自主智能系统(英文)最新文献

In this paper, we present a continuous-time algorithm with a dynamic event-triggered communication (DETC) mechanism for solving a class of distributed convex optimization problems that satisfy a metric subregularity condition. The proposed algorithm addresses the challenge of limited bandwidth in multi-agent systems by utilizing a continuous-time optimization approach with DETC. Furthermore, we prove that the distributed event-triggered algorithm converges exponentially to the optimal set, even without strong convexity conditions. Finally, we provide a comparison example to demonstrate the efficiency of our algorithm in communication resource-saving.

With the aim to enhance prediction accuracy for nonlinear time series, this paper put forward an improved deep Echo State Network based on reservoir states reconstruction driven by a Self-Normalizing Activation (SNA) function as the replacement for the traditional Hyperbolic tangent activation function to reduce the model’s sensitivity to hyper-parameters. The Strategy was implemented in a two-state reconstruction process by first inputting the time series data to the model separately. Once, the time data passes through the reservoirs and is activated by the SNA activation function, the new state for the reservoirs is created. The state is input to the next layer, and the concatenate states module saves. Pairs of states are selected from the activated multi-layer reservoirs and input into the state reconstruction module. Multiple input states are transformed through the state reconstruction module and finally saved to the concatenate state module. Two evaluation metrics were used to benchmark against three other ESNs with SNA activation functions to achieve better prediction accuracy.

With the tremendous success of machine learning (ML), concerns about their black-box nature have grown. The issue of interpretability affects trust in ML systems and raises ethical concerns such as algorithmic bias. In recent years, the feature attribution explanation method based on Shapley value has become the mainstream explainable artificial intelligence approach for explaining ML models. This paper provides a comprehensive overview of Shapley value-based attribution methods. We begin by outlining the foundational theory of Shapley value rooted in cooperative game theory and discussing its desirable properties. To enhance comprehension and aid in identifying relevant algorithms, we propose a comprehensive classification framework for existing Shapley value-based feature attribution methods from three dimensions: Shapley value type, feature replacement method, and approximation method. Furthermore, we emphasize the practical application of the Shapley value at different stages of ML model development, encompassing pre-modeling, modeling, and post-modeling phases. Finally, this work summarizes the limitations associated with the Shapley value and discusses potential directions for future research.

The future of driving is autonomous. It requires a comprehensive stack of embedded software components, enabled by open-source and proprietary platforms at different abstraction layers, and then operating within a larger ecosystem. Autonomous driving demands connectivity, cooperation and automation to form the cornerstone of autonomous mobility solutions. Platform economy principles have revolutionized the way we produce, deliver and consume products and services worldwide. More and more businesses in the field of mobility and transport appear to implement transaction, innovation, and integration platforms as core enablers for Mobility-as-a-Service and transport applications. Artificial intelligence approaches, especially those dealing with distributed systems, enable new mobility solutions, such as autonomous driving. This paper contributes to understanding the intertwining role between distributed artificial intelligence, autonomous mobility and the resulting platform ecosystem. A systematic literature review is applied, in order to identify the intersection between those aspects. Furthermore, the research project BeIntelli is considered as a hands-on application of our findings. Taking into account our analysis and the aforementioned research project, we pose a blueprint architecture for autonomous mobility. This architecture is the subject of further research. Our conclusions facilitate the development and implementation of future urban transportation systems and resulting mobility ecosystems in practice.

Current studies in few-shot semantic segmentation mostly utilize meta-learning frameworks to obtain models that can be generalized to new categories. However, these models trained on base classes with sufficient annotated samples are biased towards these base classes, which results in semantic confusion and ambiguity between base classes and new classes. A strategy is to use an additional base learner to recognize the objects of base classes and then refine the prediction results output by the meta learner. In this way, the interaction between these two learners and the way of combining results from the two learners are important. This paper proposes a new model, namely Distilling Base and Meta (DBAM) network by using self-attention mechanism and contrastive learning to enhance the few-shot segmentation performance. First, the self-attention-based ensemble module (SEM) is proposed to produce a more accurate adjustment factor for improving the fusion of two predictions of the two learners. Second, the prototype feature optimization module (PFOM) is proposed to provide an interaction between the two learners, which enhances the ability to distinguish the base classes from the target class by introducing contrastive learning loss. Extensive experiments have demonstrated that our method improves on the PASCAL-5ⁱ under 1-shot and 5-shot settings, respectively.

In response to the impact of COVID-19, the manufacturing industry and academic industrial research have largely shifted to online or hybrid conference formats. The sudden change has posed challenges for researchers and teams to adapt. Based on the current state of online conferences, inadequate communication, disruptions during meetings, confusion and loss of meeting information, and difficulties in conducting online collaborations are observed. This paper presents a design of a real-time discussion board that combines online conferences and synchronous discussions to address the issues arising from remote collaborations in industrial research. The research demonstrates that synchronous discussions conducted within multi-team industrial collaboration teams with specific and diverse issues can better control the flow of meetings, enhance meeting efficiency, promote participant interaction and engagement, reduce information loss, and weaken the boundaries between online and offline collaboration.

With the increasing number of space satellites, the demand for satellite communication (including maneuvering, command uploading and data downloading) has also grown significantly. However, the actual communication resources of ground station are relatively limited, which leads to an oversubscribed problem. How to make use of limited ground station resources to complete satellite communication requests more fully and efficiently in the strict visible time is the focus of satellite range scheduling research. This paper reviews and looks forward to the research on Satellite Range Scheduling Problem (SRSP). Firstly, SRSP is defined as the scheduling problem of establishing communication between satellites and ground stations, and the classification and development of SRSP are introduced. Then, this paper analyzes three common problem description models, and establishes a mathematical model based on the analysis of optimization objectives and constraints. Thirdly, this paper classifies and summarizes the common solving methods of SRSP, and analyzes their characteristics and application scenarios. Finally, combined with the work in this paper, the future research direction of SRSP is envisioned.

Because the number of clustering cores needs to be set before implementing the K-means algorithm, this type of algorithm often fails in applications with increasing data and changing distribution characteristics. This paper proposes an evolutionary algorithm DCC, which can dynamically adjust the number of clustering cores with data change. DCC algorithm uses the Gaussian function as the activation function of each core. Each clustering core can adjust its center vector and coverage based on the response to the input data and its memory state to better fit the sample clusters in the space. The DCC algorithm model can evolve from 0. After each new sample is added, the winning dynamic core can be adjusted or split by competitive learning, so that the number of clustering cores of the algorithm always maintains a better adaptation relationship with the existing data. Furthermore, because its clustering core can split, it can subdivide the densely distributed data clusters. Finally, detailed experimental results show that the evolutionary clustering algorithm DCC based on the dynamic core method has excellent clustering performance and strong robustness.

Although the pick-up/drop-off (PUDO) strategy in carpooling offers the convenience of short-distance walking for passengers during boarding and disembarking, there is a noticeable hesitancy among commuters to adopt this travel method, despite its numerous benefits. Here, this paper establishes a tripartite evolutionary game theory (EGT) model to verify the evolutionary stability of choosing the PUDO strategy of drivers and passengers and offering subsidies strategy of carpooling platforms in carpooling system. The model presented in this paper serves as a valuable tool for assessing the dissemination and implementation of PUDO strategy and offering subsidies strategy in carpooling applications. Subsequently, an empirical analysis is conducted to examine and compare the sensitivity of the parameters across various scenarios. The findings suggest that: firstly, providing subsidies to passengers and drivers, along with deductions for drivers through carpooling platforms, is an effective way to promote wider adoption of the PUDO strategy. Then, the decision-making process is divided into three stages: initial stage, middle stage, and mature stage. PUDO strategy progresses from initial rejection to widespread acceptance among drivers in the middle stage and, in the mature stage, both passengers and drivers tend to adopt it under carpooling platform subsidies; the factors influencing the costs of waiting and walking times, as well as the subsidies granted to passengers, are essential determinants that require careful consideration by passengers, drivers, and carpooling platforms when choosing the PUDO strategy. Our work provides valuable insight into the PUDO strategy’s applicability and the declared results provide implications for traffic managers and carpooling platforms to offer a suitable incentive.

In this paper, the formation control problem for a multi-agent system is studied. Two new robust control algorithms for serial and parallel formations respectively are proposed, which take the constraints of limited field of view into consideration. Without the need for any global information, the only relative information required is distance and bearing angle, thus is easy to implement with onboard directional sensors. It is then demonstrated how complex formations can be realized by combining the proposed basic controllers. Finally, effectiveness of the proposed algorithms is illustrated by numerical examples.