Dataset Information

A Formal and Quantifiable Log Analysis Framework for Test Driving of Autonomous Vehicles.

ABSTRACT: We propose a log analysis framework for test driving of autonomous vehicles. The log of a vehicle is a fundamental source to detect and analyze events during driving. A set of dumped logs are, however, usually mixed and fragmented since they are generated concurrently by a number of modules such as sensors, actuators and programs. This makes it hard to analyze them to discover latent errors that could occur due to complex chain reactions among those modules. Our framework provides a logging architecture based on formal specifications, which hierarchically organizes them to find out a priori relationships between them. Then, algorithmic or implementation errors can be detected by examining a posteriori relationships. However, a test in a situation of certain parameters, so called an oracle test, does not necessarily trigger latent violations of the relationships. In our framework, this is remedied by adopting metamorphic testing to quantitatively verify the formal specification. As a working proof, we define three metamorphic relations critical for testing autonomous vehicles and verify them in a quantitative manner based on our logging system.

SUBMITTER: Sung K

PROVIDER: S-EPMC7085529 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Formal and Quantifiable Log Analysis Framework for Test Driving of Autonomous Vehicles.

Sung Kyungbok K Min Kyoung-Wook KW Choi Jeongdan J Kim Byung-Cheol BC

Sensors (Basel, Switzerland) 20200302 5

We propose a log analysis framework for test driving of autonomous vehicles. The log of a vehicle is a fundamental source to detect and analyze events during driving. A set of dumped logs are, however, usually mixed and fragmented since they are generated concurrently by a number of modules such as sensors, actuators and programs. This makes it hard to analyze them to discover latent errors that could occur due to complex chain reactions among those modules. Our framework provides a logging arch ...[more]

PMID: 32121632

Similar Datasets

Project description:The computer vision systems driving autonomous vehicles are judged by their ability to detect objects and obstacles in the vicinity of the vehicle in diverse environments. Enhancing this ability of a self-driving car to distinguish between the elements of its environment under adverse conditions is an important challenge in computer vision. For example, poor weather conditions like fog and rain lead to image corruption which can cause a drastic drop in object detection (OD) performance. The primary navigation of autonomous vehicles depends on the effectiveness of the image processing techniques applied to the data collected from various visual sensors. Therefore, it is essential to develop the capability to detect objects like vehicles and pedestrians under challenging conditions such as like unpleasant weather. Ensembling multiple baseline deep learning models under different voting strategies for object detection and utilizing data augmentation to boost the models' performance is proposed to solve this problem. The data augmentation technique is particularly useful and works with limited training data for OD applications. Furthermore, using the baseline models significantly speeds up the OD process as compared to the custom models due to transfer learning. Therefore, the ensembling approach can be highly effective in resource-constrained devices deployed for autonomous vehicles in uncertain weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and were able to identify objects from the images captured in the adverse foggy and rainy weather conditions. The applied techniques demonstrated an increase in accuracy over the baseline models and reached 32.75% mean average precision (mAP) and 52.56% average precision (AP) in detecting cars in the adverse fog and rain weather conditions present in the dataset. The effectiveness of multiple voting strategies for bounding box predictions on the dataset is also demonstrated. These strategies help increase the explainability of object detection in autonomous systems and improve the performance of the ensemble techniques over the baseline models.

Dataset Information

A Formal and Quantifiable Log Analysis Framework for Test Driving of Autonomous Vehicles.

Publications

A Formal and Quantifiable Log Analysis Framework for Test Driving of Autonomous Vehicles.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets