With the development of high-quality economy, modern people are facing various health challenges while their living standards are improving, the risk of disease is rising, and the need for health is urgent and growing...
详细信息
This paper describes the design steps of an intelligent segway robot for monitoring an industrial plant, and detecting corrosion and leakages using camera video. The self-balancing inspection robot (SBIR) integrates r...
详细信息
A network of remote servers is implemented by cloud computing, which is placed on the internet to safeguard, access, manage, and process data instead of on a local server. Cloud computing is currently a very in-demand...
详细信息
Nonlinear dynamics are a pervasive phenomenon in natural and synthetic mechanical systems, which can be leveraged for novel control of vibrations and elastic wave propagation. A mechanical system with high dimensional...
详细信息
ISBN:
(纸本)9780791888322
Nonlinear dynamics are a pervasive phenomenon in natural and synthetic mechanical systems, which can be leveraged for novel control of vibrations and elastic wave propagation. A mechanical system with high dimensionality and nonlinear dynamics can perform information processing on the physical stimuli that act upon the system. This information processing (known as physical reservoir computing) results from the dimensional expansion that occurs in the dynamic system's state as it reacts to the input. The enriched signal contains both nonlinear transformations as well as memory of the original input, which can be leveraged for machine learning and control applications. In this study, a two-dimensional network of nonlinear springs is studied for its capabilities as a mechanical reservoir computer. The reservoir is acted upon by a driving input force, resulting in a nonlinear, high dimensional response from the network of rectified linear unit (ReLU) springs. These ReLU springs possess bilinear force-displacement curves that resemble the leaky ReLU activation function used in neural networks. A spectral analysis is applied to understand both the dynamics and the computational capabilities of the spring reservoirs with different nonlinearities. Specifically, the frequency content of each reservoir was compared against that of the input signal and the output target. Reservoir computing performance of fitting the target output function improved when the spectral content of the system dynamics aligned with the spectral content of the target. We further analyzed the relationship between noise and number of readouts to investigate potential trade-offs in the selection and quantity of readouts.
In this article, a robust adaptive neural network (NN)-based funnel tracking control method is investigated to address anti-perturbation issues in disturbed Euler-Lagrange (EL) systems. The NN-based approaches are use...
详细信息
ISBN:
(纸本)9789819756742;9789819756759
In this article, a robust adaptive neural network (NN)-based funnel tracking control method is investigated to address anti-perturbation issues in disturbed Euler-Lagrange (EL) systems. The NN-based approaches are used to approximate the unknown nonlinear functions, whereas adaptive techniques are employed to estimate disturbance bounds. Meanwhile, an adaptive compensation control scheme is introduced, leveraging neural networks to mitigate above effects of nonlinear functions and disturbances. Additionally, a control strategy resembling a funnel is devised to confine trajectory tracking errors within a predefined region and finite time despite persistent perturbations. The bounded stability of tracking errors in EL systems with prescribed performance is established using Lyapunov stability theory. Simulations are performed to confirm the efficacy of the control technology.
To automate the wiping task using robots, it is crucial to endow the robot with the capability to maintain desired contact with target surfaces. However, challenges arise when geometric priors and visual feedback are ...
详细信息
ISBN:
(纸本)9798350364200;9798350364194
To automate the wiping task using robots, it is crucial to endow the robot with the capability to maintain desired contact with target surfaces. However, challenges arise when geometric priors and visual feedback are not available or when detailed object information is needed. In this paper, a tactile-guided hybrid pose/force control scheme based on gain-scheduling proportional-integral-derivative (PID) is proposed to address these challenges. Leveraging a tactile sensor, three features are extracted from the tactile data and used in the control loop. The control scheme regulates the contact normal force on unknown surfaces with slowly changing curvature while following a trajectory on the surface. It also allows real-time adaptation of the desired contact force to varying surface conditions. The performance of the proposed scheme is evaluated on a robot manipulator equipped with a tactile sensor. Experimental results show that the proposed system can identify stains, guide itself to re-clean areas, and successfully accomplish the wiping task.
Self-reflecting about our performance (e.g., how confident we are) before doing a task is essential for decision making, such as selecting the most suitable tool or choosing the best route to drive. While this form of...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Self-reflecting about our performance (e.g., how confident we are) before doing a task is essential for decision making, such as selecting the most suitable tool or choosing the best route to drive. While this form of awareness-thinking about our performance or metacognitive performance-is well-known in humans, robots still lack this cognitive ability. This reflective monitoring can enhance their embodied decision power, robustness and safety. Here, we take a step in this direction by introducing a mathematical framework that allows robots to use their control self-confidence to make better-informed decisions. We derive a mathematical closed-form expression for control confidence for dynamic systems (i.e., the posterior inverse covariance of the control action). This control confidence seamlessly integrates within an objective function for decision making, that balances the: i) performance for task completion, ii) control effort, and iii) self-confidence. To evaluate our theoretical account, we framed the decision-making within the tool selection problem, where the agent has to select the best robot arm for a particular control task. The statistical analysis of the numerical simulations with randomized 2DOF arms shows that using control confidence during tool selection improves both real task performance, and the reliability of the tool for performance under unmodelled perturbations (e.g., external forces). Furthermore, our results indicate that control confidence is an early indicator of performance and thus, it can be used as a heuristic for making decisions when computation power is restricted or decision-making is intractable. Overall, we show the advantages of using confidence-aware decision-making and control scheme for dynamic systems.
Since the shape of industrial endoscopes is passively altered according to the contact around it, manual inspection approaches of aeroengines through the inspection ports have unreachable areas, and it's difficult...
ISBN:
(纸本)9798350377712;9798350377705
Since the shape of industrial endoscopes is passively altered according to the contact around it, manual inspection approaches of aeroengines through the inspection ports have unreachable areas, and it's difficult to traverse multistage blades and inspect them simultaneously, which requires engine disassembly or the cooperation of multiple operators, resulting in efficiency decline and increased costs. To this end, this paper proposes a novel continuum manipulator with push-pull multisection structure which provides a potential solution for the disadvantages mentioned above due to its higher flexibility, passability, and controllability in confined spaces. The ultra-slender design combined with a tendon-driven mechanism makes the manipulator acquire enough workspace and more flexible postures while maintaining a light weight. Considering the coupling between the tendons in multisection, a innovative kinematics decoupling control method is implemented, which can realize real-time control in the case of limited computational resources. A prototype is built to validate the capabilities of mechatronic design and the performance of the control algorithm. The experimental results demonstrate the advantages of our continuum manipulator in the in-situ inspection of aeroengines' multistage blades, which has the potential to be a replacement solution for industrial endoscopes.
Municipal solid waste incineration (MSWI) can realize the resource, harmlessness and reduction of municipal solid waste (MSW), which is a very effective method of MSW treatment. The furnace temperature is crucial for ...
详细信息
This paper designs a motion target control and automatic tracking system integrating both software and hardware, aimed at applications in communication engineering. The system consists of a main control module, a two-...
详细信息
暂无评论