Related references
Note: Only part of the references are listed.
Article
Computer Science, Information Systems
Muhammad Iqbal et al.
Summary: This paper investigates the importance of simulation-based testing in the development of ADAS and AD systems, and proposes a geometric-transformation-based metamorphic testing approach. Through empirical studies on three popular simulation platforms, issues and bugs in ADAS simulation platforms are identified. The research demonstrates the simplicity, effectiveness, and applicability of the proposed approach for ADAS simulation testing. Furthermore, successful examples of incorporating metamorphic testing into ADAS standards and protocols testing are provided.
INFORMATION AND SOFTWARE TECHNOLOGY
(2023)
Review
Computer Science, Software Engineering
Emran Altamimi et al.
Summary: Metamorphic testing tackles the oracle problem by comparing transformed results from multiple test executions. Expert knowledge is required to define metamorphic relations, which can be time-consuming to generate. There have been various techniques proposed to automate metamorphic testing, generation, and selection. However, there is a lack of overview on the current state-of-the-art in automation of metamorphic relations. A systematic literature review study was conducted to collect and synthesize the necessary data, revealing that automation of metamorphic relations is most effective in mathematical and scientific applications.
JOURNAL OF SOFTWARE-EVOLUTION AND PROCESS
(2023)
Article
Computer Science, Software Engineering
Chang-ai Sun et al.
Summary: Metamorphic testing is a technique that constructs new test cases based on software properties, with recent research focusing on generating and selecting effective source test cases. A novel approach based on path constraints to generate source test cases is proposed in this paper, leveraging path distance to guide the prioritization and improve efficiency.
JOURNAL OF SYSTEMS AND SOFTWARE
(2022)
Article
Computer Science, Artificial Intelligence
Jiangong Wang et al.
Summary: The long-tail effect is a common phenomenon in vision-related problems, and accurately perceiving long-tail scenarios remains challenging for vision systems. This paper introduces the theoretical framework of LoTR and the practical implementation of PVAS to address this issue by regularizing long-tail scenarios and generating large-scale driving scenarios.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2022)
Article
Computer Science, Artificial Intelligence
Yulan Guo et al.
Summary: Recently, deep learning on point clouds has been gaining more attention, but it is still in its early stages due to the unique challenges faced in processing point clouds with deep neural networks.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Computer Science, Hardware & Architecture
Zhan-wei Hui et al.
Summary: This article introduces a novel method based on adaptive random testing and metamorphic relations for metamorphic testing test case generation, which outperforms other algorithms in test effectiveness, test efficiency, and test coverage. The study concludes that considering the effectiveness of metamorphic relations and test cases can lead to better results, both source test cases and follow-up test cases should be considered together, and average distance performs better in test case selection for metamorphic testing.
IEEE TRANSACTIONS ON RELIABILITY
(2021)
Article
Computer Science, Information Systems
Zhiyi Zhang et al.
Summary: This paper introduces a novel metamorphic testing method called DeepBackground to evaluate the robustness of DL-driven image recognition systems regarding image background region changes. DeepBackground defines a series of domain-specific metamorphic relations (MRs) combined with BRC to automatically generate many follow-up test images. It can not only evaluate the robustness of these systems about image background changes according to BRC, but also detect their inconsistent behaviors.
INFORMATION AND SOFTWARE TECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Ying Li et al.
Summary: This article reviews the progress of deep learning in processing LiDAR point cloud data, particularly in the field of autonomous driving, including tasks such as segmentation, detection, and classification. Despite several studies focusing on computer vision topics for autonomous vehicles, there is still a research gap in the application of DL in LiDAR point cloud data for autonomous vehicles.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jordan S. K. Hu et al.
Summary: This paper proposes a pattern-aware ground truth sampling data augmentation technique to address the lack of training data for objects at farther distances in autonomous driving datasets. The research shows that using this method can effectively detect objects at farther distances, while improving the performance of PV-RCNN on the car class by more than 0.7% at distances greater than 25 meters.
2021 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC)
(2021)
Proceedings Paper
Computer Science, Software Engineering
Songqiang Chen et al.
Summary: This study introduces a method, QAASKER, that tests QA software behavior without the need for annotated labels by asking multiple recursively related questions. Experimental results show that QAASKER can reveal violations in over 80% of valid cases without the use of any pre-annotated labels.
2021 36TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING ASE 2021
(2021)
Proceedings Paper
Computer Science, Information Systems
Takami Sato et al.
Summary: Even though Automatic Lane Centering systems are convenient and widely deployed, recent research indicates that they are also vulnerable to attacks such as the Dirty Road Patch attack. This work demonstrates the effectiveness of the DRP attack on both simulation and physical-world setups.
2021 IEEE SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS (SPW 2021)
(2021)
Article
Computer Science, Artificial Intelligence
Shaoshuai Shi et al.
Summary: This study proposes a novel point-cloud-based 3D object detection framework, Part-A(2) net, which includes two stages: part-aware and part-aggregation. By utilizing part supervisions from 3D ground-truth boxes and a new-designed RoI-aware point cloud pooling module, the framework achieves high-quality 3D proposals and accurate intra-object part locations prediction.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Engineering, Electrical & Electronic
You Li et al.
IEEE SIGNAL PROCESSING MAGAZINE
(2020)
Article
Computer Science, Hardware & Architecture
Zhan-Wei Hui et al.
IEEE TRANSACTIONS ON RELIABILITY
(2020)
Proceedings Paper
Computer Science, Software Engineering
Joshua Garcia et al.
2020 ACM/IEEE 42ND INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING (ICSE 2020)
(2020)
Article
Robotics
Jin Fang et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2020)
Article
Computer Science, Artificial Intelligence
Yue Kang et al.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2019)
Article
Robotics
W. Li et al.
Review
Computer Science, Theory & Methods
Tsong Yueh Chen et al.
ACM COMPUTING SURVEYS
(2018)
Article
Chemistry, Analytical
Yan Yan et al.
Article
Robotics
Manikandasriram Srinivasan Ramanagopal et al.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2018)
Review
Automation & Control Systems
Dominique Gruyer et al.
ANNUAL REVIEWS IN CONTROL
(2017)
Article
Computer Science, Software Engineering
Tsong Yueh Chen et al.
JOURNAL OF SYSTEMS AND SOFTWARE
(2016)
Article
Robotics
A. Geiger et al.
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH
(2013)