Fuzzylot: a novel self-organising fuzzy-neural rule-based pilot system for automated vehicles

Pasquier, M.; Quek, Chai; Toh, Mary

doi:10.1016/s0893-6080(01)00048-x

Cited by 58 publications

(33 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The C2i lab undertakes intense research in the study and development of advanced brain-inspired learning memory architectures [74]- [78] for the modeling of complex, dynamic, and nonlinear systems. These techniques have been successfully applied to numerous novel applications such as automated driving [58], signature forgery detection [79], gear control for the continuous variable transmission (CVT) system in an automobile [80], fingerprint verification [81], bank failure classification and early warning system (EWS) [82], computational finance [83], [84], as well as in the biomedical engineering domain [85], [86]. …”

Section: Discussionmentioning

confidence: 99%

“…In this experiment, a driving simulator (as developed in [58]) is employed to capture the behavioral response of the human driver. The simulator consists of a 3-D virtual driving environment that integrates a detailed model of the vehicle dynamics and engine characteristics together with the environmental parameters such as road profiles.…”

Section: A Automatic Control Of Car Maneuvermentioning

confidence: 99%

See 1 more Smart Citation

Hierarchically Clustered Adaptive Quantization CMAC and Its Learning Convergence

Teddy

Lai²,

Quek

2007

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Abstract-The cerebellar model articulation controller (CMAC) neural network (NN) is a well-established computational model of the human cerebellum. Nevertheless, there are two major drawbacks associated with the uniform quantization scheme of the CMAC network. They are the following: 1) a constant output resolution associated with the entire input space and 2) the generalization-accuracy dilemma. Moreover, the size of the CMAC network is an exponential function of the number of inputs. Depending on the characteristics of the training data, only a small percentage of the entire set of CMAC memory cells is utilized. Therefore, the efficient utilization of the CMAC memory is a crucial issue. One approach is to quantize the input space nonuniformly. For existing nonuniformly quantized CMAC systems, there is a tradeoff between memory efficiency and computational complexity. Inspired by the underlying organizational mechanism of the human brain, this paper presents a novel CMAC architecture named hierarchically clustered adaptive quantization CMAC (HCAQ-CMAC). HCAQ-CMAC employs hierarchical clustering for the nonuniform quantization of the input space to identify significant input segments and subsequently allocating more memory cells to these regions. The stability of the HCAQ-CMAC network is theoretically guaranteed by the proof of its learning convergence. The performance of the proposed network is subsequently benchmarked against the original CMAC network, as well as two other existing CMAC variants on two real-life applications, namely, automated control of car maneuver and modeling of the human blood glucose dynamics. The experimental results have demonstrated that the HCAQ-CMAC network offers an efficient memory allocation scheme and improves the generalization and accuracy of the network output to achieve better or comparable performances with smaller memory usages.Index Terms-Cerebellar model articulation controller (CMAC), hierarchical clustering, hierarchically clustered adaptive quantization CMAC (HCAQ-CMAC), learning convergence, nonuniform quantization.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: A Automatic Control Of Car Maneuvermentioning

confidence: 99%

Hierarchically Clustered Adaptive Quantization CMAC and Its Learning Convergence

Teddy

Lai²,

Quek

2007

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

show abstract

“…These research endeavors culminated with the developments of the human hippocampus-inspired learning memory systems such as GenSoFNN [10,28,35], Pseudo Adaptive Complementary Learning networks [42,43] and POPFNN [44][45][46], as well as cerebellar-based computational models [47,48] for the modeling of complex, dynamic and non-linear problem domains. The application of these brain-inspired learning memory systems is actively pursued, and they have been successfully applied to automated driving [49], signature forgery detection [50], gear control for continuous-variable-transmission in automobile [51], fingerprint verification [52], medical decision-support [28,53] and computational finance [35,46,54].…”

Section: Discussionmentioning

confidence: 99%

A brain-inspired fuzzy semantic memory model for learning and reasoning with uncertainty

Tung

Quek

2007

Neural Comput & Applic

View full text Add to dashboard Cite

Decision-making pervades the human experience. The human decision process is driven by rational reasoning, which is the capacity to use the faculty of reason to facilitate logical thinking and to derive uncertain but sensible arguments from existing knowledge and the observed fact. Knowledge refers to the accumulation and the continuous neurological organization of information via the repeated exposure to its effective usage. Functionally, a decision support system seeks to provide a systematic and human-like way to data analysis by synthesizing an expert's knowledge and reasoning capability to support the decision process of the user. However, conventional knowledge engineering and decision support systems often performed poorly when they are applied to problem domains festered with uncertain information, where the quality of the observed data is compromised by measurement noises. This paper presents T2-GenSoFNN, a braininspired fuzzy semantic memory model embedded with Type-2 fuzzy logic inference for learning and reasoning with noise-corrupted data. The proposed T2-GenSoFNN model is applied to the modeling of human insulin levels for the proper regulation of blood glucose concentration in diabetes therapy. The results are encouraging.

show abstract

“…-Adaptive cruise control for the vehicles controlled by the driver; road following control for automated driving; collision prevention systems [80][81][82], -Processing sensor information; recognition of driving environment parameters; vehicle localization [83][84][85][86][87][88][89], -Coordination of road vehicle platoon systems [90][91][92], -Control architecture of autonomous vehicles [93][94][95][96]; -Specific problems of brake, traction and steering control systems of autonomous vehicles [97][98][99]; -Automated parking systems [100][101][102].…”

Section: Fuzzy Methods and Vehicle-environment Interactionmentioning

confidence: 99%

A review of fuzzy methods in automotive engineering applications

Ivanov

2015

Eur. Transp. Res. Rev.

View full text Add to dashboard Cite

Purpose The paper addresses evolution of fuzzy systems for core applications of automotive engineering. Methods The presented study is based on the analysis of bibliography dedicated to fuzzy sets and fuzzy control for ground vehicles. A special attention is given to fuzzy approaches used in the following domains of automotive engineering: vehicle dynamics control systems, driver and driving environment identification, ride comfort control, and energy management of electric vehicles. Results The bibliographical analysis, supplemented with statistics of relevant research publications, has allowed to allocate the most important fuzzy application cases for each domain. In particular, it concerns driver identification, humanmachine interface, recognition of road conditions, and controllers of vehicle chassis and powertrain systems. It is found out that fuzzy methods have the primary use most of all for tasks requiring identification and forecasting procedures, especially in conditions of limited informational space. Additional observation that can be also derived from the presented survey points to reasonable integration of fuzzy technique with other control engineering methods to improve the performance of automotive control systems. Conclusions In the aggregate the performed review indicates that fuzzy computing can be considered as a versatile tool for automotive engineering applications of different nature.

show abstract

Fuzzylot: a novel self-organising fuzzy-neural rule-based pilot system for automated vehicles

Cited by 58 publications

References 12 publications

Hierarchically Clustered Adaptive Quantization CMAC and Its Learning Convergence

Hierarchically Clustered Adaptive Quantization CMAC and Its Learning Convergence

A brain-inspired fuzzy semantic memory model for learning and reasoning with uncertainty

A review of fuzzy methods in automotive engineering applications

Contact Info

Product

Resources

About