In this paper, the iterative learning control (ILC) literature published between 1998 and 2004 is categorized and discussed, extending the earlier reviews presented by two of the authors. The papers includes a general introduction to ILC and a technical description of the methodology. The selected results are reviewed, and the ILC literature is categorized into subcategories within the broader division of application-focused and theory-focused results.

Iterative Learning Control: Brief Survey and Categorization

An evolutionary recurrent network which automates the design of recurrent neural/fuzzy networks using a new evolutionary learning algorithm is proposed in this paper. This new evolutionary learning algorithm is based on a hybrid of genetic algorithm (GA) and particle swarm optimization (PSO), and is thus called HGAPSO. In HGAPSO, individuals in a new generation are created, not only by crossover and mutation operation as in GA, but also by PSO. The concept of elite strategy is adopted in HGAPSO, where the upper-half of the best-performing individuals in a population are regarded as elites. However, instead of being reproduced directly to the next generation, these elites are first enhanced. The group constituted by the elites is regarded as a swarm, and each elite corresponds to a particle within it. In this regard, the elites are enhanced by PSO, an operation which mimics the maturing phenomenon in nature. These enhanced elites constitute half of the population in the new generation, whereas the other half is generated by performing crossover and mutation operation on these enhanced elites. HGAPSO is applied to recurrent neural/fuzzy network design as follows. For recurrent neural network, a fully connected recurrent neural network is designed and applied to a temporal sequence production problem. For recurrent fuzzy network design, a Takagi-Sugeno-Kang-type recurrent fuzzy network is designed and applied to dynamic plant control. The performance of HGAPSO is compared to both GA and PSO in these recurrent networks design problems, demonstrating its superiority.

A hybrid of genetic algorithm and particle swarm optimization for recurrent network design

The subject of the paper is the motion control problem of wheeled mobile robots (WMRs) in environments without obstacles. With reference to the popular unicycle kinematics, it is shown that dynamic feedback linearization is an efficient design tool leading to a solution simultaneously valid for both trajectory tracking and setpoint regulation problems. The implementation of this approach on the laboratory prototype SuperMARIO, a two-wheel differentially driven mobile robot, is described in detail. To assess the quality of the proposed controller, we compare its performance with that of several existing control techniques in a number of experiments. The obtained results provide useful guidelines for WMR control designers.

/pdf/wmr-control-via-dynamic-feedback-linearization-design-25vbjh5hnl.pdf

WMR control via dynamic feedback linearization: design, implementation, and experimental validation

In this paper, a TSK-type recurrent fuzzy network (TRFN) structure is proposed. The proposal calls for the design of TRFN by either neural network or genetic algorithms depending on the learning environment. A recurrent fuzzy network is described which develops from a series of recurrent fuzzy if-then rules with TSK-type consequent parts. The recurrent property comes from feeding the internal variables, derived from fuzzy firing strengths, back to both the network input and output layers. In this configuration, each internal variable is responsible for memorizing the temporal history of its corresponding fuzzy rule. The internal variable is also combined with external input variables in each rule's consequence, which shows an increase in network learning ability. TRFN design under different learning environments is next advanced. For problems where supervised training data is directly available, TRFN with supervised learning (TRFN-S) is proposed, and a neural network (NN) learning approach is adopted for TRFN-S design. An online learning algorithm with concurrent structure and parameter learning is proposed. With flexibility of partition in the precondition part, and outcome of TSK-type, the TRFN-S displays both small network size and high learning accuracy. For problems where gradient information for NN learning is costly to obtain or unavailable, like reinforcement learning, TRFN with Genetic learning (TRFN-G) is put forward. The precondition parts of TRFN-G are also partitioned in a flexible way, and all free parameters are designed concurrently by genetic algorithm. Owing to the well-designed network structure of TRFN, TRFN-G, like TRFN-S, is characterized by high learning accuracy. To demonstrate the superior properties of TRFN, TRFN-S is applied to dynamic system identification and TRFN-G to dynamic system control. By comparing the results to other types of recurrent networks and design configurations, the efficiency of TRFN is verified.

/pdf/a-tsk-type-recurrent-fuzzy-network-for-dynamic-systems-4kgrso49v1.pdf

A TSK-type recurrent fuzzy network for dynamic systems processing by neural network and genetic algorithms

Autonomous unmanned air vehicle ∞ight control systems require robust path generation to account for terrain obstructions, weather, and moving threats such as radar, jammers, and unfriendly aircraft. In this paper, we outline a feasible, hierarchal approach for real-time motion planning of small autonomous flxed-wing UAVs. The approach divides the trajectory generation into four tasks: waypoint path planning, dynamic trajectory smoothing, trajectory tracking, and low-level autopilot compensation. The waypoint path planner determines the vehicle’s route without regard for the dynamic constraints of the vehicle. This results in a signiflcant reduction in the path search space, enabling the generation of complicated paths that account for pop-up and dynamically moving threats. Kinematic constraints are satisfled using a trajectory smoother which has the same kinematic structure as the physical vehicle. The third step of the approach uses a novel tracking algorithm to generate a feasible state trajectory that can be followed by a standard autopilot. Monte-Carlo simulations were done to analyze the performance and feasibility of the approach and determine real-time computation requirements. A planar version of the algorithm has also been implemented and tested in a low-cost micro-controller. The paper describes a custom UAV built to test the algorithms.

/pdf/autonomous-vehicle-technologies-for-small-fixed-wing-uavs-1lr64kzlwl.pdf

Autonomous Vehicle Technologies for Small Fixed-Wing UAVs

Proposes a recurrent fuzzy neural network (RFNN) structure for identifying and controlling nonlinear dynamic systems. The RFNN is inherently a recurrent multilayered connectionist network for realizing fuzzy inference using dynamic fuzzy rules. Temporal relations are embedded in the network by adding feedback connections in the second layer of the fuzzy neural network (FNN). The RFNN expands the basic ability of the FNN to cope with temporal problems. In addition, results for the FNN-fuzzy inference engine, universal approximation, and convergence analysis are extended to the RFNN. For the control problem, we present the direct and indirect adaptive control approaches using the RFNN. Based on the Lyapunov stability approach, rigorous proofs are presented to guarantee the convergence of the RFNN by choosing appropriate learning rates. Finally, the RFNN is applied in several simulations (time series prediction, identification, and control of nonlinear systems). The results confirm the effectiveness of the RFNN.

https://ir.nctu.edu.tw:443/bitstream/11536/30338/1/000089458200001.pdf

Identification and control of dynamic systems using recurrent fuzzy neural networks

The tracking control problem with saturation constraint for a class of unicycle-modeled mobile robots is formulated and solved using the backstepping technique and the idea from the LaSalle's invariance principle. A global result is presented in which several constraints on the linear and the angular velocities of the mobile robot from recent literature are dropped. The proposed controller can simultaneously solve both the tracking and regulation problems of a unicycle-modeled mobile robot. With the proposed control laws, the robot can globally follow any path specified by a straight line, a circle or a path approaching the origin using a single controller. As demonstrated, the circular and parallel parking control problem are solved using the proposed controller. Computer simulations are presented which confirm the effectiveness of the proposed tracking control law. Practical experimental results validate the simulations.

https://ir.nctu.edu.tw:443/bitstream/11536/29781/1/000167656200010.pdf

Tracking control of unicycle-modeled mobile robots using a saturation feedback controller

In this paper, a direct adaptive iterative learning control (DAILC) based on a new output-recurrent fuzzy neural network (ORFNN) is presented for a class of repeatable nonlinear systems with unknown nonlinearities and variable initial resetting errors. In order to overcome the design difficulty due to initial state errors at the beginning of each iteration, a concept of time-varying boundary layer is employed to construct an error equation. The learning controller is then designed by using the given ORFNN to approximate an optimal equivalent controller. Some auxiliary control components are applied to eliminate approximation error and ensure learning convergence. Since the optimal ORFNN parameters for a best approximation are generally unavailable, an adaptive algorithm with projection mechanism is derived to update all the consequent, premise, and recurrent parameters during iteration processes. Only one network is required to design the ORFNN-based DAILC and the plant nonlinearities, especially the nonlinear input gain, are allowed to be totally unknown. Based on a Lyapunov-like analysis, we show that all adjustable parameters and internal signals remain bounded for all iterations. Furthermore, the norm of state tracking error vector will asymptotically converge to a tunable residual set as iteration goes to infinity. Finally, iterative learning control of two nonlinear systems, inverted pendulum system and Chua's chaotic circuit, are performed to verify the tracking performance of the proposed learning scheme.

https://ir.nctu.edu.tw:443/bitstream/11536/26712/1/000221578100004.pdf

Direct adaptive iterative learning control of nonlinear systems using an output-recurrent fuzzy neural network

For the last decade, the need for electric driven vehicle has risen rapidly due to the global warming problem. A high efficient motor need to be developed to replace traditional engine. In this paper, the authors present a fuzzy logic controller (FLC) for sensorless brushless dc (BLDC) motor. The proposed FLC is based on the terminal voltage measurement as the sensorless method for BLDC motor control. There are two modules designed in the speed control of BLDC motor, i.e. command and regulating modules. Command module is to find and issue commutation period and PWM duty cycle to the BLDC motor for desired speed. The regulating module is designed by applying a FLC with sensorless technology and is used to regulate the speed of BLDC motor under various disturbances, such as loading effect. Two resistances are adopted to detect the zero-crossing point (ZCP) of back-EMF signal on the unexcited phase instead of using the expensive Hall sensors. The regulating module can regulate accurately and quickly the PWM duty cycle by fuzzy reasoning which makes the BLDC motor rotate smoothly at desired rotation speed even there exists an external disturbance. In order to reduce the computational load of real-time FLC for the microcontroller C8051F330, we can perform the FLC computation off-line to cover nearly all cases. These data will be recorded and organized as a Look-Up Table (LUT). This paper shows that a regulating module designed by FLC is better than a none regulation module or a regulating module with a P controller.

Intelligent control of high-speed sensorless brushless DC motor for intelligent automobiles

In this paper, we propose a Takagi-Sugeno recurrent fuzzy neural network (TSRFNN) for the identification and control of nonlinear dynamic systems. The TSRFNN combines the recurrent multi-layered connectionist network with the dynamic Takagi-Sugeno (TS) fuzzy model. The temporal information is embedded in the recurrent structure by adding feedback connections between the state layer and the input layer of the fuzzy neural net (FNN). Based on the derived dynamic backpropagation (DBP) and recursive least squares (RLS) algorithms, the parameters in the TSRFNN are adjusted online. Compared with the traditional recurrent FNNs (RFNNs), the proposed TSRFNN not only has a smaller network structure and a smaller number of network parameters, but also a faster convergence speed and better learning performance.

Ching-Cheng Teng

Papers

Identification and control of dynamic systems using recurrent fuzzy neural networks

Tracking control of unicycle-modeled mobile robots using a saturation feedback controller

Direct adaptive iterative learning control of nonlinear systems using an output-recurrent fuzzy neural network

Intelligent control of high-speed sensorless brushless DC motor for intelligent automobiles

Takagi-Sugeno recurrent fuzzy neural networks for identification and control of dynamic systems