Ensuring the quality of automated driving systems is a major challenge the automotive industry is facing. In this context, quality defines the degree to which an object meets expectations and requirements. Especially, automated vehicles at SAE level 4 and 5 will be expected to operate safely in various contexts and complex situations without misconduct. Thus, a systematic approach is needed to show their safe operation. A way to address this challenge is simulation-based testing as pure physical testing is not feasible. During simulation-based testing, the data used to evaluate the actual quality of an automated driving system are generated using a simulation. However, to rely on these simulation data, the overall simulation, which also includes its simulation models, must provide a certain quality level. This quality level depends on the intended purpose for which the generated simulation data should be used. Therefore, three categories of quality can be considered: quality of the automated driving system and simulation quality, consisting of simulation model quality and scenario quality. Hence, quality must be determined and evaluated in various process steps in developing and testing automated driving systems, the overall simulation, and the simulation models used for the simulation. In this paper, we propose a taxonomy to serve a better understanding of the concept of quality in the development and testing process to have a clear separation and insight where further testing is needed -- both in terms of automated driving systems and simulation, including their simulation models and scenarios used for testing.
相關內容
Decision support is the science and associated practice that consist in providing recommendations to decision makers facing problems, based on available theoretical knowledge and empirical data. Although this activity is often seen as being concerned with solving mathematical problems and conceiving algorithms, it is essentially an empirical and socially framed activity, where interactions between clients and analysts, and between them and concerned third parties, play a crucial role. Since the 80s, two concepts have structured the literature devoted to analysing this aspect of decision support: validity and legitimacy. Whereas validity is focused on the interactions between the client and the analyst, legitimacy refers to the broader picture: the organisational context, the overall problem situation, the environment, culture, history. Despite its importance, this concept has not received the attention it deserves in the literature in decision support. The present paper aims at filling this gap. For that purpose, we review the literature in other disciplines relevant to elaborate a concept of legitimacy useful in decision support contexts. Based on this review, we propose a general theory of legitimacy, adapted to decision support contexts, encompassing the relevant contributions we found in the literature. According to this general theory, a legitimate decision support intervention is one for which the decision support provider produces a justification that satisfies two conditions: (i) it effectively convinces the decision support provider's interlocutors (effectiveness condition) and (ii) it is organised around the active elicitation of as many and as diverse counterarguments as possible (truthfulness condition). Despite its conceptual simplicity, legitimacy, understood in this sense, is a very exacting requirement, opening ambitious research avenues that we delineate.
In Vitro Fertilization (IVF) is the most widely used Assisted Reproductive Technology (ART). IVF usually involves controlled ovarian stimulation, oocyte retrieval, fertilization in the laboratory with subsequent embryo transfer. The first two steps correspond with follicular phase of females and ovulation in their menstrual cycle. Therefore, we refer to it as the treatment cycle in our paper. The treatment cycle is crucial because the stimulation medications in IVF treatment are applied directly on patients. In order to optimize the stimulation effects and lower the side effects of the stimulation medications, prompt treatment adjustments are in need. In addition, the quality and quantity of the retrieved oocytes have a significant effect on the outcome of the following procedures. To improve the IVF success rate, we propose a knowledge-based decision support system that can provide medical advice on the treatment protocol and medication adjustment for each patient visit during IVF treatment cycle. Our system is efficient in data processing and light-weighted which can be easily embedded into electronic medical record systems. Moreover, an oocyte retrieval oriented evaluation demonstrates that our system performs well in terms of accuracy of advice for the protocols and medications.
[Context and motivation] For automated driving systems, the operational context needs to be known in order to state guarantees on performance and safety. The operational design domain (ODD) is an abstraction of the operational context, and its definition is an integral part of the system development process. [Question / problem] There are still major uncertainties in how to clearly define and document the operational context in a diverse and distributed development environment such as the automotive industry. This case study investigates the challenges with context definitions for the development of perception functions that use machine learning for automated driving. [Principal ideas/results] Based on qualitative analysis of data from semi-structured interviews, the case study shows that there is a lack of standardisation for context definitions across the industry, ambiguities in the processes that lead to deriving the ODD, missing documentation of assumptions about the operational context, and a lack of involvement of function developers in the context definition. [Contribution] The results outline challenges experienced by an automotive supplier company when defining the operational context for systems using machine learning. Furthermore, the study collected ideas for potential solutions from the perspective of practitioners.
Future Tele-operated Driving (ToD) applications place challenging Quality of Service (QoS) demands on existing mobile communication networks that are of highly important to comply with for safe operation. New remote control and platooning services will emerge and pose high data rate and latency requirements. One key enabler for these applications is the newly available 5G New Radio (NR) promising higher bandwidth and lower latency than its predecessors. In addition to that, public 5G networks do not consistently deliver and do not guarantee the required data rates and latency of ToD. In this paper, we discuss the communication-related requirements of tele-operated driving. ToD is regarded as a complex system consisting of multiple research areas. One key aspect of ToD is the provision and maintenance of the required data rate for teleoperation by the mobile network. An in-advance prediction method of the end-to-end data rate based on so-called Radio Environmental Maps (REMs) is discussed. Furthermore, a novel approach improving the prediction accuracy is introduced and it features individually optimized REM layers. Finally, we analyze the implementation of tele-operated driving applications on a scaled vehicular platform combined with a cyber-physical test environment consisting of real and virtual objects. This approach enables large-scale testing of remote operation and autonomous applications.
Manually monitoring water quality is very exhausting and requires several hours of sampling and laboratory testing for a particular body of water. This article presents a solution to test water properties like electrical conductivity and pH with a remote-controlled floating vehicle that minimizes time intervals. An autonomous surface vehicle (ASV) has been designed mathematically and operated via MATLAB \& Simulink simulation where the Proportional integral derivative (PID) controller has been considered. A PVC model with Small waterplane area twin-hull (SWATH) technology is used to develop this vehicle. Manually collected data is compared to online sensors, suggesting a better solution for determining water properties such as dissolved oxygen (DO), biochemical oxygen demand (BOD), temperature, conductivity, total alkalinity, and bacteria. Preliminary computational results show the promising result, as Sungai Pasu rivers tested water falls in the safe range of pH (~6.8-7.14) using the developed ASV.
We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog, which have up to 137B parameters and are pre-trained on 1.56T words of public dialog data and web text. While model scaling alone can improve quality, it shows less improvements on safety and factual grounding. We demonstrate that fine-tuning with annotated data and enabling the model to consult external knowledge sources can lead to significant improvements towards the two key challenges of safety and factual grounding. The first challenge, safety, involves ensuring that the model's responses are consistent with a set of human values, such as preventing harmful suggestions and unfair bias. We quantify safety using a metric based on an illustrative set of human values, and we find that filtering candidate responses using a LaMDA classifier fine-tuned with a small amount of crowdworker-annotated data offers a promising approach to improving model safety. The second challenge, factual grounding, involves enabling the model to consult external knowledge sources, such as an information retrieval system, a language translator, and a calculator. We quantify factuality using a groundedness metric, and we find that our approach enables the model to generate responses grounded in known sources, rather than responses that merely sound plausible. Finally, we explore the use of LaMDA in the domains of education and content recommendations, and analyze their helpfulness and role consistency.
Autonomous driving has achieved a significant milestone in research and development over the last decade. There is increasing interest in the field as the deployment of self-operating vehicles on roads promises safer and more ecologically friendly transportation systems. With the rise of computationally powerful artificial intelligence (AI) techniques, autonomous vehicles can sense their environment with high precision, make safe real-time decisions, and operate more reliably without human interventions. However, intelligent decision-making in autonomous cars is not generally understandable by humans in the current state of the art, and such deficiency hinders this technology from being socially acceptable. Hence, aside from making safe real-time decisions, the AI systems of autonomous vehicles also need to explain how these decisions are constructed in order to be regulatory compliant across many jurisdictions. Our study sheds a comprehensive light on developing explainable artificial intelligence (XAI) approaches for autonomous vehicles. In particular, we make the following contributions. First, we provide a thorough overview of the present gaps with respect to explanations in the state-of-the-art autonomous vehicle industry. We then show the taxonomy of explanations and explanation receivers in this field. Thirdly, we propose a framework for an architecture of end-to-end autonomous driving systems and justify the role of XAI in both debugging and regulating such systems. Finally, as future research directions, we provide a field guide on XAI approaches for autonomous driving that can improve operational safety and transparency towards achieving public approval by regulators, manufacturers, and all engaged stakeholders.
Understanding what online users may pay attention to is key to content recommendation and search services. These services will benefit from a highly structured and web-scale ontology of entities, concepts, events, topics and categories. While existing knowledge bases and taxonomies embody a large volume of entities and categories, we argue that they fail to discover properly grained concepts, events and topics in the language style of online population. Neither is a logically structured ontology maintained among these notions. In this paper, we present GIANT, a mechanism to construct a user-centered, web-scale, structured ontology, containing a large number of natural language phrases conforming to user attentions at various granularities, mined from a vast volume of web documents and search click graphs. Various types of edges are also constructed to maintain a hierarchy in the ontology. We present our graph-neural-network-based techniques used in GIANT, and evaluate the proposed methods as compared to a variety of baselines. GIANT has produced the Attention Ontology, which has been deployed in various Tencent applications involving over a billion users. Online A/B testing performed on Tencent QQ Browser shows that Attention Ontology can significantly improve click-through rates in news recommendation.
There has been considerable growth and interest in industrial applications of machine learning (ML) in recent years. ML engineers, as a consequence, are in high demand across the industry, yet improving the efficiency of ML engineers remains a fundamental challenge. Automated machine learning (AutoML) has emerged as a way to save time and effort on repetitive tasks in ML pipelines, such as data pre-processing, feature engineering, model selection, hyperparameter optimization, and prediction result analysis. In this paper, we investigate the current state of AutoML tools aiming to automate these tasks. We conduct various evaluations of the tools on many datasets, in different data segments, to examine their performance, and compare their advantages and disadvantages on different test cases.
Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions. Recent studies show that adversarial examples can pose a threat to real-world security-critical applications: a "physical adversarial Stop Sign" can be synthesized such that the autonomous driving cars will misrecognize it as others (e.g., a speed limit sign). However, these image-space adversarial examples cannot easily alter 3D scans of widely equipped LiDAR or radar on autonomous vehicles. In this paper, we reveal the potential vulnerabilities of LiDAR-based autonomous driving detection systems, by proposing an optimization based approach LiDAR-Adv to generate adversarial objects that can evade the LiDAR-based detection system under various conditions. We first show the vulnerabilities using a blackbox evolution-based algorithm, and then explore how much a strong adversary can do, using our gradient-based approach LiDAR-Adv. We test the generated adversarial objects on the Baidu Apollo autonomous driving platform and show that such physical systems are indeed vulnerable to the proposed attacks. We also 3D-print our adversarial objects and perform physical experiments to illustrate that such vulnerability exists in the real world. Please find more visualizations and results on the anonymous website: //sites.google.com/view/lidar-adv.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191