In order to improve the motion stability and monitorability of inspection robots, a digital twin predictive control system for inspection robots based on Unity3D and Robot Operating System (ROS) is proposed. Firstly, ...
详细信息
ISBN:
(纸本)9798350352634;9798350352627
In order to improve the motion stability and monitorability of inspection robots, a digital twin predictive control system for inspection robots based on Unity3D and Robot Operating System (ROS) is proposed. Firstly, with the support of wireless communication technology and ROS system, the mapping of virtual-real space scene and robot state is carried out through TCP/IP protocol;secondly, considering the impact of data communication lag and signal loss on the control system, a predictive control model is constructed to control the robot's motion in order to reduce the reliance on real-time data, and the predictive control model is optimized by using Laguerre's function as well as filtering algorithm to optimize the control response and mitigate control oscillations in time;finally, in the virtual decision space, the physical robot is driven to follow the predicted trajectory in a synchronized mapping manner. The experimental results prove that the digital twin control system has good tracking performance and is stable and reliable. Compared with that before model optimization, the efficiency is improved by 50.93% and the error is reduced by 69.23%.
This paper investigates lane-changing mechanisms for autonomous vehicles by employing a decision model based on fuzzy logic, trajectory planning via a quintic polynomial, and a hybrid PSO-LQR algorithm for tracking co...
详细信息
Aerial manipulation has received increasing research interest with wide applications of drones. To perform specific tasks, robotic arms with various mechanical structures will be mounted on the drone. It results in su...
详细信息
ISBN:
(纸本)9798350384581;9798350384574
Aerial manipulation has received increasing research interest with wide applications of drones. To perform specific tasks, robotic arms with various mechanical structures will be mounted on the drone. It results in sudden disturbances to the aerial manipulator when switching the robotic arm or interacting with the environment. Hence, it is challenging to design a generic and robust control strategy adapted to various robotic arms when achieving multi-task aerial manipulation. In this paper, we present a learning-based control algorithm that allows online trajectory optimization and tracking to accomplish various aerial interaction tasks without manual adjustment. The proposed energy-saved trajectory planning approach integrates coupled dynamics model with a single rigid body to generate the energy-efficient trajectory for the aerial manipulator. Addressing the challenges of precise control when performing aerial manipulation tasks, this paper presents a controller based on deep neural networks that classifies and learns accurate forces and moments caused by different robotic arms and interactions. Moreover, the forces arising from robotic arm motions are delicately used as part of the drone's power to save energy. Extensive real-world experiments demonstrate that the proposed method can adapt to various robotic arms and interactions when performing multi-task aerial manipulation.
The application of electronic control system is critical in the automatic production line, however it has an issue with erroneous performance positioning. The typical Embedded control is unable to address the producti...
详细信息
Kolmogorov-Arnold Networks (KANs) have shown potential as an alternative to Multi-Layer Perceptrons (MLPs) in neural networks, providing universal function approximation with fewer parameters and reduced memory usage....
详细信息
ISBN:
(纸本)9798331517939;9788993215380
Kolmogorov-Arnold Networks (KANs) have shown potential as an alternative to Multi-Layer Perceptrons (MLPs) in neural networks, providing universal function approximation with fewer parameters and reduced memory usage. In this paper, we explore the use of KANs as function approximators within the Proximal Policy Optimization (PPO) algorithm. We evaluate this approach by comparing its performance to the original MLP-based PPO using the DeepMind control Proprio robotics benchmark. Our results indicate that the KAN-based reinforcement learning algorithm can achieve comparable performance to its MLP-based counterpart, often with fewer parameters. These findings suggest that KANs may offer a more efficient option for reinforcement learning models. Our implementations can be found in the following link: https://***/victorkich/Kolmogorov-PPO.
In this paper, longitudinal and transverse lateral guidance methods are proposed to solve the trajectory tracking problem of hypersonic drone during the return of the energy management segment. A three-degree-of-freed...
详细信息
To increase the motion stability and accuracy of omnidirectional mobile robots for nuclear power inspection, an improved PID controller based on a fuzzy immune algorithm is proposed. Firstly, a kinematic model with ve...
详细信息
Corrosion of reinforcing bars is a major factor affecting the durability of reinforced concrete structures. The volume of corroded reinforcement expands and the protective layer gradually cracks, which in turn reduces...
详细信息
ISBN:
(纸本)9798350364200;9798350364194
Corrosion of reinforcing bars is a major factor affecting the durability of reinforced concrete structures. The volume of corroded reinforcement expands and the protective layer gradually cracks, which in turn reduces the serviceability of the structure. In this study, a fibre optic intelligent corrosion monitoring device based on magnetic sensing is investigated. A new type of magnetic probe is designed for sensing the corrosion of steel reinforcement, and strain sensing is carried out by utilizing high elasticity diaphragm and fibre optic grating structure. A finite element method is utilized to simulate the sensitivity and linearity of the device under different magnetic forces. The experimental results show that the sensor has good mechanical response effect and the fibre optic diaphragm stress sensing structure has good linearity, which can achieve longterm high-precision non-destructive monitoring of rebar corrosion.
This paper presents an impedance control approach for human-robot interaction (HRI) systems without using torque sensors. A sliding-mode disturbance observer based on super-twisting algorithm is proposed to estimate t...
详细信息
This paper presents an innovative approach to automatic volume control using image processing and deep learning techniques. The ability to automatically adjust volume levels based on environmental factors and user pre...
详细信息
暂无评论