Intelligent vehicle anticipation of the movement intentions of other drivers can reduce collisions. Typically, when a human driver of another vehicle (referred to as the target vehicle) engages in specific behaviors such as checking the rearview mirror prior to lane change, a valuable clue is therein provided on the intentions of the target vehicle's driver. Furthermore, the target driver's intentions can be influenced and shaped by their driving environment. For example, if the target vehicle is too close to a leading vehicle, it may renege the lane change decision. On the other hand, a following vehicle in the target lane is too close to the target vehicle could lead to its reversal of the decision to change lanes. Knowledge of such intentions of all vehicles in a traffic stream can help enhance traffic safety. Unfortunately, such information is often captured in the form of images/videos. Utilization of personally identifiable data to train a general model could violate user privacy. Federated Learning (FL) is a promising tool to resolve this conundrum. FL efficiently trains models without exposing the underlying data. This paper introduces a Personalized Federated Learning (PFL) model embedded a long short-term transformer (LSTR) framework. The framework predicts drivers' intentions by leveraging in-vehicle videos (of driver movement, gestures, and expressions) and out-of-vehicle videos (of the vehicle's surroundings - frontal/rear areas). The proposed PFL-LSTR framework is trained and tested through real-world driving data collected from human drivers at Interstate 65 in Indiana. The results suggest that the PFL-LSTR exhibits high adaptability and high precision, and that out-of-vehicle information (particularly, the driver's rear-mirror viewing actions) is important because it helps reduce false positives and thereby enhances the precision of driver intention inference.
相關內容
We observe a large variety of robots in terms of their bodies, sensors, and actuators. Given the commonalities in the skill sets, teaching each skill to each different robot independently is inefficient and not scalable when the large variety in the robotic landscape is considered. If we can learn the correspondences between the sensorimotor spaces of different robots, we can expect a skill that is learned in one robot can be more directly and easily transferred to the other robots. In this paper, we propose a method to learn correspondences between robots that have significant differences in their morphologies: a fixed-based manipulator robot with joint control and a differential drive mobile robot. For this, both robots are first given demonstrations that achieve the same tasks. A common latent representation is formed while learning the corresponding policies. After this initial learning stage, the observation of a new task execution by one robot becomes sufficient to generate a latent space representation pertaining to the other robot to achieve the same task. We verified our system in a set of experiments where the correspondence between two simulated robots is learned (1) when the robots need to follow the same paths to achieve the same task, (2) when the robots need to follow different trajectories to achieve the same task, and (3) when complexities of the required sensorimotor trajectories are different for the robots considered. We also provide a proof-of-the-concept realization of correspondence learning between a real manipulator robot and a simulated mobile robot.
The coordination of autonomous vehicles is an open field that is addressed by different researches comprising many different techniques. In this paper we focus on decentralized approaches able to provide adaptability to different infrastructural and traffic conditions. We formalize an Emergent Behavior Approach that, as per our knowledge, has never been performed for this purpose, and a Decentralized Auction approach. We compare them against existing centralized negotiation approaches based on auctions and we determine under which conditions each approach is preferable to the others.
We explain the methodology used to create the data submitted to HuMob Challenge, a data analysis competition for human mobility prediction. We adopted a personalized model to predict the individual's movement trajectory from their data, instead of predicting from the overall movement, based on the hypothesis that human movement is unique to each person. We devised the features such as the date and time, activity time, days of the week, time of day, and frequency of visits to POI (Point of Interest). As additional features, we incorporated the movement of other individuals with similar behavior patterns through the employment of clustering. The machine learning model we adopted was the Support Vector Regression (SVR). We performed accuracy through offline assessment and carried out feature selection and parameter tuning. Although overall dataset provided consists of 100,000 users trajectory, our method use only 20,000 target users data, and do not need to use other 80,000 data. Despite the personalized model's traditional feature engineering approach, this model yields reasonably good accuracy with lower computational cost.
Its numerous applications make multi-human 3D pose estimation a remarkably impactful area of research. Nevertheless, assuming a multiple-view system composed of several regular RGB cameras, 3D multi-pose estimation presents several challenges. First of all, each person must be uniquely identified in the different views to separate the 2D information provided by the cameras. Secondly, the 3D pose estimation process from the multi-view 2D information of each person must be robust against noise and potential occlusions in the scenario. In this work, we address these two challenges with the help of deep learning. Specifically, we present a model based on Graph Neural Networks capable of predicting the cross-view correspondence of the people in the scenario along with a Multilayer Perceptron that takes the 2D points to yield the 3D poses of each person. These two models are trained in a self-supervised manner, thus avoiding the need for large datasets with 3D annotations.
We introduce SHARCS for adaptive inference that takes into account the hardness of input samples. SHARCS can train a router on any transformer network, enabling the model to direct different samples to sub-networks with varying widths. Our experiments demonstrate that: (1) SHARCS outperforms or complements existing per-sample adaptive inference methods across various classification tasks in terms of accuracy vs. FLOPs; (2) SHARCS generalizes across different architectures and can be even applied to compressed and efficient transformer encoders to further improve their efficiency; (3) SHARCS can provide a 2 times inference speed up at an insignificant drop in accuracy.
Flow, an optimal mental state merging action and awareness, significantly impacts performance, emotion and wellbeing in real-world contexts. However, capturing its fluctuations on a sub-minute timescale is challenging due to the sparsity of the existing flow measuring tools. Here we present a virtual reality fine fingertip force control (F3C) task to induce flow, wherein the task challenge is set at a compatible level with personal skill, and to track the flow fluctuations from the synchronous force control performance. We extract eight performance metrics from the fingertip force sequence and reveal their significant differences under distinct flow states. Further, we built a flow decoder and demonstrated that the flow variations can be decoded using selected metrics. The predicted values reach significant correlation with the self-reported flow intensity (r=0.81). This study showcases the feasibility of tracking intrinsic flow variations with high temporal resolution using task performance measures.
In this article, we focus on the error that is committed when computing the matrix logarithm using the Gauss--Legendre quadrature rules. These formulas can be interpreted as Pad\'e approximants of a suitable Gauss hypergeometric function. Empirical observation tells us that the convergence of these quadratures becomes slow when the matrix is not close to the identity matrix, thus suggesting the usage of an inverse scaling and squaring approach for obtaining a matrix with this property. The novelty of this work is the introduction of error estimates that can be used to select a priori both the number of Legendre points needed to obtain a given accuracy and the number of inverse scaling and squaring to be performed. We include some numerical experiments to show the reliability of the estimates introduced.
Currently the state of the art network models are based or depend on Discrete Event Simulation (DES). While DES is highly accurate, it is also computationally costly and cumbersome to parallelize, making it unpractical to simulate high performance networks. Additionally, simulated scenarios fail to capture all of the complexities present in real network scenarios. While there exists network models based on Machine Learning (ML) techniques to minimize these issues, these models are also trained with simulated data and hence vulnerable to the same pitfalls. Consequently, the Graph Neural Networking Challenge 2023 introduces a dataset of captured traffic traces that can be used to build a ML-based network model without these limitations. In this paper we propose a Graph Neural Network (GNN)-based solution specifically designed to better capture the complexities of real network scenarios. This is done through a novel encoding method to capture information from the sequence of captured packets, and an improved message passing algorithm to better represent the dependencies present in physical networks. We show that the proposed solution it is able to learn and generalize to unseen captured network scenarios.
Within the realm of image recognition, a specific category of multi-label classification (MLC) challenges arises when objects within the visual field may occlude one another, demanding simultaneous identification of both occluded and occluding objects. Traditional convolutional neural networks (CNNs) can tackle these challenges; however, those models tend to be bulky and can only attain modest levels of accuracy. Leveraging insights from cutting-edge neural science research, specifically the Holistic Bursting (HB) cell, this paper introduces a pioneering integrated network framework named HB-net. Built upon the foundation of HB cell clusters, HB-net is designed to address the intricate task of simultaneously recognizing multiple occluded objects within images. Various Bursting cell cluster structures are introduced, complemented by an evidence accumulation mechanism. Testing is conducted on multiple datasets comprising digits and letters. The results demonstrate that models incorporating the HB framework exhibit a significant $2.98\%$ enhancement in recognition accuracy compared to models without the HB framework ($1.0298$ times, $p=0.0499$). Although in high-noise settings, standard CNNs exhibit slightly greater robustness when compared to HB-net models, the models that combine the HB framework and EA mechanism achieve a comparable level of accuracy and resilience to ResNet50, despite having only three convolutional layers and approximately $1/30$ of the parameters. The findings of this study offer valuable insights for improving computer vision algorithms. The essential code is provided at //github.com/d-lab438/hb-net.git.
In general insurance, claims are often lower-truncated and right-censored because insurance contracts may involve deductibles and maximal covers. Most classical statistical models are not (directly) suited to model lower-truncated and right-censored claims. A surprisingly flexible family of distributions that can cope with lower-truncated and right-censored claims is the class of MBBEFD distributions that originally has been introduced by Bernegger (1997) for reinsurance pricing, but which has not gained much attention outside the reinsurance literature. We derive properties of the class of MBBEFD distributions, and we extend it to a bigger family of distribution functions suitable for modeling lower-truncated and right-censored claims. Interestingly, in general insurance, we mainly rely on unimodal skewed densities, whereas the reinsurance literature typically proposes monotonically decreasing densities within the MBBEFD class.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191