Search

Behavior cloning (BC) is a popular supervised imitation learning method in the societies of robotics, autonomous driving, etc., wherein complex skills can be learned by direct imitation from expert demonstrations. Despite its rapid development, it is still affected by limited field of view where accumulation of sensors and joint noise bring compounding errors. In this paper, we introduced geometrically and historically constrained behavior cloning (GHCBC) to dominantly consider high-level state information inspired by neuroscientists, wherein the geometrically constrained behavior cloning were used to geometrically constrain predicting poses, and the historically constrained behavior cloning were utilized to temporally constrain action sequences. The synergy between these two types of constrains enhanced the BC performance in terms of robustness and stability. Comprehensive experimental results showed that success rates were improved by 29.73% in simulation and 39.4% in real robot experiments in average, respectively, compared to state-of-the-art BC method, especially in long-term operational scenes, indicating great potential of using the GHCBC for robotic learning.

Industrial managements, including quality control, cost and safety optimization, etc., heavily rely on high quality industrial human action recognitions (IHARs) which were hard to be implemented in large-scale industrial scenes due to their high costs and poor real-time performance. In this paper, we proposed a large-scale foundation model(LSFM)-based IHAR method, wherein various LSFMs and lightweight methods were jointly used, for the first time, to fulfill low-cost dataset establishment and real-time IHARs. Comprehensive tests on in-situ large-scale industrial manufacturing lines elucidated that the proposed method realized great reduction on employment costs, superior real-time performance, and satisfactory accuracy and generalization capabilities, indicating its great potential as a backbone IHAR method, especially for large-scale industrial applications.

Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the AT. In this paper, in order to reserve high generalization while improving robustness, we proposed a dynamic perturbation-adaptive adversarial training (DPAAT) method, which placed AT in a dynamic learning environment to generate adaptive data-level perturbations and provided a dynamically updated criterion by loss information collections to handle the disadvantage of fixed perturbation sizes in conventional AT methods and the dependence on external transference. Comprehensive testing on dermatology HAM10000 dataset showed that the DPAAT not only achieved better robustness improvement and generalization preservation but also significantly enhanced mean average precision and interpretability on various CNNs, indicating its great potential as a generic adversarial training method on the MIC., Comment: 9 pages, 4 figures, 2 tables

Deep neural networks were significantly vulnerable to adversarial examples manipulated by malicious tiny perturbations. Although most conventional adversarial attacks ensured the visual imperceptibility between adversarial examples and corresponding raw images by minimizing their geometric distance, these constraints on geometric distance led to limited attack transferability, inferior visual quality, and human-imperceptible interpretability. In this paper, we proposed a supervised semantic-transformation generative model to generate adversarial examples with real and legitimate semantics, wherein an unrestricted adversarial manifold containing continuous semantic variations was constructed for the first time to realize a legitimate transition from non-adversarial examples to adversarial ones. Comprehensive experiments on MNIST and industrial defect datasets showed that our adversarial examples not only exhibited better visual quality but also achieved superior attack transferability and more effective explanations for model vulnerabilities, indicating their great potential as generic adversarial examples. The code and pre-trained models were available at https://github.com/shuaili1027/MAELS.git., Comment: 12 pages, 6 figures

Multi-agent Deep Reinforcement Learning (MADRL) based traffic signal control becomes a popular research topic in recent years. To alleviate the scalability issue of completely centralized RL techniques and the non-stationarity issue of completely decentralized RL techniques on large-scale traffic networks, some literature utilizes a regional control approach where the whole network is firstly partitioned into multiple disjoint regions, followed by applying the centralized RL approach to each region. However, the existing partitioning rules either have no constraints on the topology of regions or require the same topology for all regions. Meanwhile, no existing regional control approach explores the performance of optimal joint action in an exponentially growing regional action space when intersections are controlled by 4-phase traffic signals (EW, EWL, NS, NSL). In this paper, we propose a novel RL training framework named RegionLight to tackle the above limitations. Specifically, the topology of regions is firstly constrained to a star network which comprises one center and an arbitrary number of leaves. Next, the network partitioning problem is modeled as an optimization problem to minimize the number of regions. Then, an Adaptive Branching Dueling Q-Network (ABDQ) model is proposed to decompose the regional control task into several joint signal control sub-tasks corresponding to particular intersections. Subsequently, these sub-tasks maximize the regional benefits cooperatively. Finally, the global control strategy for the whole network is obtained by concatenating the optimal joint actions of all regions. Experimental results demonstrate the superiority of our proposed framework over all baselines under both real and synthetic datasets in all evaluation metrics.

Most feature-based stereo visual odometry (SVO) approaches estimate the motion of mobile robots by matching and tracking point features along a sequence of stereo images. However, in dynamic scenes mainly comprising moving pedestrians, vehicles, etc., there are insufficient robust static point features to enable accurate motion estimation, causing failures when reconstructing robotic motion. In this paper, we proposed DynPL-SVO, a complete dynamic SVO method that integrated united cost functions containing information between matched point features and re-projection errors perpendicular and parallel to the direction of the line features. Additionally, we introduced a \textit{dynamic} \textit{grid} algorithm to enhance its performance in dynamic scenes. The stereo camera motion was estimated through Levenberg-Marquard minimization of the re-projection errors of both point and line features. Comprehensive experimental results on KITTI and EuRoC MAV datasets showed that accuracy of the DynPL-SVO was improved by over 20\% on average compared to other state-of-the-art SVO systems, especially in dynamic scenes.

When stressed sufficiently, solid materials yield and deform plastically via reorganization of microscopic constituents. Indeed, it is possible to alter the micro-structure of materials by judicious application of stress, an empirical pro- cess utilized in practice to enhance the mechanical properties of metals. Un- derstanding the interdependence of plastic flow and microscopic structure in these non-equilibrium states, however, remains a major challenge. Here, we ex- perimentally investigate this relationship, between the relaxation dynamics and microscopic structure of disordered colloidal solids during plastic deformation. We apply oscillatory shear to solid colloidal monolayers and study their particle trajectories as a function of shear rate in the plastic regime. Under these cir- cumstances, the strain rate, the relaxation rate associated with plastic flow, and the sample microscopic structure oscillate together but with different phases. Interestingly, the experiments reveal that the relaxation rate associated with plastic flow at time t is correlated with the strain rate and sample microscopic structure measured at earlier and later times, respectively. The relaxation rate, in this non-stationary condition, exhibits power-law shear-thinning behavior and scales exponentially with sample excess entropy. Thus, measurement of sample static structure (excess entropy) provides insight about both strain-rate and constituent rearrangement dynamics in the sample at earlier times.

This paper studies the gamma-ray spectra of positron annihilation processes in a series of molecules. The results show that the average valence electron energy of the molecules has a linear correlation with the full width at half maximum (FWHM) of the gamma-ray spectra. In addition, we defined a new physical quantity Average Doppler Shift (ADS), which can be used as the eigenvalue to describe the characteristics of the gamma-ray spectra. Since ADS contains all the information about the gamma-ray spectra, it can more accurately represent the characteristics of the gamma-ray spectra. For a series of molecules, this paper compares the ADS and FWHM of their gamma-ray spectra and the average valence electron energy. The results show that ADS has a linear correlation with the average valence electron energy and the FWHM. Further, this proves that the annihilation mainly occurs on valence electrons, and it also illustrates that the ADS has certain applicability. It is expected that this will provide us with a deeper understanding of the positron annihilation process.

This paper presents a new explanation of the width of gamma-ray spectra based on Rahm's electronegativity scale. This quantitatively proves, for the first time, that positrophilic electrons in the positron-electron annihilation process are exactly the valence electrons. This suggests the replacement of Full Width at Half Maximum (FWHM) of the gamma-ray spectra with the newly defined physical quantity Average Doppler Shift (ADS). Both FWHM and ADS of the gamma-ray spectra in light elements agree well with the corresponding Rahm's electronegativity values, respectively. Further, ADS provides strong evidence in favor of Rahm's electronegativity scale. It is expected that this will be useful in understanding the mechanism of the positron-electron annihilation process.

In this study, a fully self-consistent method was developed to obtain the wave functions of the positron and electrons in molecules simultaneously. The wave function of a positron at room temperature , with a characteristic energy of approximately $0.04 eV$, was used to analyse the experimental results of its annihilation in helium, neon, hydrogen, and methane molecules. The interactions between the positron and molecule provide a significant correction in the gamma-ray spectra of the annihilating electron--positron pairs. It was also observed that high-order correlations offered almost no correction in the spectra, as the interaction between the low-energy positron and electrons cannot drive the electrons into excited electronic states. More accurate studies, which consider the coupling of the positron--electron pair states and vibration states of nuclei, must be undertaken.