Asynchronous frameworks for distributed embedded systems, like ROS and MQTT, are increasingly used in safety-critical applications such as autonomous driving, where the cost of unintended behavior is high. The coordination mechanism between the components in these frameworks, however, gives rise to nondeterminism, where factors such as communication timing can lead to arbitrary ordering in the handling of messages. In this paper, we demonstrate the significance of this problem in an open-source full-stack autonomous driving software, Autoware.Auto 1.0, which relies on ROS 2. We give an alternative: Xronos, an open-source framework for distributed embedded systems that has a novel coordination strategy with predictable properties under clearly stated assumptions. If these assumptions are violated, Xronos provides for application-specific fault handlers to be invoked. We port Autoware.Auto to Xronos and show that it avoids the identified problems with manageable cost in end-to-end latency. Furthermore, we compare the maximum throughput of Xronos to ROS 2 and MQTT using microbenchmarks under different settings, including on three different hardware configurations, and find that it can match or exceed those frameworks in terms of throughput.
相關內容
Vehicular communication is an essential part of a smart city. Scalability is a major issue for vehicular communication, specially, when the number of vehicles increases at any given point. Vehicles also suffer some other problems such as broadcast problem. Clustering can solve the issues of vehicular ad hoc network (VANET); however, due to the high mobility of the vehicles, clustering in VANET suffers stability issue. Previously proposed clustering algorithms for VANET are optimized for either straight road or for intersection. Moreover, the absence of the intelligent use of a combination of the mobility parameters, such as direction, movement, position, velocity, degree of vehicle, movement at the intersection etc., results in cluster stability issues. A dynamic clustering algorithm considering the efficient use of all the mobility parameters can solve the stability problem in VANET. To achieve higher stability for VANET, a novel robust and dynamic clustering algorithm stable dynamic predictive clustering (SDPC) for VANET is proposed in this paper. In contrast to previous studies, vehicle relative velocity, vehicle position, vehicle distance, transmission range, and vehicle density are considered in the creation of a cluster, whereas relative distance, movement at the intersection, degree of vehicles are considered to select the cluster head. From the mobility parameters the future road scenario is constructed. The cluster is created, and the cluster head is selected based on the future construction of the road. The performance of SDPC is compared in terms of the average cluster head change rate, the average cluster head duration, the average cluster member duration, and the ratio of clustering overhead in terms of total packet transmission. The simulation result shows SDPC outperforms the existing algorithms and achieved better clustering stability.
In recent years, deep learning has been a topic of interest in almost all disciplines due to its impressive empirical success in analyzing complex data sets, such as imaging, genetics, climate, and medical data. While most of the developments are treated as black-box machines, there is an increasing interest in interpretable, reliable, and robust deep learning models applicable to a broad class of applications. Feature-selected deep learning is proven to be promising in this regard. However, the recent developments do not address the situations of ultra-high dimensional and highly correlated feature selection in addition to the high noise level. In this article, we propose a novel screening and cleaning strategy with the aid of deep learning for the cluster-level discovery of highly correlated predictors with a controlled error rate. A thorough empirical evaluation over a wide range of simulated scenarios demonstrates the effectiveness of the proposed method by achieving high power while having a minimal number of false discoveries. Furthermore, we implemented the algorithm in the riboflavin (vitamin $B_2$) production dataset in the context of understanding the possible genetic association with riboflavin production. The gain of the proposed methodology is illustrated by achieving lower prediction error compared to other state-of-the-art methods.
Clustering is an important exploratory data analysis technique to group objects based on their similarity. The widely used $K$-means clustering method relies on some notion of distance to partition data into a fewer number of groups. In the Euclidean space, centroid-based and distance-based formulations of the $K$-means are equivalent. In modern machine learning applications, data often arise as probability distributions and a natural generalization to handle measure-valued data is to use the optimal transport metric. Due to non-negative Alexandrov curvature of the Wasserstein space, barycenters suffer from regularity and non-robustness issues. The peculiar behaviors of Wasserstein barycenters may make the centroid-based formulation fail to represent the within-cluster data points, while the more direct distance-based $K$-means approach and its semidefinite program (SDP) relaxation are capable of recovering the true cluster labels. In the special case of clustering Gaussian distributions, we show that the SDP relaxed Wasserstein $K$-means can achieve exact recovery given the clusters are well-separated under the $2$-Wasserstein metric. Our simulation and real data examples also demonstrate that distance-based $K$-means can achieve better classification performance over the standard centroid-based $K$-means for clustering probability distributions and images.
Cyber-physical systems (CPSs) are usually complex and safety-critical; hence, it is difficult and important to guarantee that the system's requirements, i.e., specifications, are fulfilled. Simulation-based falsification of CPSs is a practical testing method that can be used to raise confidence in the correctness of the system by only requiring that the system under test can be simulated. As each simulation is typically computationally intensive, an important step is to reduce the number of simulations needed to falsify a specification. We study Bayesian optimization (BO), a sample-efficient method that learns a surrogate model that describes the relationship between the parametrization of possible input signals and the evaluation of the specification. In this paper, we improve the falsification using BO by; first adopting two prominent BO methods, one fits local surrogate models, and the other exploits the user's prior knowledge. Secondly, the formulation of acquisition functions for falsification is addressed in this paper. Benchmark evaluation shows significant improvements in using local surrogate models of BO for falsifying benchmark examples that were previously hard to falsify. Using prior knowledge in the falsification process is shown to be particularly important when the simulation budget is limited. For some of the benchmark problems, the choice of acquisition function clearly affects the number of simulations needed for successful falsification.
Edge computing has become a popular paradigm where services and applications are deployed at the network edge closer to the data sources. It provides applications with outstanding benefits, including reduced response latency and enhanced privacy protection. For emerging advanced applications, such as autonomous vehicles, industrial IoT, and metaverse, further research is needed. This is because such applications demand ultra-low latency, hyper-connectivity, and dynamic and reliable service provision, while existing approaches are inadequate to address the new challenges. Hence, we envision that the future edge computing is moving towards distributed intelligence, where heterogeneous edge nodes collaborate to provide services in large-scale and geo-distributed edge infrastructure. We thereby propose Edge-as-a-Service (EaaS) to enable distributed intelligence. EaaS jointly manages large-scale cross-node edge resources and facilitates edge autonomy, edge-to-edge collaboration, and resource elasticity. These features enable flexible deployment of services and ubiquitous computation and intelligence. We first give an overview of existing edge computing studies and discuss their limitations to articulate the motivation for proposing EaaS. Then, we describe the details of EaaS, including the physical architecture, proposed software framework, and benefits of EaaS. Various application scenarios, such as real-time video surveillance, smart building, and metaverse, are presented to illustrate the significance and potential of EaaS. Finally, we discuss several challenging issues of EaaS to inspire more research towards this new edge computing framework.
Effective surveillance on the long-term public health impact due to war and terrorist attacks remain limited. Such health issues are commonly under-reported, specifically for a large group of individuals. For this purpose, efficient estimation of the size of the population under the risk of physical and mental health hazards is of utmost necessity. In this context, multiple system estimation is a potential strategy that has recently been applied to quantify under-reported events allowing heterogeneity among the individuals and dependence between the sources of information. To model such complex phenomena, a novel trivariate Bernoulli model is developed, and an estimation methodology using Monte Carlo based EM algorithm is proposed which successfully overcomes the identifiability issue present in the model. Simulation results show superiority of the performance of the proposed method over existing competitors and robustness under model mis-specifications. The method is applied to analyze real case studies on the Gulf War and 9/11 Terrorist Attack at World Trade Center, US. Estimates of the incident rate and survival rate are computed by adjusting the undercount estimates for an unbiased evaluation of the post-war syndromes. The results provide interesting insights that can assist in effective decision making and policy formulation for monitoring the health status of post-war survivors.
When is heterogeneity in the composition of an autonomous robotic team beneficial and when is it detrimental? We investigate and answer this question in the context of a minimally viable model that examines the role of heterogeneous speeds in perimeter defense problems, where defenders share a total allocated speed budget. We consider two distinct problem settings and develop strategies based on dynamic programming and on local interaction rules. We present a theoretical analysis of both approaches and our results are extensively validated using simulations. Interestingly, our results demonstrate that the viability of heterogeneous teams depends on the amount of information available to the defenders. Moreover, our results suggest a universality property: across a wide range of problem parameters the optimal ratio of the speeds of the defenders remains nearly constant.
Effective multi-robot teams require the ability to move to goals in complex environments in order to address real-world applications such as search and rescue. Multi-robot teams should be able to operate in a completely decentralized manner, with individual robot team members being capable of acting without explicit communication between neighbors. In this paper, we propose a novel game theoretic model that enables decentralized and communication-free navigation to a goal position. Robots each play their own distributed game by estimating the behavior of their local teammates in order to identify behaviors that move them in the direction of the goal, while also avoiding obstacles and maintaining team cohesion without collisions. We prove theoretically that generated actions approach a Nash equilibrium, which also corresponds to an optimal strategy identified for each robot. We show through extensive simulations that our approach enables decentralized and communication-free navigation by a multi-robot system to a goal position, and is able to avoid obstacles and collisions, maintain connectivity, and respond robustly to sensor noise.
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Explaining, in a human-understandable way, the relationship between the input and output of machine learning models is essential to the development of trustworthy machine-learning-based systems. A burgeoning body of research seeks to define the goals and methods of explainability in machine learning. In this paper, we seek to review and categorize research on counterfactual explanations, a specific class of explanation that provides a link between what could have happened had input to a model been changed in a particular way. Modern approaches to counterfactual explainability in machine learning draw connections to the established legal doctrine in many countries, making them appealing to fielded systems in high-impact areas such as finance and healthcare. Thus, we design a rubric with desirable properties of counterfactual explanation algorithms and comprehensively evaluate all currently-proposed algorithms against that rubric. Our rubric provides easy comparison and comprehension of the advantages and disadvantages of different approaches and serves as an introduction to major research themes in this field. We also identify gaps and discuss promising research directions in the space of counterfactual explainability.
Graph representation learning for hypergraphs can be used to extract patterns among higher-order interactions that are critically important in many real world problems. Current approaches designed for hypergraphs, however, are unable to handle different types of hypergraphs and are typically not generic for various learning tasks. Indeed, models that can predict variable-sized heterogeneous hyperedges have not been available. Here we develop a new self-attention based graph neural network called Hyper-SAGNN applicable to homogeneous and heterogeneous hypergraphs with variable hyperedge sizes. We perform extensive evaluations on multiple datasets, including four benchmark network datasets and two single-cell Hi-C datasets in genomics. We demonstrate that Hyper-SAGNN significantly outperforms the state-of-the-art methods on traditional tasks while also achieving great performance on a new task called outsider identification. Hyper-SAGNN will be useful for graph representation learning to uncover complex higher-order interactions in different applications.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191