Feng-Chun Tai

Adaptive steering control using fuzzy CMAC for electric seatless unicycles

This paper presents an adaptive steering control of an electric seatless unicycle using fuzzy cerebella model articulation controller (FCMAC), which are employed to approximate the frictions between the wheel and terrain surface. A backstepping controller with on-line parameter tuning rules is then presented to simultaneously achieve self-balancing and forward motion of the vehicle based on the riders body inclination. The performance and merit of the proposed method are well exemplified by conducting one simulation on an electric seatless unicycle.

Distributed Consensus Formation Control with Collision and Obstacle Avoidance for Uncertain Networked Omnidirectional Multi-robot Systems Using Fuzzy Wavelet Neural Networks

This paper presents a distributed consensus formation control with collision and obstacle avoidance using fuzzy wavelet neural networks (FWNNs) for a group of networked mobile Mecanum-wheeled omnidirectional robots (MWORs) with uncertainties. The dynamic behavior of each uncertain MWOR is modeled by a reduced three-input–three-output second-order state equation with uncertainties, and the multi-MWOR system is modeled by graph theory. Using the Lyapunov stability theory and online learning the system uncertainties via FWNNs, an adaptive and distributed consensus backstepping control approach is presented to carry out formation control in the presence of uncertainties. Collision and obstacle-avoidance methods are provided to avoid any collisions among MWORs and their working environments. Five simulations are conducted to show the effectiveness and merit of the proposed method .

Adaptive steering control of an electric unicycle

This paper presents techniques for adaptive steering control of an electric unicycle with a steering turning mechanism, in order to achieve self-balancing and speed tracking simultaneously. A state feedback control method using the linear quadratic regulator approach is first presented to simultaneously achieve self-balancing and speed tracking, and then an adaptive friction compensating term is proposed to overcome frictions caused by different terrain surfaces. The performance and merit of the proposed control method are well exemplified by conducting two simulations and five experiments on a laboratory-built electric unicycle.

Cooperation and task execution of an anthropomorphous two-armed robot: An application to coffee making

This paper presents techniques for cooperation and task execution of an anthropomorphous two-armed robot with two seven degrees of freedom arms. An inverse kinematic solver is proposed to find all joint angles for given postures of two effectors on both arms. Any task can always be separated into many sub-tasks, in which some sub-tasks may have the same action. For executions of these sub-task can be realized by composition of the motion processes. In particular, this paper will emphasize on the description of the task regarding how to coffee making via two-armed cooperation, because this task requires various motion. Experimental results are conducted for illustration of effectiveness of the proposed methods.

Decentralized cooperative transportation with obstacle avoidance using fuzzy wavelet neural networks for uncertain networked omnidirectional multi-robots

This paper presents a decentralized cooperative transportation control method with obstacle avoidance using fuzzy wavelet neural networks (FWNN) and consensus algorithm for a group of mobile Mecanum-wheeled omnidirectional robots (MWORs) with uncertainties, in order to get together to move a large payload. The dynamic behavior of each uncertain MWOR is modelled by a reduced three-input-three-output second-order system model and the uncertain multi-MWOR system is modeled by graph theory. By online learning the system uncertainties using FWNN and using the Lyapunov stability theory, an intelligent adaptive, cooperative consensus-based control approach is presented to carry out transportation control with uncertainties. An obstacle avoidance method is proposed to modify the generating trajectory of the virtual leader, in order to avoid any collisions between the robots and the environment. Two simulations are conducted to show the effectiveness of the proposed method.

Adaptive Predictive PID Control Using Fuzzy Wavelet Neural Networks for Nonlinear Discrete-Time Time-Delay Systems

This paper presents a novel adaptive predictive proportional–integral–derivative (PID) control using fuzzy wavelet neural networks (FWNN) for a kind of highly nonlinear discrete-time system with time delay. The proposed controller, abbreviated as FWNN-APPID, is composed of an adaptive predictive PID controller with abilities of accurate tracking and disturbance rejection and an FWNN identifier with online parameter tuning and estimation. Several simulations for controlling a highly nonlinear time-delay process show constant disturbances rejection and its performance of setpoint tracking for the proposed FWNN-APPID control method, thus clearly showing its effectiveness and merit. Experimental results on a real PET stretch blow molding machine show the applicability of the proposed method.

Intelligent sliding-mode formation control for uncertain networked heterogeneous Mecanum-wheeled omnidirectional platforms

This paper presents an intelligent sliding mode formation control using recurrent fuzzy wavelet neural networks (RFWNN) for a group of uncertain, networked heterogeneous Mecanum-wheeled omnidirectional platforms (MWOPs). The dynamic behavior of each uncertain MWOP is modelled by a reduced three-input-three-output second-order state equation and the multi-MWOP system is modeled by a directed graph. By using the Lyapunov stability theory and online learning the system uncertainties via RFWNN, an intelligent adaptive, sliding mode control approach is presented to carry out formation control in presence of uncertainties. Two simulations are conducted to show the effectiveness and merit of the proposed method with existing collision-free and obstacle-avoidance approaches.

Intelligent adaptive distributed consensus formation control for uncertain networked heterogeneous swedish-wheeled omnidirectional multi-robots

This paper presents an distributed consensus formation control using recurrent fuzzy wavelet neural networks (RFWNN) for a group of heterogeneous mobile three-Swedish-wheeled omnidirectional robots (TSWORs) with uncertainties. The dynamic behavior of each TSWOR is modelled by a three-input-three-output second-order state equation and the multirobot system is modeled by a directed graph. By online learning the system uncertainties using RFWNN and using the Lyapunov stability theory, an intelligent adaptive distributed consensus formation control approach is presented to carry out formation control in the presence of heterogeneity and uncertainties. Simulations are conducted to show the effectiveness and merits of the proposed method.

Backstepping sliding-mode leader-follower consensus formation control of uncertain networked heterogeneous nonholonomic wheeled mobile multirobots

This paper presents a leader-follower consensus formation control method using backstepping sliding-mode control for a group of uncertain, networked heterogeneous nonholonomic wheeled mobile robots (NWMRs), in order to achieve formation keeping and trajectory tracking, respectively. The NWMRs are composed of two kind of wheeled mobile robots, including nonholonomic self-balancing two-wheeled mobile robots (NSBTWMRs) and nonholonomic wheeled differential-driving mobile Robots (NWDDMRs). The dynamic behavior of each NWMR is governed by its second-order dynamic model, and the networked multi-NWMR system is modeled by a directed graph. By using the Lyapunov stability and sliding-mode control theories, one intelligent adaptive, distributed consensus control approach is respectively presented to carry out formation keeping and trajectory tracking in the presence of uncertainties, in order to not only keep all the robots in formation, but also let them track their desired trajectories and maintain them in formation, respectively. Simulations are conducted to show the effectiveness and merits of the proposed methods.

Intelligent predictive temperature control using PSO-RGA for transfer mold heating processes in semiconductor die packaging machines

This paper presents an intelligent predictive PI temperature control using particle swarm optimization - real coded genetic algorithm (PSO-RGA) for transfer molding modules in semiconductor die packaging machines. The system parameters of the transfer molding process are obtained by using the well-known reaction curve method. The best control parameters of the PI controller are offline tuned by using PSO-RGA algorithm. The set-point tracking, disturbance rejection, and robustness capabilities of the proposed method are well exemplified by conducting simulations and experiments on a real transfer mold process.