Modern vehicles are increasingly vulnerable to attacks that exploit network infrastructures, particularly the controller Area Network (CAN) networks. To effectively counter such threats using contemporary tools like I...
详细信息
Vector limiter is a computationally complex component of vector control, but its hardware-friendly algorithm is rarely discussed. This paper presents an efficient solution with pure shift-and-add operations, namely th...
详细信息
ISBN:
(数字)9798350359558
ISBN:
(纸本)9798350359565
Vector limiter is a computationally complex component of vector control, but its hardware-friendly algorithm is rarely discussed. This paper presents an efficient solution with pure shift-and-add operations, namely the dual vector rotation algorithm (DVRA). Its programmable logic realization is also provided. The DVRA is then simulated in a motor driving system, and physical validation is made on a Xilinx FPGA. Furthermore, performance comparison is conducted between the DVRA and four control groups (conventional algorithms). All control groups are built by Xilinx IPs under diversified configurations, thus human bias can be minimized. Post-implementation results evince that the DVRA exhibits significantly less resource expenditure and better timing, with power consumption and accuracy comparable to the control groups.
We consider the problem of control allocation for weakly redundant systems subject to actuator faults. In particular, the design of a suitable allocator will be devised with the aim of compensating for the fault effec...
详细信息
ISBN:
(数字)9798350395440
ISBN:
(纸本)9798350395457
We consider the problem of control allocation for weakly redundant systems subject to actuator faults. In particular, the design of a suitable allocator will be devised with the aim of compensating for the fault effects while, at the same time, keeping the control burden as low as possible. To this goal, two approaches can be followed for the synthesis of the allocation servomechanism: direct allocation using orthogonal projection and optimization-based allocation. Some numerical examples illustrate and highlight advantages, disadvantages and limitations of both strategies.
We study the problem of policy estimation for the Linear Quadratic Regulator (LQR) in discrete-time linear timeinvariant uncertain dynamical systems. We propose a Moreau Envelope-based surrogate LQR cost, built from a...
详细信息
ISBN:
(数字)9798350316339
ISBN:
(纸本)9798350316346
We study the problem of policy estimation for the Linear Quadratic Regulator (LQR) in discrete-time linear timeinvariant uncertain dynamical systems. We propose a Moreau Envelope-based surrogate LQR cost, built from a finite set of realizations of the uncertain system, to define a meta-policy efficiently adjustable to new realizations. Moreover, we design an algorithm to find an approximate first-order stationary point of the meta-LQR cost function. Numerical results show that the proposed approach outperforms naive averaging of controllers on new realizations of the linear system. We also provide empirical evidence that our method has better sample complexity than Model-Agnostic Meta-Learning (MAML) approaches.
In this letter, we address the problem of re-targeting a commercial under-actuated robotic system to a higher dimensional output task. Commercial platforms are equipped with an on-board low-level internal controller t...
详细信息
Recent developments in autonomous vehicle technologies and applications gain a lot of interest by the public, as the popularity of both driver assistance and automated driving systems increase. One of the most promisi...
详细信息
Recent developments in autonomous vehicle technologies and applications gain a lot of interest by the public, as the popularity of both driver assistance and automated driving systems increase. One of the most promising aspect of the autonomous vehicle compared to conventional human driven vehicle is the increased level of safety. Machine learning techniques enables to achieve fast and efficient control actions compared to model based techniques. However, the advantages of a more conservative model based controller are their better robustness properties. In this paper a synergy of the two control philosophy is presented through a trajectory tracking control design for autonomous vehicles. A supervised reinforcement learning (RL) control method is introduced, where a robust Linear Parameter Varying (LPV) controller supervises the operation of the trained RL agent. Thus, in case sensor noise is detected, the guaranteed stability LPV controller takes over the steering control action. In order to demonstrate the operation of the proposed method, three different simulations have been evaluated and compared in CarSim simulation environment.
Differential privacy (DP) has recently been introduced into episodic reinforcement learning (RL) to formally address user privacy concerns in personalized services. Previous work mainly focuses on two trust models of ...
详细信息
A significant amount of remotely sensed data is generated daily by many Earth observation (EO) spaceborne and airborne sensors over different countries of our planet. Different applications use those data, such as nat...
详细信息
In this paper, an approach to augment action recognition time series datasets, devoted to improving the accuracy of deep learning classifiers, is proposed. In the introduced method, two operators are sequentially intr...
详细信息
In this paper, an approach to augment action recognition time series datasets, devoted to improving the accuracy of deep learning classifiers, is proposed. In the introduced method, two operators are sequentially introduced that perform linear and nonlinear modifications in the time scale of the input time series. The resulting data samples contribute to the variability within classes and allow a deep learning-based classifier to better capture their boundaries, leading to a significant improvement in the classification accuracy. The extensive experiments performed on eight publicly available action recognition datasets using the popular Bidirectional Long Short-Term Memory (BiLSTM) classifier reveal the superiority of the proposed algorithm over related approaches.
The paper addresses the problem of an observer design for a nonlinear system for which a linear approach is followed for the control synthesis. The linear context driven by the control design allows to focus the obser...
详细信息
暂无评论