Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAutomated Vehicle Crash Sequences: Patterns and Potential Uses in Safety Testing
35
0
0.0
(
0
)
Added by
Yu Song
Publication date
2021
fields
Mathematical Statistics
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
With safety being one of the primary motivations for developing automated vehicles (AVs), extensive field and simulation tests are being carried out to ensure AVs can operate safely on roadways. Since 2014, the California DMV has been collecting AV collision and disengagement reports, which are valuable data sources for studying AV crash patterns. In this study, crash sequence data extracted from California AV collision reports were used to investigate patterns and how they may be used to develop AV test scenarios. Employing sequence analysis, this study evaluated 168 AV crashes (with AV in automatic driving mode before disengagement or collision) from 2015 to 2019. Analysis of subsequences showed that the most representative pattern in AV crashes was (collision following AV stop) type. Analysis of event transition showed that disengagement, as an event in 24 percent of all studied AV crash sequences, had a transition probability of 68 percent to an immediate collision. Cluster analysis characterized AV crash sequences into seven groups with distinctive crash dynamic features. Cross-tabulation analysis showed that sequence groups were significantly associated with variables measuring crash outcomes and describing environmental conditions. Crash sequences are useful for developing AV test scenarios. Based on the findings, a scenario-based AV safety testing framework was proposed with sequence of events embedded as a core component.
rate research
Read More
The development of safety-critical systems requires the control of hazards that can potentially cause harm. To this end, safety engineers rely during the development phase on architectural solutions, called safety patterns, such as safety monitors, voters, and watchdogs. The goal of these patterns is to control (identified) faults that can trigger hazards. Safety patterns can control such faults by e.g., increasing the redundancy of the system. Currently, the reasoning of which pattern to use at which part of the target system to control which hazard is documented mostly in textual form or by means of models, such as GSN-models, with limited support for automation. This paper proposes the use of logic programming engines for the automated reasoning about system safety. We propose a domain-specific language for embedded system safety and specify as disjunctive logic programs reasoning principles used by safety engineers to deploy safety patterns, e.g., when to use safety monitors, or watchdogs. Our machinery enables two types of automated safety reasoning: (1) identification of which hazards can be controlled and which ones cannot be controlled by the existing safety patterns; and (2) automated recommendation of which patterns could be used at which place of the system to control potential hazards. Finally, we apply our machinery to two examples taken from the automotive domain: an adaptive cruise control system and a battery management system.
Approach-level models were developed to accommodate the diversity of approaches within the same intersection. A random effect term, which indicates the intersection-specific effect, was incorporated into each crash type model to deal with the spatial correlation between different approaches within the same intersection. The model parameters were estimated under the Bayesian framework. Results show that different crash types are correlated with different groups of factors, and each factor shows diverse effects on different crash types, which indicates the importance of crash type models. Besides, the significance of random effect term confirms the existence of spatial correlations among different approaches within the same intersection.
Estimating the states of surrounding traffic participants stays at the core of autonomous driving. In this paper, we study a novel setting of this problem: model-free single-object tracking (SOT), which takes the object state in the first frame as input, and jointly solves state estimation and tracking in subsequent frames. The main purpose for this new setting is to break the strong limitation of the popular detection and tracking scheme in multi-object tracking. Moreover, we notice that shape completion by overlaying the point clouds, which is a by-product of our proposed task, not only improves the performance of state estimation but also has numerous applications. As no benchmark for this task is available so far, we construct a new dataset LiDAR-SOT and corresponding evaluation protocols based on the Waymo Open dataset. We then propose an optimization-based algorithm called SOTracker involving point cloud registration, vehicle shapes, correspondence, and motion priors. Our quantitative and qualitative results prove the effectiveness of our SOTracker and reveal the challenging cases for SOT in point clouds, including the sparsity of LiDAR data, abrupt motion variation, etc. Finally, we also explore how the proposed task and algorithm may benefit other autonomous driving applications, including simulating LiDAR scans, generating motion data, and annotating optical flow. The code and protocols for our benchmark and algorithm are available at https://github.com/TuSimple/LiDAR_SOT/. A video demonstration is at https://www.youtube.com/watch?v=BpHixKs91i8.
Recently the European Union Agency for Railways (ERA) has received a mandate for the development of common safety methods for assessing the safety level and the safety performance of railway operators at national and Union level. Currently, several methods are under development. It is of interest how a possible candidate would behave and what would be the advantages and disadvantages of a particular method. In this paper, we study a version of the procedure. On the one hand side we analyze it based on the theory of mathematical statistics. As a result, we present a statistically efficient method the rate-ratio test based on a quantity that has smaller variance than the quantity handled by the ERA. Then, we support the theoretical results with the help of a simple simulation study in order to estimate failure probabilities of the first and second kinds. We construct such alternative distributions which the decision procedure cannot distinguish. We will show that the use of procedures that are optimal in the sense of mathematical statistics combined with the use of a characteristics that has small spread, here the number of accidents, is advantageous.
A consistent theme in software experimentation at Microsoft has been solving problems of experimentation at scale for a diverse set of products. Running experiments at scale (i.e., many experiments on many users) has become state of the art across the industry. However, providing a single platform that allows software experimentation in a highly heterogenous and constantly evolving ecosystem remains a challenge. In our case, heterogeneity spans multiple dimensions. First, we need to support experimentation for many types of products: websites, search engines, mobile apps, operating systems, cloud services and others. Second, due to the diversity of the products and teams using our platform, it needs to be flexible enough to analyze data in multiple compute fabrics (e.g. Spark, Azure Data Explorer), with a way to easily add support for new fabrics if needed. Third, one of the main factors in facilitating growth of experimentation culture in an organization is to democratize metric definition and analysis processes. To achieve that, our system needs to be simple enough to be used not only by data scientists, but also engineers, product managers and sales teams. Finally, different personas might need to use the platform for different types of analyses, e.g. dashboards or experiment analysis, and the platform should be flexible enough to accommodate that. This paper presents our solution to the problems of heterogeneity listed above.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
