In this paper, we tackle the problem of Unmanned Aerial (UAV) path planning in complex and uncertain environments by designing a Model Predictive control (MPC), based on a Long-Short-Term Memory ( LSTM) network integr...
详细信息
ISBN:
(纸本)9798350310375
In this paper, we tackle the problem of Unmanned Aerial (UAV) path planning in complex and uncertain environments by designing a Model Predictive control (MPC), based on a Long-Short-Term Memory ( LSTM) network integrated into the Deep Deterministic Policy Gradient algorithm. In the proposed solution, LSTM-MPC operates as a deterministic policy within the DDPG network, and it leverages a predicting pool to store predicted future states and actions for improved robustness and efficiency. The use of the predicting pool also enables the initialization of the critic network, leading to improved convergence speed and reduced failure rate compared to traditional reinforcement learning and deep reinforcement learning methods. The effectiveness of the proposed solution is evaluated by numerical simulations.
controlling nonlinear dynamical systems using machine learning allows to not only drive systems into simple behavior like periodicity but also to more complex arbitrary dynamics. For this, it is crucial that a machine...
详细信息
ISBN:
(纸本)9781665488679
controlling nonlinear dynamical systems using machine learning allows to not only drive systems into simple behavior like periodicity but also to more complex arbitrary dynamics. For this, it is crucial that a machine learning system can be trained to reproduce the target dynamics sufficiently well. On the example of forcing a chaotic parametrization of the Lorenz system into intermittent dynamics, we show first that classical reservoir computing excels at this task. In a next step, we compare those results based on different amounts of training data to an alternative setup, where next-generation reservoir computing is used instead. It turns out that while delivering comparable performance for usual amounts of training data, next-generation RC significantly outperforms in situations where only very limited data is available. This opens even further practical control applications in real world problems where data is restricted.
In the process of oil production, the submerged oil motor works 1-3 km downhole and is connected to the inverter by a long-wire cable, which generates overvoltage at the motor end due to the problem of matching the im...
详细信息
Conceptual modeling is gaining an essential role in designing large-scale systems, especially as the complexity of the latter increases. The design tool for such systems is the development of ontologies for their subj...
详细信息
Model predictive control (MPC) may provide local motion planning for mobile robotic platforms. The challenging aspect is the analytic representation of collision cost for the case when both the obstacle map and robot ...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Model predictive control (MPC) may provide local motion planning for mobile robotic platforms. The challenging aspect is the analytic representation of collision cost for the case when both the obstacle map and robot footprint are arbitrary. We propose a Neural Potential Field: a neural network model that returns a differentiable collision cost based on robot pose, obstacle map, and robot footprint. The differentiability of our model allows its usage within the MPC solver. It is computationally hard to solve problems with a very high number of parameters. Therefore, our architecture includes neural image encoders, which transform obstacle maps and robot footprints into embeddings, which reduce problem dimensionality by two orders of magnitude. The reference data for network training are generated based on algorithmic calculation of a signed distance function. Comparative experiments showed that the proposed approach is comparable with existing local planners: it provides trajectories with outperforming smoothness, comparable path length, and safe distance from obstacles.
The synthesis of a robust-optimal control system for the multidimensional nonlinear model of a quadcopter with optimized motion trajectories is proposed. These trajectories are described by ordinary nonlinear differen...
详细信息
In near-field measurements probe presence leads to antenna under test field distortions that is critical in the diagnostic problems and antenna under test characteristics reconstruction. The paper briefly describes th...
详细信息
Fluid simulation technology is a kind of experimental technology on the computer, through this technology, the control system can be fine design and verification. Fluid simulation techniques can provide a realistic an...
详细信息
The paper is concerned with optimization problem of controlled stochastic switching systems. A switching system are regulated by the set of stochastic differential equations which initial circumstances to rely on its ...
详细信息
This paper compares different stub shapes for minimizing far-end crosstalk. COMSOL Multiphysics software was used as the modeling environment. Frequency-domain modeling revealed that the use of rectangular stubs signi...
详细信息
暂无评论