A GENERIC SELF-ORGANISING FUZZY-NEURAL NETWORK AND ITS APPLICATION TO AUTOMATED DRIVING

摘要

Existing neural fuzzy (neuro-fuzzy) networks proposed in the literature can be broadly classified into two groups. The first group is essentially fuzzy systems with self-tuning capabilities and requires an initial rule base to be specified prior to training. The second group of neural fuzzy networks, on the other hand, is able to automatically formulate the fuzzy rules from the numerical training data. No initial rule base needs to be specified prior to training. However, most existing neural fuzzy systems (whether they belong to the first or second group) encountered one or more of the following major problems. They are (1) Inconsistent rule-base; (2) Heuristically defined node operations; (3) Susceptibility to noisy training data and the stability-plasticity dilemma [6] and (4) Needs for prior knowledge such as the number of clusters to be computed. Hence, a novel neural fuzzy system that is immune to the above-mentioned deficiencies is proposed in this paper. This new neural fuzzy system is named the Generic Self-organising Fuzzy Neural Network (GenSoFNN). The GenSoFNN network employs a new clustering technique known as Discrete Incremental Clustering (DIC) to enhance its clustering flexibility and tolerance to noisy data. The fuzzy rule base of the GenSoFNN network is consistent and compact as GenSoFNN has built-in mechanisms to identify and prune redundant and/or obsolete rules. The proposed GenSoFNN is subsequently coupled with a driving simulator to develop a fully automated pilot system (auto-pilot) for an Intelligent Vehicle (IV). Driving a vehicle is a very complex task that humans can perform relatively well. Hence the idea to capture the human driving expertise in the form of an intuitive set of IF-THEN fuzzy rules is very appealing. The driving simulator records the steering and speed control actions of a human driver under different road scenarios. Subsequently, the GenSoFNN network is used to formulate a set of fuzzy rules that fits the recorded driving behavior of the human driver. This set of fuzzy rules formed the knowledge base of the autopilot system and is subsequently validated in auto-pilot mode.