Real-time interception of a fast-moving object by a robotic arm in cluttered environments filled with static or dynamic obstacles permits only tens of milliseconds for reaction times, hence quite challenging and arduous for state-of-the-art robotic planning algorithms to perform multiple robotic skills, for instance, catching the dynamic object and avoiding obstacles, in parallel. This paper proposes an unified framework of robotic path planning through embedding the high-dimensional temporal information contained in the event stream to distinguish between safe and colliding trajectories into a low-dimension space manifested with a pre-constructed 2D densely connected graph. We then leverage a fast graph-traversing strategy to generate the motor commands necessary to effectively avoid the approaching obstacles while simultaneously intercepting a fast-moving objects. The most distinctive feature of our methodology is to conduct both object interception and obstacle avoidance within the same algorithm framework based on deep manifold learning. By leveraging a highly efficient diffusion-map based variational autoencoding and Extended Kalman Filter(EKF), we demonstrate the effectiveness of our approach on an autonomous 7-DoF robotic arm using only onboard sensing and computation. Our robotic manipulator was capable of avoiding multiple obstacles of different sizes and shapes while successfully capturing a fast-moving soft ball thrown by hand at normal speed in different angles. Complete video demonstrations of our experiments can be found in https://sites.google.com/view/multirobotskill/home.
The combination of non-orthogonal multiple access (NOMA) and wireless power transfer (WPT) is a promising solution to enhance the energy efficiency of Device-to-Device (D2D) enabled wireless communication networks. In this paper, we focus on maximizing the energy efficiency of a WPT-D2D pair in a multiple-input single-output (MISO)-NOMA downlink network, by alternatively optimizing the beamforming vectors of the base station (BS) and the time switching coefficient of the WPT assisted D2D transmitter. The formulated energy efficiency maximization problem is non-convex due to the highly coupled variables. To efficiently address the non-convex problem, we first divide it into two subproblems. Afterwards, an alternating algorithm based on the Dinkelbach method and quadratic transform is proposed to solve the two subproblems iteratively. To verify the proposed alternating algorithm's accuracy, partial exhaustive search algorithm is proposed as a benchmark. We also utilize a deep reinforcement learning (DRL) method to solve the non-convex problem and compare it with the proposed algorithm. To demonstrate the respective superiority of the proposed algorithm and DRL-based method, simulations are performed for two scenarios of perfect and imperfect channel state information (CSI). Simulation results are provided to compare NOMA and orthogonal frequency-division multiple access (OFDMA), which demonstrate the superior performance of energy efficiency of the NOMA scheme.
Tracking multiple athletes in sports videos is a very challenging Multi-Object Tracking (MOT) task, since athletes often have the same appearance and are intimately covered with each other, making a common occlusion problem becomes an abhorrent duplicate detection. In this paper, the duplicate detection is newly and precisely defined as occlusion misreporting on the same athlete by multiple detection boxes in one frame. To address this problem, we meticulously design a novel transformer-based Duplicate Detection Decontaminator (D$^3$) for training, and a specific algorithm Rally-Hungarian (RH) for matching. Once duplicate detection occurs, D$^3$ immediately modifies the procedure by generating enhanced boxes losses. RH, triggered by the team sports substitution rules, is exceedingly suitable for sports videos. Moreover, to complement the tracking dataset that without shot changes, we release a new dataset based on sports video named RallyTrack. Extensive experiments on RallyTrack show that combining D$^3$ and RH can dramatically improve the tracking performance with 9.2 in MOTA and 4.5 in HOTA. Meanwhile, experiments on MOT-series and DanceTrack discover that D$^3$ can accelerate convergence during training, especially save up to 80 percent of the original training time on MOT17. Finally, our model, which is trained only with volleyball videos, can be applied directly to basketball and soccer videos for MAT, which shows priority of our method. Our dataset is available at https://github.com/heruihr/rallytrack.
Given a discriminating neural network, the problem of fairness improvement is to systematically reduce discrimination without significantly scarifies its performance (i.e., accuracy). Multiple categories of fairness improving methods have been proposed for neural networks, including pre-processing, in-processing and post-processing. Our empirical study however shows that these methods are not always effective (e.g., they may improve fairness by paying the price of huge accuracy drop) or even not helpful (e.g., they may even worsen both fairness and accuracy). In this work, we propose an approach which adaptively chooses the fairness improving method based on causality analysis. That is, we choose the method based on how the neurons and attributes responsible for unfairness are distributed among the input attributes and the hidden neurons. Our experimental evaluation shows that our approach is effective (i.e., always identify the best fairness improving method) and efficient (i.e., with an average time overhead of 5 minutes).
Massive multiple-input multiple-output (MIMO) is a key technique for fifth-generation (5G) and beyond communications. Therefore, accurate characterization of the responses of the large-scale antenna arrays at an arbitrary direction is critical. The effective aperture distribution function (EADF) can provide an analytic description of an antenna array based on a full-sphere measurement of the array in an anechoic chamber. However, as the aperture of an array becomes significantly larger, application of the EADF requires very dense spatial samples due to the large distance-offsets of the array elements to the reference point in the anechoic chamber. This leads to a prohibitive measurement time and a high computational complexity of EADF. In this paper, we first present the EADF applied to large-scale arrays, followed by an analytical analysis of the issue caused by the large array aperture. To solve this issue, an enhanced low-complexity EADF is proposed with a low complexity that is only considering the intrinsic characteristics of each array element rather than the aperture size of the array. Moreover, a measurement campaign conducted at the frequency band of 27-30\,GHz using a relatively large planar array is introduced, where the proposed enhanced EADF is applied and validated.
While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learning to model raw observations from high dimensional sensors can be challenging. Prior work has addressed this challenge by learning low-dimensional representation of observations through auxiliary objectives, such as reconstruction or value prediction. However, the alignment between these auxiliary objectives and the RL objective is often unclear. In this work, we propose a single objective which jointly optimizes a latent-space model and policy to achieve high returns while remaining self-consistent. This objective is a lower bound on expected returns. Unlike prior bounds for model-based RL on policy exploration or model guarantees, our bound is directly on the overall RL objective. We demonstrate that the resulting algorithm matches or improves the sample-efficiency of the best prior model-based and model-free RL methods. While such sample efficient methods typically are computationally demanding, our method attains the performance of SAC in about 50\% less wall-clock time.
Since the preparation of labeled data for training semantic segmentation networks of point clouds is a time-consuming process, weakly supervised approaches have been introduced to learn from only a small fraction of data. These methods are typically based on learning with contrastive losses while automatically deriving per-point pseudo-labels from a sparse set of user-annotated labels. In this paper, our key observation is that the selection of what samples to annotate is as important as how these samples are used for training. Thus, we introduce a method for weakly supervised segmentation of 3D scenes that combines self-training with active learning. The active learning selects points for annotation that likely result in performance improvements to the trained model, while the self-training makes efficient use of the user-provided labels for learning the model. We demonstrate that our approach leads to an effective method that provides improvements in scene segmentation over previous works and baselines, while requiring only a small number of user annotations.
Powder-based additive manufacturing has transformed the manufacturing industry over the last decade. In Laser Powder Bed Fusion, a specific part is built in an iterative manner in which two-dimensional cross-sections are formed on top of each other by melting and fusing the proper areas of the powder bed. In this process, the behavior of the melt pool and its thermal field has a very important role in predicting the quality of the manufactured part and its possible defects. However, the simulation of such a complex phenomenon is usually very time-consuming and requires huge computational resources. Flow-3D is one of the software packages capable of executing such simulations using iterative numerical solvers. In this work, we create three datasets of single-trail processes using Flow-3D and use them to train a convolutional neural network capable of predicting the behavior of the three-dimensional thermal field of the melt pool solely by taking three parameters as input: laser power, laser velocity, and time step. The CNN achieves a relative Root Mean Squared Error of 2% to 3% for the temperature field and an average Intersection over Union score of 80% to 90% in predicting the melt pool area. Moreover, since time is included as one of the inputs of the model, the thermal field can be instantly obtained for any arbitrary time step without the need to iterate and compute all the steps
Object detection algorithms allow to enable many interesting applications which can be implemented in different devices, such as smartphones and wearable devices. In the context of a cultural site, implementing these algorithms in a wearable device, such as a pair of smart glasses, allow to enable the use of augmented reality (AR) to show extra information about the artworks and enrich the visitors' experience during their tour. However, object detection algorithms require to be trained on many well annotated examples to achieve reasonable results. This brings a major limitation since the annotation process requires human supervision which makes it expensive in terms of time and costs. A possible solution to reduce these costs consist in exploiting tools to automatically generate synthetic labeled images from a 3D model of the site. However, models trained with synthetic data do not generalize on real images acquired in the target scenario in which they are supposed to be used. Furthermore, object detectors should be able to work with different wearable devices or different mobile devices, which makes generalization even harder. In this paper, we present a new dataset collected in a cultural site to study the problem of domain adaptation for object detection in the presence of multiple unlabeled target domains corresponding to different cameras and a labeled source domain obtained considering synthetic images for training purposes. We present a new domain adaptation method which outperforms current state-of-the-art approaches combining the benefits of aligning the domains at the feature and pixel level with a self-training process. We release the dataset at the following link https://iplab.dmi.unict.it/OBJ-MDA/ and the code of the proposed architecture at https://github.com/fpv-iplab/STMDA-RetinaNet.
Mixed Integer programs (MIPs) are typically solved by the Branch-and-Bound algorithm. Recently, Learning to imitate fast approximations of the expert strong branching heuristic has gained attention due to its success in reducing the running time for solving MIPs. However, existing learning-to-branch methods assume that the entire training data is available in a single session of training. This assumption is often not true, and if the training data is supplied in continual fashion over time, existing techniques suffer from catastrophic forgetting. In this work, we study the hitherto unexplored paradigm of Lifelong Learning to Branch on Mixed Integer Programs. To mitigate catastrophic forgetting, we propose LIMIP, which is powered by the idea of modeling an MIP instance in the form of a bipartite graph, which we map to an embedding space using a bipartite Graph Attention Network. This rich embedding space avoids catastrophic forgetting through the application of knowledge distillation and elastic weight consolidation, wherein we learn the parameters key towards retaining efficacy and are therefore protected from significant drift. We evaluate LIMIP on a series of NP-hard problems and establish that in comparison to existing baselines, LIMIP is up to 50% better when confronted with lifelong learning.