Complexity of In-Vehicle Controllers and Their Effect on Task Performance

Smart functions in vehicles have led to an increase in the complexity of control interfaces. This study aims to develop a model for evaluating in-vehicle controller complexity and to investigate the relationship between complexity and task performance. A research framework consisting of three complexity dimensions (functional, behavioral, and structural dimensions) and controller-related variables was developed based on previous literature. A user experiment was conducted using 10 vehicles and 91 participants. A regression analysis was used to examine the relationship between the measurement variables and perceived controller complexity, and the results indicated correlations between them. An increase in functional dimension variables caused an increase in the perceived complexity level, while behavioral dimension variables are not a statistically significant predictor. Structural dimension variables showed different results depending on the characteristics of the variables. The results of the control task experiment showed a negative correlation between task performance and the perceived complexity level. In addition, satisfaction decreased with increasing levels of complexity. These results provide insights for managing in-vehicle controller complexity.     

A Novel Intelligent Multiobjective Simulated Annealing Algorithm for Designing Robust PID Controllers

This paper proposes an intelligent multiobjective simulated annealing algorithm (IMOSA) and its application to an optimal proportional integral derivative (PID) controller design problem. A well-designed PID-type controller should satisfy the following objectives: 1) disturbance attenuation; 2) robust stability; and 3) accurate setpoint tracking. The optimal PID controller design problem is a large-scale multiobjective optimization problem characterized by the following: 1) nonlinear multimodal search space; 2) large-scale search space; 3) three tight constraints; 4) multiple objectives; and 5) expensive objective function evaluations. In contrast to existing multiobjective algorithms of simulated annealing, the high performance in IMOSA arises mainly from a novel multiobjective generation mechanism using a Pareto-based scoring function without using heuristics. The multiobjective generation mechanism operates on a high-score nondominated solution using a systematic reasoning method based on an orthogonal experimental design, which exploits its neighborhood to economically generate a set of well-distributed nondominated solutions by considering individual and overall objectives. IMOSA is evaluated by using a practical design example of a super-maneuverable fighter aircraft system. An efficient existing multiobjective algorithm, the improved strength Pareto evolutionary algorithm, is also applied to the same example for comparison. Simulation results demonstrate high performance of the IMOSA-based method in designing robust PID controllers.     

Self-regulated Complexity in Neural Networks

Recordings of spontaneous activity of in vitro neuronal networks reveal various phenomena on different time scales. These include synchronized firing of neurons, bursting events of firing on both cell and network levels, hierarchies of bursting events, etc. These findings suggest that networks’ natural dynamics are self-regulated to facilitate different processes on intervals in orders of magnitude ranging from fractions of seconds to hours. Observing these unique structures of recorded time-series give rise to questions regarding the diversity of the basic elements of the sequences, the information storage capacity of a network and the means of implementing calculations. Due to the complex temporal nature of the recordings, the proper methods of characterizing and quantifying these dynamics are on the time–frequency plane. We thus introduce time-series analysis of neuronal network’s synchronized bursting events applying the wavelet packet decomposition based on the Haar mother-wavelet. We utilize algorithms for optimal tiling of the time–frequency plane to signify the local and global variations within the sequence. New quantifying observables of regularity and complexity are identified based on both the homogeneity and diversity of the tiling (Hulata et al., 2004, Physical Review Letters 92: 198181–198104 ). These observables are demonstrated while exploring the regularity–complexity plane to fulfill the accepted criteria (yet lacking an operational definition) of Effective Complexity. The presented question regarding the sequences’ capacity of information is addressed through applying our observables on recorded sequences, scrambled sequences, artificial sequences produced with similar long-range statistical distributions and on outputs of neuronal models devised to simulate the unique networks’ dynamics.     

Complexity Measures for Process Evolution

The foundation for process evolution research is the modelling of process structural complexity. With such a model, process systems can be directed toward acquiring good maintainability attributes according to the principles of engineering. In this paper a process management (PM) model is developed to acquire directly from the target process codes the knowledge hidden among and within components of process systems. With the knowledge acquired by the PM model, process structural complexity measures in terms of partitioning, restructuring and rewriting criteria are developed; a systematic process remodularization schema is derived, and algorithms for scheduling process changes are presented. These criteria and mechanisms are used to guide the process production chain.     

On the Evolution Complexity of Design Patterns

Software co-evolution can be characterised as a way to “adjust” any given software implementation to a change (“shift”) in the software requirements. In this paper, we propose a formal definition of evolution complexity to precisely quantify the cost of adjusting a particular implementation to a change (“shift”) in the requirements. As a validation, we show that this definition formalises intuition about the evolvability of design patterns.     

求解任务指派问题的差异演化算法磁

建立了任务指派问题的数学模型,采用差异演化算法对其进行求解,给出了差异演化算法求解该问题的具体方案,对不同的任务指派问题算例进行了仿真实验。结果表明,算法可以有效、快速地找到任务指派问题的最优解。     

Learning from Innate Behaviors: A Quantitative Evaluation of Neural Network Controllers

The aim was to investigate a method of developing mobile robot controllers based on ideas about how plastic neural systems adapt to their environment by extracting regularities from the amalgamated behavior of inflexible (nonplastic) innate subsystems interacting with the world. Incremental bootstrapping of neural network controllers was examined. The objective was twofold. First, to develop and evaluate the use of prewired or innate robot controllers to bootstrap backpropagation learning for Multilayer Perceptron (MLP) controllers. Second, to develop and evaluate a new MLP controller trained on the back of another bootstrapped controller. The experimental hypothesis was that MLPs would improve on the performance of controllers used to train them. The performances of the innate and bootstrapped MLP controllers were compared in eight experiments on the tasks of avoiding obstacles and finding goals. Four quantitative measures were employed: the number of sensorimotor loops required to complete a task; the distance traveled; the mean distance from walls and obstacles; the smoothness of travel. The overall pattern of results from statistical analyses of these quantities supported the hypothesis; the MLP controllers completed the tasks faster, smoother, and steered further from obstacles and walls than their innate teachers. In particular, a single MLP controller incrementally bootstrapped by a MLP subsumption controller was superior to the others.     

Understanding Neural Complexity: A Role For Reduction

Psychoneural reduction is under attack again, only this time from a former ally: cognitive neuroscience. It has become popular to think of the brain as a complex system whose theoretically important properties emerge from dynamic, non-linear interactions between its component parts. ``Emergence' is supposed to replace reduction: the latter is thought to be incapable of explaining the brain qua complex system. Rather than engage this issue at the level of theories of reduction versus theories of emergence, I here emphasize a role that reductionism plays – and will continue to play – even if neuroscience adopts this ``complex systems' view. In detailed investigations into the function of complex neural circuits, certain questions can only be addressed by moving down levels and scales. This role for reduction also finds a place for approaches that dominate mainstream neuroscience, like the widespread use of experimental techniques and theories from molecular biology and biochemistry. These are difficult to reconcile with the anti-reductionist sentiments of the ``complex systems' branch of cognitive neuroscience.     

On the Sample Complexity for Nonoverlapping Neural Networks

A neural network is said to be nonoverlapping if there is at most one edge outgoing from each node. We investigate the number of examples that a learning algorithm needs when using nonoverlapping neural networks as hypotheses. We derive bounds for this sample complexity in terms of the Vapnik-Chervonenkis dimension. In particular, we consider networks consisting of threshold, sigmoidal and linear gates. We show that the class of nonoverlapping threshold networks and the class of nonoverlapping sigmoidal networks on n inputs both have Vapnik-Chervonenkis dimension (nlog n). This bound is asymptotically tight for the class of nonoverlapping threshold networks. We also present an upper bound for this class where the constants involved are considerably smaller than in a previous calculation. Finally, we argue that the Vapnik-Chervonenkis dimension of nonoverlapping threshold or sigmoidal networks cannot become larger by allowing the nodes to compute linear functions. This sheds some light on a recent result that exhibited neural networks with quadratic Vapnik-Chervonenkis dimension.     

Learning from Innate Behaviors: A Quantitative Evaluation of Neural Network Controllers

The aim was to investigate a method of developing mobile robot controllers based on ideas about how plastic neural systems adapt to their environment by extracting regularities from the amalgamated behavior of inflexible (non-plastic) innate s ubsystems interacting with the world.Incremental bootstrapping of neural network controllers was examined. The objective was twofold. First, to develop and evaluate the use of prewired or innate robot controllers to bootstrap backpropagation learning for Multi-Layer Perceptron (MLP) controllers. Second, to develop and evaluate a new MLP controller trained on the back of another bootstrapped controller. The experimental hypothesis was that MLPs would improve on the performance of controllers used to train them. The performances of the innate and bootstrapped MLP controllers were compared in eight experiments on the tasks of avoiding obstacles and finding goals. Four quantitative measures were employed: the number of sensorimotor loops required to complete a task; the distance traveled; the mean distance from walls and obstacles; the smoothness of travel. The overall pattern of results from statistical analyses of these quantities su pported the hypothesis; the MLP controllers completed the tasks faster, smoother, and steered further from obstacles and walls than their innate teachers. In particular, a single MLP controller incrementally bootstrapped by a MLP subsumption controller was superior to the others.     

Pinning Stabilization of Linearly Coupled Stochastic Neural Networks via Minimum Number of Controllers

Pinning stabilization problem of linearly coupled stochastic neural networks (LCSNNs) is studied in this paper. A minimum number of controllers are used to force the LCSNNs to the desired equilibrium point by fully utilizing the structure of the network. In order to pinning control the LCSNNs to a certain desired state, only one controller is required for strongly connected network topology, and m controllers, which will be shown to be the minimum number, are needed for LCSNNs with m -reducible coupling matrix. The isolate node of the LCSNNs can be stable, periodic, or even chaotic. The coupling Laplacian matrix of the LCSNNs can be symmetric irreducible, asymmetric irreducible, or m-reducible, which means that the network topology can be strongly connected, weakly connected, or even unconnected. There is no constraint on the network topology. Some criteria are derived to judge whether the LCSNNs can be controlled in mean square by using designed controllers. The given criteria are expressed in terms of strict linear matrix inequalities, which can be easily checked by resorting to recently developed algorithm. Moreover, numerical examples including small-world and scale-free networks are also given to demonstrate that our theoretical results are valid and efficient for large systems.     

Convolutional Neural Network Structure Transformations for Complexity Reduction and Speed Improvement

Two methods of convolution-complexity reduction, and therefore acceleration of convolutional neural network processing, are introduced. Convolutional neural networks (CNNs) are widely used in computer vision problems. In the first method, we propose to change the structure of the convolutional layer of the neural network into a separable one, which is more computationally simple. It is shown experimentally that the proposed structure makes it possible to achieve up to a 5.6-fold increase in the operating speed of the convolutional layer for 11 × 11-sized convolutional filters without loss in recognition accuracy. The second method uses 1 × 1 fusing convolutions to increase the number of convolution outputs along with decreasing the number of filters. It decreases the computational complexity of convolution and provides an experimental processing speed increase of 11% in the case of large convolutional filters. It is shown that both proposed methods preserve accuracy when tested with the recognition of Russian letters, CIFAR-10, and MNIST images.     

Effect of Task Complexity and Stimulus Duration on Perceptual-Motor Performance of Two Disparate Age Groups

Abstract

This study was concerned with two task dimensions, complexity and stimulus duration, which previous research had shown to accentuate or reduce performance. differences between age groups. Young and old groups made an unguided movement at the onset of one stimulus light in a four-light display. Task complexity was varied by altering the number of response alternatives (1 or 2) while holding the display constant. Two stimulus durations were used: 0110 sec and 2.0 sec. Old subjects reacted 30 per cent slower and moved 7G percent slower than young. Both reaction time and movement time were slower for the complex task than for the simple. The difference between simple and complex movement time was significantly greater for old subjects than for young./ Young subjects moved faster with the 0.110 sec stimulus while old subjects moved faster with the 2.0 sec stimulus.     

Genetic Tuning of PID Controllers Using a Neural Network Model: A Seesaw Example

When genetic algorithms (GAs) are applied for PID parameter tuning, since the PID parameters are adjusted almost randomly, it is possible that the plant will be damaged due to abrupt changes in PID parameters. To solve this problem, a neural network will be used to model the plant and the genetic tuning procedure will be performed on the neural network instead of the plant. After determining the PID parameters in this off-line manner, these gains are then applied to the plant for on-line control. Moreover, considering that the neural network model may not be accurate enough, a method is also proposed for on-line fine-tuning of PID parameters. To show the validity of the proposed method, a seesaw system that has one input and two outputs will be used for experimental evaluation     

Evolution of Fuzzy Controllers for Robotic Vehicles: The Role of Fitness Function Selection

An important issue not addressed in the literature, is related to the selection of the fitness function parameters which are used in the evolution process of fuzzy logic controllers for mobile robot navigation. The majority of the fitness functions used for controllers evolution are empirically selected and (most of times) task specified. This results to controllers which heavily depend on fitness function selection. In this paper we compare three major different types of fitness functions and how they affect the navigation performance of a fuzzy logic controlled real robot. Genetic algorithms are employed to evolve the membership functions of these controllers. Further, an efficiency measure is introduced for the systematic analysis and benchmarking of overall performance. This measure takes into account important performance results of the robot during experimentation, such as the final distance from target, the time needed to reach its final position, the time of sensor activation, the mean linear velocity e.t.c. In order to examine the validity of our approach a low cost mobile robot has been developed, which is used as a testbed.     

A Neural Network Approach to Dynamic Task Assignment of Multirobots

In this paper, a neural network approach to task assignment, based on a self-organizing map (SOM), is proposed for a multirobot system in dynamic environments subject to uncertainties. It is capable of dynamically controlling a group of mobile robots to achieve multiple tasks at different locations, so that the desired number of robots will arrive at every target location from arbitrary initial locations. In the proposed approach, the robot motion planning is integrated with the task assignment, thus the robots start to move once the overall task is given. The robot navigation can be dynamically adjusted to guarantee that each target location has the desired number of robots, even under uncertainties such as when some robots break down. The proposed approach is capable of dealing with changing environments. The effectiveness and efficiency of the proposed approach are demonstrated by simulation studies.     

演化非线性参数估计在PID控制器设计中的应用研究

在目前的工业过程控制中,采用最多的控制策略依然是PID方式。这是由于PID控制器具有简单而固定的形式,较好的鲁棒性。PID参数复杂的整定问题一直是这一领域中的一个重要的技术问题。该文将由阶跃响应求取受控对象模型的过程看作是一个非线性回归问题,讨论了用演化算法来进行参数估计的方法和步骤。数值算例表明：该方法具有良好的计算效率和精度。这种方法也适用于一般的传递函数模型。