Search

Enhanced microwave absorption properties were successfully achievable from SrFe2-xZnxFe16O27 (SrFe2-xZnxW; x = 0.0, 0.5, 1.0, and 2.0) hexaferrite filler-epoxy resin matrix composites. The composite samples were fabricated with the filler volume fractions (Vf) of 30, 50, 70, and 90%. Compared with fully Zn-substituted SrZn2W composite (x = 2.0), unsubstituted and partially Zn-substituted SrFe2-xZnxW (x = 0.0, 0.5, and 1.0) composites exhibited much higher real and imaginary parts of complex permittivity (er), which is attributable to higher electron hopping between Fe2+ and Fe3+ ions, and also slightly higher real and imaginary parts of complex permeability (μr) due to higher saturation magnetization (Ms). Among all samples, a 2.8 mm-thick SrFe1·5Zn0·5W (x = 0.5) composite with the Vf of 90% exhibited the most appropriate for application in the region of 3.4–3.8 GHz, having the minimum reflection loss (RLmin) of −46 dB at 3.6 GHz with the bandwidth of 0.43 GHz (3.38–3.81 GHz) below −10 dB, while a 2.15 mm-thick SrFeZnW (x = 1.0) composite with the Vf of 70% showed the most appropriate for application in the region of 5.9–7.1 GHz, possessing the RLmin value of −23.7 dB at 6.6 GHz with the bandwidth of 1.38 GHz (5.85–7.23 GHz) below −10 dB. Consequently, partially Zn-substituted SrW-type hexaferrites are very promising microwave absorbers for 5G mobile communications in the Ku band (0.5–18 GHz).

A high-performance soft-magnetic composite (SMC) has been successfully fabricated in a toroidal mold without the application of compaction pressure by mixing three different alumina-coated Fe-based metal powders, namely carbonyl iron (FM), Fe-Si-Cr alloy (FSC), and Fe-Si-Al alloy (sendust), with epoxy resin in a centrifugal paste mixer. Surface coating with an alumina layer was performed via a sol–gel process, and its thickness was controlled by varying the coating time. Without the alumina coating, the SMC toroidal core with a FM:FSC:sendust mixing ratio of 8:22:70 by mass exhibited optimal magnetic properties including an effective permeability (μeff) of 33.9 and total core loss (Pt) of 252 mW/cm3 at 100 kHz with an amplitude (B) of 50 mT. With the alumina coating, however, the SMC toroidal core with the same mixing ratio exhibited a significantly reduced Pt value of 213 mW/cm3 while its μeff value was slightly decreased to 32.4, primarily due to the suppression of the macroscopic eddy-current loss from 115 mW/cm3 to 85 mW/cm3. These results indicate that an optimal mixture of the three different alumina-coated Fe-based metal powders is very effective for fabricating high-performance SMC cores without external pressure for molding, being applicable for miniature electronic components.

In this paper, we focus on the problem of learning from demonstration (LfD) where demonstrations with different proficiencies are provided without labeling. To this end, we model multiple policies with different qualities as correlated Gaussian processes and present a leverage optimization method that estimates the leverage of each policy where the difference between two leverages defines the correlation between the corresponding policies. To recover a single policy function of an expert, we present a sparsity constraint on the leverage parameters. We first show that the proposed leverage optimization method can recover the correlations between sensory fields where the fields are realized from correlated Gaussian processes and sensor measurements are collected from the fields. Furthermore, we applied the proposed method to autonomous driving experiments, where demonstrations are collected from three different driving modes. While the driving policies are not realized from correlated processes, the proposed method assigns reasonable leverages to the driving demonstrations. The estimated driving policy of an expert, which incorporates the optimized leverages, outperforms previous LfD methods in terms of both safety and driving quality.

In this letter, we propose the Interactive Text2Pickup (IT2P) network for human-robot collaboration that enables an effective interaction with a human user despite the ambiguity in user's commands. We focus on the task where a robot is expected to pick up an object instructed by a human, and to interact with the human when the given instruction is vague. The proposed network understands the command from the human user and estimates the position of the desired object first. To handle the inherent ambiguity in human language commands, a suitable question which can resolve the ambiguity is generated. The user's answer to the question is combined with the initial command and given back to the network, resulting in more accurate estimation. The experiment results show that given unambiguous commands, the proposed method can estimate the position of the requested object with an accuracy of 98.49% based on the test dataset. Given ambiguous language commands, we show that the accuracy of the pick up task increases by 1.94 times after incorporating the information obtained from the interaction.

Each person has a different personal space and behaves differently when another person approaches. Based on this observation, we propose a novel method to learn how to approach a person comfortably based on the person's preference while avoiding uncomfortable encounters. We propose a personal comfort field to learn each person's preference about an approaching object. A personal comfort field is based on existing theories in anthropology and personalized for each user through repeated encounters. We propose an online method to learn a personal comfort field of a user, i.e., personalized learning, based on the concept from the Gaussian process upper confidence bound and show that the proposed method has no regret asymptotically. The effectiveness of the proposed method has been extensively validated in simulation and real-world experiments. Results show that the proposed method can gradually learn the personalized approaching behavior preferred by the user as the number of encounters increases.

We present a robust target tracking algorithm for a mobile robot. It is assumed that a mobile robot carries a sensor with a fan-shaped field of view and finite sensing range. The goal of the proposed tracking algorithm is to minimize the probability of losing a target. If the distribution of the next position of a moving target is available as a Gaussian distribution from a motion prediction algorithm, the proposed algorithm can guarantee the tracking success probability. In addition, the proposed method minimizes the moving distance of the mobile robot based on the chosen bound on the tracking success probability. While the considered problem is a non-convex optimization problem, we derive a closed-form solution when the heading is fixed and develop a real-time algorithm for solving the considered target tracking problem. We also present a robust target tracking algorithm for aerial robots in 3D. The performance of the proposed method is evaluated extensively in simulation. The proposed algorithm has been successful applied in field experiments using Pioneer mobile robot with a Microsoft Kinect sensor for following a pedestrian.

In this paper, we propose a nonparametric motion controller using Gaussian process regression for autonomous navigation in a dynamic environment. Particularly, we focus on its applicability to low-cost mobile robot platforms with low-performance processors. The proposed motion controller predicts future trajectories of pedestrians using the partially-observable egocentric view of a robot and controls a robot using both observed and predicted trajectories. Furthermore, a hierarchical motion controller is proposed by dividing the controller into multiple sub-controllers using a mixture-of-experts framework to further alleviate the computational cost. We also derive an efficient method to approximate the upper bound of the learning curve of Gaussian process regression, which can be used to determine the required number of training samples for the desired performance. The performance of the proposed method is extensively evaluated in simulations and validated experimentally using a Pioneer 3DX mobile robot with two Microsoft Kinect sensors. In particular, the proposed baseline and hierarchical motion controllers show over 65 % and 51 % improvements over a reactive planner and predictive vector field histogram, respectively, in terms of the collision rate.

Imitation of the upper body motions of human demonstrators or animation characters to human-shaped robots is studied in this paper. We present a pipeline for motion retargeting by transferring the joints of interest (JOI) of source motions to the target humanoid robot. To this end, we deploy an optimization-based motion retargeting method utilizing link length modifications of the source skeleton and a task (Cartesian) space fine-tuning of JOI motion descriptors. To evaluate the effectiveness of the proposed pipeline, we use two different 3-D motion datasets from three human demonstrators and an Ogre animation character, Bork, and successfully transfer the motions to four different humanoid robots: DARwIn-OP, COmpliant HuMANoid Platform (COMAN), THORMANG, and Atlas. Furthermore, COMAN and THORMANG are actually controlled to show that the proposed method can be deployed to physical robots.

In this paper, we propose a trajectory-based reinforcement learning method named deep latent policy gradient (DLPG) for learning locomotion skills. We define the policy function as a probability distribution over trajectories and train the policy using a deep latent variable model to achieve sample efficient skill learning. We first evaluate the sample efficiency of DLPG compared to the state-of-the-art reinforcement learning methods in simulated environments. Then, we apply the proposed method to a four-legged walking robot named Snapbot to learn three basic locomotion skills of turn left, go straight, and turn right. We demonstrate that, by properly designing two reward functions for curriculum learning, Snapbot successfully learns the desired locomotion skills with moderate sample complexity.

A piezoelectric unimorph anemovane is proposed and analyzed for measuring precisely variation of wind direction and speed. The proposed anemovane has various advantages, compared with general anemovane. It can detect the wind in all direction, and be fabricated as small one. This anemovane was designed as the shape similar to a sea urchin. We use cantilevers to imitate prickles projected on the sea urchin sphere. If the wind blows, it hit the cantilever and the pressure makes the voltage signal through the piezoelectric unimorph bender. The simulation of the proposed system was performed using the FEM software (COMSOL Multiphysics), and the multi-physics analysis (Fluid mechanics, Mechanics and Electrostatics) was executed by considering real boundary conditions. Based on FEM analysis of the new anemovane with the new structure and control method, the characteristics between the fluid and the piezoelectric unimorph bender was comprehended. The possibility of the proposed anemovane was verified through the fabrication and the experiment.

In this paper, we propose a coordinated localization algorithm for mobile sensor networks with camera sensors to operate under Global Positioning System (GPS) denied areas or indoor environments. Mobile robots are partitioned into two groups. One group moves within the field of views of remaining stationary robots. The moving robots are tracked by stationary robots and their trajectories are used as spatiotemporal features. From these spatiotemporal features, relative poses of robots are computed using multiview geometry and a group of robots is localized with respect to the reference coordinate based on the proposed multirobot localization. Once poses of all robots are recovered, a group of robots moves from one location to another while maintaining the formation of robots for coordinated localization under the proposed multirobot navigation strategy. By taking the advantage of a multiagent system, we can reliably localize robots over time as they perform a group task. In experiment, we demonstrate that the proposed method consistently achieves a localization error rate of 0.37% or less for trajectories of length between $715~{\rm cm}$ and $890~{\rm cm}$ using an inexpensive off-the-shelf robotic platform.

We report enhanced electrical properties of metal–insulator–metal (MIM) capacitors consisting of Al (100 nm)/Nb-doped a-HfO2 (∼30 nm)/Pt (100 nm) on a p-type silicon wafer, where Nb-doped amorphous HfO2 (a-HfO2) layers were deposited by radio frequency magnetron sputtering in various low oxygen partial pressures at room temperature. Polycrystalline HfO2 targets with three different Nb contents of 0 mol. %, 6 mol. %, and 10 mol. % were used in this study. Compared with the leakage current of the undoped a-HfO2 film (∼1.1 × 10−8 A cm−2 at 1 V), greatly reduced leakage currents (∼3.7 × 10−10 A cm−2 at 1 V) with no significant alteration in the dielectric constants (∼22) were obtainable from the MIM samples composed of Nb-doped a-HfO2 films, which is attributable to the suppression of oxygen vacancy formation based on the XPS analysis results. The Nb-doped a-HfO2 dielectric thin films also exhibited improved voltage nonlinearity compared to undoped HfO2. These results indicate that Nb-doped a-HfO2 has potential application as a high-κ dielectric material in MIM capacitors.

Denoising is a fundamental imaging problem. Versatile but fast filtering has been demanded for mobile camera systems. We present an approach to multiscale filtering which allows real-time applications on low-powered devices. The key idea is to learn a set of kernels that upscales, filters, and blends patches of different scales guided by local structure analysis. This approach is trainable so that learned filters are capable of treating diverse noise patterns and artifacts. Experimental results show that the presented approach produces comparable results to state-of-the-art algorithms while processing time is orders of magnitude faster.

In this paper, we focus on weakly supervised learning with noisy training data for both classification and regression problems.We assume that the training outputs are collected from a mixture of a target and correlated noise distributions.Our proposed method simultaneously estimates the target distribution and the quality of each data which is defined as the correlation between the target and data generating distributions.The cornerstone of the proposed method is a Cholesky Block that enables modeling dependencies among mixture distributions in a differentiable manner where we maintain the distribution over the network weights.We first provide illustrative examples in both regression and classification tasks to show the effectiveness of the proposed method.Then, the proposed method is extensively evaluated in a number of experiments where we show that it constantly shows comparable or superior performances compared to existing baseline methods in the handling of noisy data., Accepted to Computer Vision and Pattern Recognition (CVPR) 2020

This paper presents a connectivity control algorithm of a multi-agent system. The connectivity of the multi-agent system can be represented by the second smallest eigenvalue λ 2 of the Laplacian matrix L G and it is also referred to as algebraic connectivity. Unlike many of the existing connectivity control algorithms which adapt convex optimization technique to maximize algebraic connectivity, we first show that the algebraic connectivity can be maximized by minimizing the weighted sum of distances between the connected agents. We implement a hill-climbing algorithm that minimizes the weighted sum of distances. Semi-definite programming (SDP) is used for computing proper weight w∗. Our proposed algorithm can effectively be mixed with other cooperative applications such as covering an unknown area or following a leader.

In this paper, a sparse Markov decision process (MDP) with novel causal sparse Tsallis entropy regularization is proposed.The proposed policy regularization induces a sparse and multi-modal optimal policy distribution of a sparse MDP. The full mathematical analysis of the proposed sparse MDP is provided.We first analyze the optimality condition of a sparse MDP. Then, we propose a sparse value iteration method which solves a sparse MDP and then prove the convergence and optimality of sparse value iteration using the Banach fixed point theorem. The proposed sparse MDP is compared to soft MDPs which utilize causal entropy regularization. We show that the performance error of a sparse MDP has a constant bound, while the error of a soft MDP increases logarithmically with respect to the number of actions, where this performance error is caused by the introduced regularization term. In experiments, we apply sparse MDPs to reinforcement learning problems. The proposed method outperforms existing methods in terms of the convergence speed and performance., 15 pages, 9 figures

In this paper, we propose a novel algorithm for learning from demonstration, which can learn a policy function robustly from a large number of demonstrations with mixed qualities. While most of the existing approaches assume that demonstrations are collected from skillful experts, the proposed method alleviates such restrictions by estimating the proficiency level of each demonstration using the proposed leverage optimization. Furthermore, a novel leveraged cost function is proposed to represent a policy function using deep neural networks by reformulating the objective function of leveraged Gaussian process regression using the representer theorem. The proposed method is successfully applied to autonomous track driving tasks, where a large number of demonstrations with mixed qualities are given as training data without labels.

In this paper, a novel online learning navigation algorithm is proposed to incorporate negative data generated from failure in an online manner. While existing methods require additional knowledge about what to do at failed situations, the proposed method alleviates this by utilizing failures as a clue of what not to do without requiring additional knowledge of what to do. By combining the benefits of leveraged Gaussian processes and sparse online Gaussian processes, we proposed an online learning framework for navigation and its update rule which instantly learns which actions to avoid from the failures while navigating. Our navigation method is successfully validated on a static planar world and dynamic worlds on both simulation and real-world dataset.

A partial substitution of Zn2+ for the Fe2+ site of BaY-type hexaferrite was found to be effective for the improvement of microwave absorption properties in 0.5–18 GHz. For this study, the composites of polycrystalline Ba2Fe2-xZnxFe12O22 (Ba2Fe2-xZnxY, 0.5 ≤ x ≤ 2.0) and epoxy resin were fabricated with various hexaferrite volume fractions (Vf) of 30–90%. As a result, Ba2ZnxFe2-xY (x = 0.5–1.5) composites having the partial substitution of Zn2+ exhibited larger complex permittivity values than fully Zn2+ substituted composite of Ba2Zn2Y (x = 2.0) due to an electron hopping between Fe2+ and Fe3+ ions. Because of the enhanced permittivity, Ba2Fe2-xZnxY (x = 0.5–1.5) composites with 30% of Vf possessed better impedance matching characteristics compared with other composites having larger Vf values. Consequently, Ba2Fe2-xZnxY (x = 0.5–1.5) composites exhibited excellent RL values lower than −50 dB with the thickness values ranging from 1.52 to 1.80 mm.

The Rapid and Accurate Image Super Resolution (RAISR) method of Romano, Isidoro, and Milanfar is a computationally efficient image upscaling method using a trained set of filters. We describe a generalization of RAISR, which we name Best Linear Adaptive Enhancement (BLADE). This approach is a trainable edge-adaptive filtering framework that is general, simple, computationally efficient, and useful for a wide range of problems in computational photography. We show applications to operations which may appear in a camera pipeline including denoising, demosaicking, and stylization.

In this paper, we propose a novel inverse reinforcement learning algorithm with leveraged Gaussian processes that can learn from both positive and negative demonstrations. While most existing inverse reinforcement learning (IRL) methods suffer from the lack of information near low reward regions, the proposed method alleviates this issue by incorporating (negative) demonstrations of what not to do. To mathematically formulate negative demonstrations, we introduce a novel generative model which can generate both positive and negative demonstrations using a parameter, called proficiency. Moreover, since we represent a reward function using a leveraged Gaussian process which can model a nonlinear function, the proposed method can effectively estimate the structure of a nonlinear reward function.

In this paper, we propose Gaussian random paths by defining a probability distribution over continuous paths interpolating a finite set of anchoring points using Gaussian process regression. By utilizing the generative property of Gaussian random paths, a Gaussian random path planner is developed to safely steer a robot to a goal position. The Gaussian random path planner can be used in a number of applications, including local path planning for a mobile robot and trajectory optimization for whole body motion planning. We have conducted an extensive set of simulations and experiments, showing that the proposed planner outperforms look-ahead planners which use a pre-defined subset of egocentric trajectories in terms of collision rates and trajectory lengths. Furthermore, we apply the proposed method to existing trajectory optimization methods as an initialization step and demonstrate that it can help produce more cost-efficient trajectories.

To enable safe motion planning in a dynamic environment, it is vital to anticipate and predict object movements. In practice, however, an accurate object identification among multiple moving objects is extremely challenging, making it infeasible to accurately track and predict individual objects. Furthermore, even for a single object, its appearance can vary significantly due to external effects, such as occlusions, varying perspectives, or illumination changes. In this paper, we propose a novel recurrent network architecture called a recurrent flow network that can infer the velocity of each cell and the probability of future occupancy from a sequence of occupancy grids which we refer to as an occupancy flow. The parameters of the recurrent flow network are optimized using Bayesian optimization. The proposed method outperforms three baseline optical flow methods, Lucas-Kanade, Lucas-Kanade with Tikhonov regularization, and HornSchunck methods, and a Bayesian occupancy grid filter in terms of both prediction accuracy and robustness to noise.

In this paper, we propose a novel method for robust learning from demonstration using leveraged Gaussian process regression. While existing learning from demonstration (LfD) algorithms assume that demonstrations are given from skillful experts, the proposed method alleviates such assumption by allowing demonstrations from casual or novice users. To learn from demonstrations of mixed quality, we present a sparse-constrained leveraged optimization algorithm using proximal linearized minimization. The proposed sparse constrained leverage optimization algorithm is successfully applied to sensory field reconstruction and direct policy learning for planar navigation problems. In experiments, the proposed sparse-constrained method outperforms existing LfD methods.

This paper considers two important problems for autonomous robot navigation in a dynamic environment, where the goal is to predict pedestrian motion and control a robot with the prediction for safe navigation. While there are several methods for predicting the motion of a pedestrian and controlling a robot to avoid incoming pedestrians, it is still difficult to safely navigate in a dynamic environment due to challenges, such as the varying quality and complexity of training data with unwanted noises. This paper addresses these challenges simultaneously by proposing a robust kernel subspace learning algorithm based on the recent advances in nuclear-norm and l 1 -norm minimization. We model the motion of a pedestrian and the robot controller using Gaussian processes. The proposed method efficiently approximates a kernel matrix used in Gaussian process regression by learning low-rank structured matrix (with symmetric positive semi-definiteness) to find an orthogonal basis, which eliminates the effects of erroneous and inconsistent data. Based on structured kernel subspace learning, we propose a robust motion model and motion controller for safe navigation in dynamic environments. We evaluate the proposed robust kernel learning in various tasks, including regression, motion prediction, and motion control problems, and demonstrate that the proposed learning-based systems are robust against outliers and outperform existing regression and navigation methods.