Related papers: Vision-based route following by an embodied insect…

Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers.…

Recently, sparse training methods have started to be established as a de facto approach for training and inference efficiency in artificial neural networks. Yet, this efficiency is just in theory. In practice, everyone uses a binary mask to…

In this paper, we introduce a novel method to capture visual trajectories for navigating an indoor robot in dynamic settings using streaming image data. First, an image processing pipeline is proposed to accurately segment trajectories from…

Efficient spatial navigation is a hallmark of the mammalian brain, inspiring the development of neuromorphic systems that mimic biological principles. Despite progress, implementing key operations like back-tracing and handling ambiguity in…

Recently, neural control policies have outperformed existing model-based planning-and-control methods for autonomously navigating quadrotors through cluttered environments in minimum time. However, they are not perception aware, a crucial…

Catching objects in-flight is an outstanding challenge in robotics. In this paper, we present a closed-loop control system fusing data from two sensor modalities: an RGB-D camera and a radar. To develop and test our method, we start with an…

Structured prediction is often approached by training a locally normalized model with maximum likelihood and decoding approximately with beam search. This approach leads to mismatches as, during training, the model is not exposed to its…

Graph embedding is gaining its popularity for link prediction in complex networks and achieving excellent performance. However, limited work has been done in sparse networks that represent most of real networks. In this paper, we propose a…

Motivated by distributed machine learning settings such as Federated Learning, we consider the problem of fitting a statistical model across a distributed collection of heterogeneous data sets whose similarity structure is encoded by a…

Event-based vision has already revolutionized the perception task for robots by promising faster response, lower energy consumption, and lower bandwidth without introducing motion blur. In this work, a novel deep learning method based on…

Tabular datasets are widely used in scientific disciplines such as biology. While these disciplines have already adopted AI methods to enhance their findings and analysis, they mainly use tree-based methods due to their interpretability. At…

Recent work showed that hybrid networks, which combine predefined and learnt filters within a single architecture, are more amenable to theoretical analysis and less prone to overfitting in data-limited scenarios. However, their performance…

This paper presents a data-driven approach to learning vision-based collective behavior from a simple flocking algorithm. We simulate a swarm of quadrotor drones and formulate the controller as a regression problem in which we generate 3D…

Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…

We characterize the connectivity structure of feed-forward, deep neural networks (DNNs) using network motif theory. To address whether a particular motif distribution is characteristic of the training task, or function of the DNN, we…

We address the problem of reconstructing sparse signals from noisy and compressive measurements using a feed-forward deep neural network (DNN) with an architecture motivated by the iterative shrinkage-thresholding algorithm (ISTA). We…

Autonomous tracking of flying aerial objects has important civilian and defense applications, ranging from search and rescue to counter-unmanned aerial systems (counter-UAS). Ground based tracking requires setting up infrastructure, could…

If modern computers are sometimes superior to humans in some specialized tasks such as playing chess or browsing a large database, they can't beat the efficiency of biological vision for such simple tasks as recognizing and following an…

Recent applications of deep learning to navigation have generated end-to-end navigation solutions whereby visual sensor input is mapped to control signals or to motion primitives. The resulting visual navigation strategies work very well at…

Hashing is one of the most popular methods for similarity search because of its speed and efficiency. Dense binary hashing is prevalent in the literature. Recently, insect olfaction was shown to be structurally and functionally analogous to…