this paper evaluates the possibility of implementing a production line that incorporates the strategies of Industry 4.0 into its operation system, which includes the use of the Internet of things (IoT), artificial int...
详细信息
this paper explores design, modeling and hovering control of a new under-actuated 5-DoF (degree of freedom) tilt-birotor robot. Specifically, the robot has an assembled inverted pendulum to be an extra actuating input...
详细信息
ISBN:
(纸本)9781728177090
this paper explores design, modeling and hovering control of a new under-actuated 5-DoF (degree of freedom) tilt-birotor robot. Specifically, the robot has an assembled inverted pendulum to be an extra actuating input in addition to a pair of tilt wings. Hence, it has a 5-DoF actuator control input vector: two motor thrusts, two tilt angles, and one tunable pendulum angle. We show the model analysis in terms of the Newton-Euler formulation and establish a key equation between the model control inputs and the actuator inputs. Based on that, we are able to achieve the hovering control task using an inner-outer-loop design. We also illustrate the results by numerical and experimental tests.
Motor imagery (MI) EEG-based brain-computer interface (BCI) facilitates direct communication between the brain’s intentions and a computer. In essence, it allows a person to control external equipment by decoding EEG...
详细信息
ISBN:
(数字)9798350391916
ISBN:
(纸本)9798350391923
Motor imagery (MI) EEG-based brain-computer interface (BCI) facilitates direct communication between the brain’s intentions and a computer. In essence, it allows a person to control external equipment by decoding EEG signals during the mental imagery of limb movements. However, due to the intricate individual variances in EEG signals, creating a general decoding model with parameters applicable to all subjects is exceptionally challenging. Consequently, a prolonged calibration process is necessary to gather labeled subject-specific data for each individual, making it less user-friendly. A potential solution to this problem is transfer learning, a methodology that transfers knowledge from related domains to a target domain. To tackle the problem, this paper proposes a novel transfer learning approach on the Riemannian manifold framework in the context of multiclass MI EEG-based BCI classification. Particularly, a user-specific frequency band selection (FBS) method with MI EEG class distinctiveness is utilized to improve the accuracy and efficiency of Riemannian space calculations, which is measured using the inter-class distance and intra-class variance on the manifold. then, the Riemannian space Alignment (RA) strategy is used to calibrate the MI EEG variances of different subjects. the comparative experiments between the proposed approach and baseline/conventional methods are conducted on a public dataset with four-class motor imagery EEG, including two-class transfer learning scenario and four-class transfer learning scenario. proposed transfer learning approach is outperformed. Compared withthe baseline/conventional methods using a fixed wide frequency band, the preliminary results suggests that the proposed approach can significantly improve the transfer learning performance for the MI EEG signals from different subjects in Riemannian space.
Cloth manipulation is common in domestic and service tasks, and most studies use fixed-base manipulators to manipulate objects whose sizes are relatively small with respect to the manipulators' workspace, such as ...
Cloth manipulation is common in domestic and service tasks, and most studies use fixed-base manipulators to manipulate objects whose sizes are relatively small with respect to the manipulators' workspace, such as towels, shirts, and rags. In contrast, manipulation of large-scale cloth, such as bed making and tablecloth spreading, poses additional challenges of reachability and manipulation control. To address them, this paper presents a novel framework to spread large-scale cloth, with a single-arm mobile manipulator that can solve the reachability issue, for an initial feasibility study. On the manipulation control side, without modeling highly deformable cloth, a vision-based manipulation control scheme is applied and based on an online-update Jacobian matrix mapping from selected feature points to the end-effector motion. To coordinate the control of the manipulator and mobile platform, Behavior Trees (BTs) are used because of their modularity. Finally, experiments are conducted, including validation of the model-free manipulation control for cloth spreading in different conditions and the large-scale cloth spreading framework. the experimental results demonstrate the large-scale cloth spreading task feasibility with a single-arm mobile manipulator and the model-free deformation controller.
In the existing literature, many methods have been utilized in solving the pursuit evasion game. However, most of these methods have one thing in common: all pursuers have to know the evader's position. this paper...
详细信息
ISBN:
(纸本)9781728177090
In the existing literature, many methods have been utilized in solving the pursuit evasion game. However, most of these methods have one thing in common: all pursuers have to know the evader's position. this paper presents a method combining the multi-agent leader-following control and reinforcement learning, which aims at addressing a pursuit evasion game only when partial pursuers have the knowledge of the position of the evader who moves randomly in two-dimensional grid space. through decomposing the team task, pursuers realize the encirclement of the evader. Simulation experiment validates the effectiveness of our method.
the purpose of this work is to develop a robust iterative learning control for nonlinear systems based on neural networks. In order to introduce the robustness to the control scheme the problem of accurate estimation ...
详细信息
ISBN:
(纸本)9781728177090
the purpose of this work is to develop a robust iterative learning control for nonlinear systems based on neural networks. In order to introduce the robustness to the control scheme the problem of accurate estimation of uncertainties associated withthe black-box type model is concerned. An uncertainty of the system is derived in terms of the variance of the model output prediction using a concept of Fisher information matrix well-known in the optimum experimental design theory. Once the bounds of the system response are estimated, they can be directly applied during training of the learning controller by a rigorous definition of the penalty cost function. then, a neural controller is suitably adopted to the effective design of iterative learning control for nonlinear systems. the proposed approach is experimentally verified on the example of a magnetic levitation system.
In this paper, an event-triggered optimal adaptive control is developed for robot trajectory tracking system. Due to the nonlinearity of Hamilton function, we apply the actor-critic neural network structure to solve i...
详细信息
ISBN:
(纸本)9781728177090
In this paper, an event-triggered optimal adaptive control is developed for robot trajectory tracking system. Due to the nonlinearity of Hamilton function, we apply the actor-critic neural network structure to solve it. Firstly, the critic network is used to estimate the cost function and the actor network is used to estimate the optimal event-triggered control law. Due to the advantage of event-triggered method, the weight update rate of actor-critic neural network only occurs when the triggering condition is violated, which save a lot of communication resources. then, the event-triggered robot trajectory tracking system is ultimately bounded by Lyapunov stability analysis. Finally, the simulation show that the proposed method is effective.
Managing multiple robots into a formation can be beneficial, especially in logistics sectors where multiple robots can work together to transport larger loads. this paper presents a consensus control law for formation...
详细信息
ISBN:
(纸本)9781728177090
Managing multiple robots into a formation can be beneficial, especially in logistics sectors where multiple robots can work together to transport larger loads. this paper presents a consensus control law for formation with navigation and obstacle avoidance of multiple wheeled mobile robots. the formation control is based on adapting a consensus algorithm from flocking, and we propose an obstacle avoidance methodology that ensures the formation while navigating around obstacles. Simulations of the control law using four wheeled mobile robots as well as experiments using actual industrial robots are shown in order to validate the theory.
the automation of electronic waste disassembly processes is very challenging due to the diversity and conditions of the products, but also due to the heterogeneous disassembly environments based on different hardware ...
the automation of electronic waste disassembly processes is very challenging due to the diversity and conditions of the products, but also due to the heterogeneous disassembly environments based on different hardware and software components. All these resources and the subjacent information flows should be coordinated and integrated to ensure an effective disassembly process. In this paper, we present a developed architecture for closed-loop planning and controlling dynamic disassembly processes of robots. We extended the infrastructure provided by the Robot Operating System (ROS) to integrate the components of the robotic system with its vision system and the software components for inference, replanning, and knowledge transfer. the architecture was implemented for a real use case of antenna amplifier disassembly. the implemented framework is generalizable for other purposes implementing four automatic configuration mechanisms to support domain-specific tailoring: code generation, object serialization, object mapping, and object-triple mapping.
this paper presents a new method for trajectory planning and control of a 2R planar horizontal robotic arm with only the first joint actuated, which is known to be controllable but not asymptotically stabilizable with...
详细信息
ISBN:
(纸本)9781728177090
this paper presents a new method for trajectory planning and control of a 2R planar horizontal robotic arm with only the first joint actuated, which is known to be controllable but not asymptotically stabilizable with smooth feedback controllers. the main idea is to first determine an admissible trajectory that satisfies boththe constraints of system dynamics and boundary value conditions, and then design a feedforward controller for the system. For complex and highly nonlinear systems, an optimization method is applied to determine the trajectory. Moreover, a time-scaling method can be used to controlthe magnitude of the inputs and also make it easier to find a solution in the optimization procedure. To further improve the robustness of the controller, a feedback controller is designed along the planned trajectory. Position to position control of the robot is simulated to demonstrate the effectiveness of the method.
暂无评论