自主智能系统(英文)最新文献

Fault diagnosis plays a vital role in assessing the health management of industrial robots and improving maintenance schedules. In recent decades, artificial intelligence-based data-driven approaches have made significant progress in machine fault diagnosis using monitoring data. However, current methods pay less attention to correlations and internal differences in monitoring data, resulting in limited diagnostic performance. In this paper, a data-driven method is proposed for the fault diagnosis of industrial robot reducers, that is, a dual-module attention convolutional neural network (DMA-CNN). This method aims to diagnose the fault state of industrial robot reducer. It establishes two parallel convolutional neural networks with two different attentions to capture the different features related to the fault. Finally, the features are fused to obtain the fault diagnosis results (normal or abnormal). The fault diagnosis effect of the DMA-CNN method and other attention models are compared and analyzed. The effectiveness of the method is verified on a dataset of real industrial robots.

An industrial robot is a complex mechatronics system, whose failure is hard to diagnose based on monitoring data. Previous studies have reported various methods with deep network models to improve the accuracy of fault diagnosis, which can get an accurate prediction model when the amount of data sample is sufficient. However, the failure data is hard to obtain, which leads to the few-shot issue and the bad generalization ability of the model. Therefore, this paper proposes an attention enhanced dilated convolutional neural network (D-CNN) approach for the cross-axis industrial robotics fault diagnosis method. Firstly, key feature extraction and sliding window are adopted to pre-process the monitoring data of industrial robots before D-CNN is introduced to extract data features. And self-attention is used to enhance feature attention capability. Finally, the pre-trained model is used for transfer learning, and a small number of the dataset from another axis of the multi-axis industrial robot are used for fine-tuning experiments. The experimental results show that the proposed method can reach satisfactory fault diagnosis accuracy in both the source domain and target domain.

In this paper, the constrained Nash equilibrium seeking problem of aggregative games is investigated for uncertain nonlinear Euler-Lagrange (EL) systems under unbalanced digraphs, where the cost function for each agent depends on its own decision variable and the aggregate of all other decisions. By embedding a distributed estimator of the left eigenvector associated with zero eigenvalue of the digraph Laplacian matrix, a dynamic adaptive average consensus protocol is employed to estimate the aggregate function in the unbalanced case. To solve the constrained Nash equilibrium seeking problem, an integrated distributed protocol based on output-constrained nonlinear control and projected dynamics is proposed for uncertain EL players to reach the Nash equilibrium. The convergence analysis is established by using variational inequality technique and Lyapunov stability analysis. Finally, a numerical example in electricity market is provided to validate the effectiveness of the proposed method.

We propose a two-stage reward allocation method with decay using an extension of replay memory to adapt this rewarding method for deep reinforcement learning (DRL), to generate coordinated behaviors for tasks that can be completed by executing a few subtasks sequentially by heterogeneous agents. An independent learner in cooperative multi-agent systems needs to learn its policies for effective execution of its own responsible subtask, as well as for coordinated behaviors under a certain coordination structure. Although the reward scheme is an issue for DRL, it is difficult to design it to learn both policies. Our proposed method attempts to generate these different behaviors in multi-agent DRL by dividing the timing of rewards into two stages and varying the ratio between them over time. By introducing the coordinated delivery and execution problem with an expiration time, where a task can be executed sequentially by two heterogeneous agents, we experimentally analyze the effect of using various ratios of the reward division in the two-stage allocations on the generated behaviors. The results demonstrate that the proposed method could improve the overall performance relative to those with the conventional one-time or fixed reward and can establish robust coordinated behavior.

Machine learning and in particular deep learning techniques have demonstrated the most efficacy in training, learning, analyzing, and modelling large complex structured and unstructured datasets. These techniques have recently been commonly deployed in different industries to support robotic and autonomous system (RAS) requirements and applications ranging from planning and navigation to machine vision and robot manipulation in complex environments. This paper reviews the state-of-the-art with regard to RAS technologies (including unmanned marine robot systems, unmanned ground robot systems, climbing and crawler robots, unmanned aerial vehicles, and space robot systems) and their application for the inspection and monitoring of mechanical systems and civil infrastructure. We explore various types of data provided by such systems and the analytical techniques being adopted to process and analyze these data. This paper provides a brief overview of machine learning and deep learning techniques, and more importantly, a classification of the literature which have reported the deployment of such techniques for RAS-based inspection and monitoring of utility pipelines, wind turbines, aircrafts, power lines, pressure vessels, bridges, etc. Our research provides documented information on the use of advanced data-driven technologies in the analysis of critical assets and examines the main challenges to the applications of such technologies in the industry.

In this paper, we aim to develop distributed continuous-time algorithms over directed graphs to seek the Nash equilibrium in a noncooperative game. Motivated by the recent consensus-based designs, we present a distributed algorithm with a proportional gain for weight-balanced directed graphs. By further embedding a distributed estimator of the left eigenvector associated with zero eigenvalue of the graph Laplacian, we extend it to the case with arbitrary strongly connected directed graphs having possible unbalanced weights. In both cases, the Nash equilibrium is proven to be exactly reached with an exponential convergence rate. An example is given to illustrate the validity of the theoretical results.

Distributed Nash equilibrium seeking of aggregative games is investigated and a continuous-time algorithm is proposed. The algorithm is designed by virtue of projected gradient play dynamics and aggregation tracking dynamics, and is applicable to games with constrained strategy sets and weight-balanced communication graphs. The key feature of our method is that the proposed projected dynamics achieves exponential convergence, whereas such convergence results are only obtained for non-projected dynamics in existing works on distributed optimization and equilibrium seeking. Numerical examples illustrate the effectiveness of our methods.

Autonomous driving has attracted significant research interests in the past two decades as it offers many potential benefits, including releasing drivers from exhausting driving and mitigating traffic congestion, among others. Despite promising progress, lane-changing remains a great challenge for autonomous vehicles (AV), especially in mixed and dynamic traffic scenarios. Recently, reinforcement learning (RL) has been widely explored for lane-changing decision makings in AVs with encouraging results demonstrated. However, the majority of those studies are focused on a single-vehicle setting, and lane-changing in the context of multiple AVs coexisting with human-driven vehicles (HDVs) have received scarce attention. In this paper, we formulate the lane-changing decision-making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing decisions based on the motions of both neighboring AVs and HDVs. Specifically, a multi-agent advantage actor-critic (MA2C) method is proposed with a novel local reward design and a parameter sharing scheme. In particular, a multi-objective reward function is designed to incorporate fuel efficiency, driving comfort, and the safety of autonomous driving. A comprehensive experimental study is made that our proposed MARL framework consistently outperforms several state-of-the-art benchmarks in terms of efficiency, safety, and driver comfort.

Circular economy enables to restore product value at the end of life i.e. when no longer used or damaged. Thus, the product life cycle is extended and this economy permits to reduce waste increase and resources rarefaction. There are several revaluation options (reuse, remanufacturing, recycling, …). So, decision makers need to assess these options to determine which is the best decision. Thus, we will present a study about an End-Of-Life (EoL) decision making which aims to facilitate the industrialization of circular economy. For this, it is essential to consider all variables and parameters impacting the decision of the product trajectory. A first part of the work proposes to identify the variables and parameters impacting the decision making. A second part proposes an assessment approach based on a modeling by Generalized Colored Stochastic Petri Net (GCSPN) and on a Monte-Carlo simulation. The approach developed is tested on an industrial example from the literature to analyze the efficiency and effectiveness of the model. This first application showed the feasibility of the approach, and also the limits of the GCSPN modelling.

Vehicle mass is an important parameter for motion control of intelligent vehicles, but is hard to directly measure using normal sensors. Therefore, accurate estimation of vehicle mass becomes crucial. In this paper, a vehicle mass estimation method based on fusion of machine learning and vehicle dynamic model is introduced. In machine learning method, a feedforward neural network (FFNN) is used to learn the relationship between vehicle mass and other state parameters, namely longitudinal speed and acceleration, driving or braking torque, and wheel angular speed. In dynamics-based method, recursive least square (RLS) with forgetting factor based on vehicle dynamic model is used to estimate the vehicle mass. According to the reliability of each method under different conditions, these two methods are fused using fuzzy logic. Simulation tests under New European Driving Cycle (NEDC) condition are carried out. The simulation results show that the estimation accuracy of the fusion method is around 97%, and that the fusion method performs better stability and robustness compared with each single method.