Related papers: HoNVis: Visualizing and Exploring Higher-Order Net…
This paper proposes a supervised machine learning framework for the non-intrusive model order reduction of unsteady fluid flows to provide accurate predictions of non-stationary state variables when the control parameter values vary. Our…
The process of visually presenting networks is an effective way to understand entity relationships within the networks since it reveals the overall structure and topology of the network. Real networks are extremely difficult to visualize…
Ad hoc networks rely on the cooperation of the nodes participating in the network to forward packets for each other. A node may decide not to cooperate to save its resources while still using the network to relay its traffic. If too many…
Transportation networks play a crucial role in human mobility, the exchange of goods, and the spread of invasive species. With 90% of world trade carried by sea, the global network of merchant ships provides one of the most important modes…
Data-driven modeling of spatiotemporal physical processes with general deep learning methods is a highly challenging task. It is further exacerbated by the limited availability of data, leading to poor generalizations in standard neural…
Understanding how humans interact with the surrounding environment, and specifically reasoning about object interactions and affordances, is a critical challenge in computer vision, robotics, and AI. Current approaches often depend on…
The recently proposed network model, Operational Neural Networks (ONNs), can generalize the conventional Convolutional Neural Networks (CNNs) that are homogenous only with a linear neuron model. As a heterogenous network model, ONNs are…
Common deep neural networks (DNNs) for image classification have been shown to rely on shortcut opportunities (SO) in the form of predictive and easy-to-represent visual factors. This is known as shortcut learning and leads to impaired…
Advancements in deep learning enable cloud servers to provide inference-as-a-service for clients. In this scenario, clients send their raw data to the server to run the deep learning model and send back the results. One standing challenge…
Vision-Language Navigation requires the agent to follow natural language instructions to reach a specific target. The large discrepancy between seen and unseen environments makes it challenging for the agent to generalize well. Previous…
Military and disaster relief operations increasingly rely on unmanned vehicles (UxVs). It is important to develop a network control system (NCS) that can continuously coordinate and optimize the movement of UxVs based on mission objectives.…
Despite significant advances in Graph Neural Networks (GNNs), their limited expressivity remains a fundamental challenge. Research on GNN expressivity has produced many expressive architectures, leading to architecture hierarchies with…
Fast, collision-free motion through unknown environments remains a challenging problem for robotic systems. In these situations, the robot's ability to reason about its future motion is often severely limited by sensor field of view (FOV).…
Object goal navigation (ObjectNav) in unseen environments is a fundamental task for Embodied AI. Agents in existing works learn ObjectNav policies based on 2D maps, scene graphs, or image sequences. Considering this task happens in 3D…
Deep neural networks (DNNs) can be useful within the marine robotics field, but their utility value is restricted by their black-box nature. Explainable artificial intelligence methods attempt to understand how such black-boxes make their…
Vehicle-based mobile sensing is an emerging data collection paradigm that leverages vehicle mobilities to scan a city at low costs. Certain urban sensing scenarios require dedicated vehicles for highly targeted monitoring, such as volatile…
The main challenge in vision-and-language navigation (VLN) is how to understand natural-language instructions in an unseen environment. The main limitation of conventional VLN algorithms is that if an action is mistaken, the agent fails to…
Network-wide traffic flow, which captures dynamic traffic volume on each link of a general network, is fundamental to smart mobility applications. However, the observed traffic flow from sensors is usually limited across the entire network…
The demand for mobile robots has rapidly increased in recent years due to the flexibility and high variety of application fields comparing to static robots. To deal with complex tasks such as navigation, they work with high amounts of…
Navigating autonomous underwater vehicles (AUVs) in unknown environments is significantly challenging due to poor visibility, weak signal transmission, and dynamic water currents. These factors pose challenges in accurate global…