The increasing complexity of modern plant systems and the limitations of precise mathematical modeling have led to a shift towards data-driven control methods. These methods present an effective alternative that treat...
详细信息
Modern cyber-physical systems use deep-learning based algorithms for many applications for intelligent decision-making. Many of these systems are resource-constrained due to small form factor or finite energy budget. ...
详细信息
ISBN:
(纸本)9798350322811
Modern cyber-physical systems use deep-learning based algorithms for many applications for intelligent decision-making. Many of these systems are resource-constrained due to small form factor or finite energy budget. However, these systems often use multiple deep-learning algorithms simultaneously for a given mission or task. Due to the diverse nature of the algorithms and their performance needs, we need to allocate optimal software and hardware resources for their coexistence. To this aim, in this paper, we study and evaluate the performance tradeoff which will enable the users to choose the size and complexity of the deep learning models, the capacity of the device and also the software framework. With real-world experiments with a wide range of hardware and software, we demonstrate and evaluate the performance of the coexisting deep neural networks (DNN) based applications.
Hysteresis has posed significant challenges to the modeling and control of flexible endoscopic robots, which impedes the advancement of automated endoscopic operation. Despite numerous hysteresis modeling approaches a...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Hysteresis has posed significant challenges to the modeling and control of flexible endoscopic robots, which impedes the advancement of automated endoscopic operation. Despite numerous hysteresis modeling approaches aimed at improving accuracy, there are still several unresolved issues, such as inappropriate model selection and non-ideal assumption of noise. Focusing on these challenges, a novel reinforcement active modeling (RAM) scheme is proposed in this paper. By incorporating reinforcement learning, this method augments an Extended Kalman Filter (EKF)-based active modeling strategy, which improves the insensitivity and generalization ability to non-Gaussian noise that is not introduced in training. Finally, a series of comparative experiments are conducted on the self-built flexible endoscopic robot to validate the improvement achieved by the proposed scheme. Compared with some widely-applied methods, the proposed scheme achieved at least 63.8% improvement in the root mean square error (RMSE) in modeling accuracy under Gaussian noise conditions, and at least 36.5% improvement in RMSE under Poisson noise conditions.
This study addresses the challenge of formation control and navigation in swarms of mobile robots, presenting an innovative algorithm that integrates behavioral approaches with fuzzy logic to calculate behavior weight...
详细信息
Assembly processes involving humans and robots are challenging scenarios because the individual activities and access to shared workspace have to be coordinated. Fixed robot programs leave no room to diverge from a fi...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Assembly processes involving humans and robots are challenging scenarios because the individual activities and access to shared workspace have to be coordinated. Fixed robot programs leave no room to diverge from a fixed protocol. Working on such a process can be stressful for the user and lead to ineffective behavior or failure. We propose a novel approach of online constraint-based scheduling in a reactive execution control framework facilitating behavior trees called CoBOS. This allows the robot to adapt to uncertain events such as delayed activity completions and activity selection (by the human). The user will experience less stress as the robotic coworkers adapt their behavior to best complement the humanselected activities to complete the common task. In addition to the improved working conditions, our algorithm leads to increased efficiency, even in highly uncertain scenarios. We evaluate our algorithm using a probabilistic simulation study with 56000 experiments. We outperform all other compared methods by a margin of 4- 10%. Initial real robot experiments using a Franka Emika Panda robot and human tracking based on HTC Vive VR gloves look promising.
This paper considers a differential game approach to the predecessor-following vehicle platoon control problem without and with collision avoidance. In this approach, each vehicle tries to minimize the performance ind...
详细信息
ISBN:
(纸本)9798350399462
This paper considers a differential game approach to the predecessor-following vehicle platoon control problem without and with collision avoidance. In this approach, each vehicle tries to minimize the performance index (PI) of its control objective, which is reaching consensual velocity with the predecessor vehicle while maintaining a small inter-vehicle distance from it. Two differential games were formulated. The differential game problem for platoon control without collision avoidance is solved for the open-loop Nash equilibrium and its associated state trajectories. The second differential game problem for platoon control with collision avoidance has a non-quadratic PI, which poses a greater challenge to obtaining its open-loop Nash equilibrium. Since the exact solution is unavailable, we propose an estimated Nash strategy approach that is greatly simplified for implementation. An illustrative example of a vehicle platoon control problem was solved under both the without and with collision avoidance scenarios. The results showed the effectiveness of the models and their solutions for both scenarios.
Time-series data prediction aims to predict future data according to previous data. Following the temporal correlation of data, the data can be forecasted via recurrent network, considering the neighboring data. By le...
详细信息
This paper investigates the performance of an intelligent reflecting surface (IRS)-assisted underwater optical wireless communication (UOWC) system in considering oceanic propagation loss, oceanic turbulence, and poin...
详细信息
ISBN:
(纸本)9798350336672
This paper investigates the performance of an intelligent reflecting surface (IRS)-assisted underwater optical wireless communication (UOWC) system in considering oceanic propagation loss, oceanic turbulence, and pointing errors. Pointing errors induced by IRS vibration is the main factor that causes the performance degradation of IRS-assisted UOWC systems. Unlike previous works that employed zero boresight pointing error model for the performance analysis of UOWC systems, in this study, we develop a nonzero boresight pointing error model. In addition, we derive the approximation formula for the comprehensive channel model that combines three separate models including the propagation loss model, log-normal oceanic turbulence model, and the nonzero boresight pointing error model. The outcomes of this study reveal that the vibration of an IRS-installed buoy/ship severely impacts the system outage performance. Insightful discussions based on the numerical results are useful for the practical system design of the IRSassisted UOWC system.
Data mining is an important field of intelligentcomputing and has been applied in many industries. The large amount of telemetry data accumulated by China's aerospace industry over the years is a warehouse that n...
详细信息
Enterprise Resource Planning (ERP) systems have become essential instruments in contemporary corporate operations, offering significant benefits in process optimization and efficient data management. The assurance of ...
详细信息
暂无评论