of the range and diversity of external situations (terrain, obstacles, humans, peer robots) that AR must deal with. Common measures of testing adequacy may not address this diversity. Explicit situation coverage has been proposed as a solution, but there has been little empirical study of its effectiveness. In this paper, we describe an implementation of situation coverage for testing a simple simulated autonomous road vehicle, and evaluate its ability to find seeded faults compared to a random test generation approach. In our experimen…
Software project management makes extensive use of predictive modeling to estimate product size, defect proneness and development effort. Although uncertainty is acknowledged in these tasks, fuzzy inference systems, designed to cope well with uncertainty, have received only limited attention in the software engineering domain. In this study we empirically investigate the impact of two choices on the predictive accuracy of generated fuzzy inference systems when applied to a software engineering data set: sampling of observations for training and testing; and the size of the rule set generated u…
Systematic testing of autonomous vehicles operating in complex real-world scenarios is a difficult and expensive problem. We present Paracosm, a reactive language for writing test scenarios for autonomous driving systems. Paracosm allows users to programmatically describe complex driving situations with specific visual features, e.g., road layout in an urban environment, as well as reactive temporal behaviors of cars and pedestrians. Paracosm programs are executed on top of a game engine that provides realistic physics simulation and visual rendering. The infrastructure allows systematic explo…
Metamorphic testing has proven to be effective for test case generation and fault detection in many domains. It is a software testing strategy that uses certain relations between input-output pairs of a program, referred to as metamorphic relations. This approach is relevant in the autonomous systems domain since it helps in cases where the outcome of a given test input may be difficult to determine. In this paper therefore, we provide an overview of metamorphic testing as well as an implementation in the autonomous systems domain. We implement an obstacle detection and avoidance task in auton…
Drivora: A Unified and Extensible Infrastructure for Search-based Autonomous Driving Testing
Singapore Management University（新加坡管理大学）；University of Ottawa（渥太华大学）；Lero Centre, University of Limerick（利默里克大学Lero中心）；Zhejiang Sci-Tech University（浙江理工大学）
While Deep Neural Networks (DNNs) have established the fundamentals of DNN-based autonomous driving systems, they may exhibit erroneous behaviors and cause fatal accidents. To resolve the safety issues of autonomous driving systems, a recent set of testing techniques have been designed to automatically generate test cases, e.g., new input images transformed from the original ones. Unfortunately, many such generated input images often render inferior authenticity, lacking accurate semantic information of the driving scenes and hence compromising the resulting efficacy and reliability. In this p…
University of Bristol（布里斯托大学）；University of Bremen（不来梅大学）
In this position paper, a novel approach to testing complex autonomous transportation systems (ATS) in the automotive, avionic, and railway domains is described. It is intended to mitigate some of the most critical problems regarding verification and validation (V&V) effort for ATS. V&V is known to become infeasible for complex ATS, when using conventional methods only. The approach advocated here uses complete testing methods on the module level, because these establish formal proofs for the logical correctness of the software. Having established logical correctness, system-level tests are pe…
VP-AutoTest: A Virtual-Physical Fusion Autonomous Driving Testing Platform
Department of Traffic Engineering & Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University（交通工程系及道路交通工程重点实验室，教育部，同济大学）；College of Electronic and Information Engineering, Department of Control Science and Engineering, and Shanghai Institute of Intelligent Science and Technology, Tongji University（电子信息学院、控制科学与工程系及上海智能科学技术研究院，同济大学）；State Key Laboratory of Automotive Simulation and Control, Jilin University（汽车仿真与控制国家重点实验室，吉林大学）
Constrained Co-evolutionary Metamorphic Differential Testing for Autonomous Systems with an Interpretability Approach
School of EECS, University of Ottawa（渥太华大学电气与计算机工程学院）；Lero SFI centre for Software Research, University of Limerick（利默里克大学Lero软件研究中心）；Waterloo Research Center of Huawei Technologies Canada Co., Ltd.（华为技术有限公司加拿大分公司滑铁卢研发中心）
ISCAS（中国科学院软件研究所）；Beijing University of Technology（北京工业大学）；University of Chinese Academy of Sciences（中国科学院大学）
ComOpT is an open-source research tool for coverage-driven testing of autonomous driving systems, focusing on planning and control. Starting with (i) a meta-model characterizing discrete conditions to be considered and (ii) constraints specifying the impossibility of certain combinations, ComOpT first generates constraint-feasible abstract scenarios while maximally increasing the coverage of k-way combinatorial testing. Each abstract scenario can be viewed as a conceptual equivalence class, which is then instantiated into multiple concrete scenarios by (1) randomly picking one local map that f…
University of California, Santa Cruz（加州大学圣克鲁兹分校）；American Automobile Association (AAA) of Northern California, Nevada & Utah (NCNU)（北加州、内华达和犹他州美国汽车协会）；LG Electronics America R&D Lab（LG电子美国研发实验室）；University of California, Berkeley（加州大学伯克利分校）
We present a new approach to automated scenario-based testing of the safety of autonomous vehicles, especially those using advanced artificial intelligence-based components, spanning both simulation-based evaluation as well as testing in the real world. Our approach is based on formal methods, combining formal specification of scenarios and safety properties, algorithmic test case generation using formal simulation, test case selection for track testing, executing test cases on the track, and analyzing the resulting data. Experiments with a real autonomous vehicle at an industrial testing faci…
University of Luxembourg（卢森堡大学）；University of Ottawa（渥太华大学）
There is a growing body of research on developing testing techniques for Deep Neural Networks (DNN). We distinguish two general modes of testing for DNNs: Offline testing where DNNs are tested as individual units based on test datasets obtained independently from the DNNs under test, and online testing where DNNs are embedded into a specific application and tested in a close-loop mode in interaction with the application environment. In addition, we identify two sources for generating test datasets for DNNs: Datasets obtained from real-life and datasets generated by simulators. While offline te…
The Role of Road Features and Vehicle Dynamics in Cost-Effective Autonomous Vehicles Safety Testing: Insights from Instance Space Analysis
Monash University（莫纳什大学）；University of Bern（伯尔尼大学）；RMIT University（皇家墨尔本理工大学）；Italian Institute of Artificial Intelligence for Industry (AI4I)（意大利工业人工智能研究所）
Growth of software size, lack of resources to perform regression testing, and failure to detect bugs faster have seen increased reliance on continuous integration and test automation. Even with greater hardware and software resources dedicated to test automation, software testing is faced with enormous challenges, resulting in increased dependence on complex mechanisms for automated test case selection and prioritization as part of a continuous integration framework. These mechanisms are currently using simple entities called test cases that are concretely realized as executable scripts. Our k…
The acceptance of autonomous vehicles is dependent on the rigorous assessment of their safety. Furthermore, the commercial viability of AV programs depends on the ability to estimate the time and resources required to achieve desired safety levels. Naive approaches to estimating the reliability and safety levels of autonomous vehicles under development are will require infeasible amounts of testing of a static vehicle configuration. To permit both the estimation of current safety, and make predictions about the reliability of future systems, I propose the use of a standard tool for modelling t…
