Fuzzy sets

There have been much technological advances and research in Unmanned Surface
Vehicles (USV) as a support and delivery platform for Autonomous/Unmanned
Underwater Vehicles (AUV/UUV). Advantages include extending underwater search and
survey operations time and reach, improving underwater positioning and mission
awareness, in addition to minimizing the costs and risks associated with similar manned
vessel operations. The objective of this thesis is to present the design and development a
high-level fuzzy logic guidance controller for a WAM-V 14 USV in order to
autonomously launch and recover a REMUS 100 AUV. The approach to meeting this objective is to develop ability for the USV to intercept and rendezvous with an AUV that is in transit in order to maximize the probability of a final mobile docking maneuver. Specifically, a fuzzy logic Rendezvous Docking controller has been developed that generates Waypoint-Heading goals for the USV to minimize the cross-track errors between the USV and AUV. A subsequent fuzzy
logic Waypoint-Heading controller has been developed to provide the desired heading
and speed commands to the low-level controller given the Waypoint-Heading goals.
High-level mission control has been extensively simulated using Matlab and partially
characterized in real-time during testing. Detailed simulation, experimental results and
findings will be reported in this paper.

The development of a Flight Control System for a non-linear six degree of freedom model of an Autonomous Underwater Vehicle is described. Heading, pitch and depth are regulated by three independent Fuzzy Logic Controllers (FLCs). Numerical methods are used to tune rule bases to control tables that are based on the minimum time characteristics of the model. Setpoint errors are eliminated using fuzzily constrained integrators. A scheme to vary control policy with forward speed is also detailed. System stability is evaluated using cell-to-cell mapping. A variable structure fuzzy heading controller is designed for an unstable non-linear model of an Unmanned Underwater Vehicle. Scheduling of scaling parameters accommodates changes in forward speed as predicted by thruster RPM and angular distance turned. This FLC combines bang-bang and linear type control to respond more rapidly and robustly than a gain scheduled linear PID controller.

Case-based reasoning (CBR) is a powerful reasoning paradigm for many application domains like planning, diagnosis, classification, and decision making. Recognizing solutions of past instances which are similar to the problem in hand is the central concept of CBR. Accordingly, the main research issues in CBR are efficient indexing, retrieval, and evaluation of cases. Generalization of indices has been a major concern as it directly influences the size of casebases and the ability to recognize the right candidate cases. This dissertation work presents a novel indexing scheme--using fuzzy sets to represent case indices and fuzzy aggregation operators to evaluate case matches. The proposed scheme, REFIC (REasoning from Fuzzy Indexed Cases), provides a flexible and transparent scheme to generalize case indices leading to smaller casebases. A hierarchical aggregation of different index matches is suggested for case evaluation. Also, for continuous variable domains, it is proposed to combine the solutions of a small subset of best matching cases as opposed to the conventional approach of selecting and modifying a single best one. These schemes are demonstrated by implementing a case-based navigation planner for autonomous underwater vehicles (AUVs). This navigation planner comprises of an annotated map database, a case-based path planner, and a hybrid fuzzy-CBR based reactive navigation module. The annotated map database provides a general framework for modeling the navigational environment. Annotations attached to objects and geometrical query handling are two main features of this database. Using this system as a spatial casebase, an off-line path planning system for AUV missions is designed. The obstacle avoidance module employs CBR to dynamically select promising directions of movement and to activate a subset of navigational behaviors. This reactive navigation scheme has been found to be very robust under noisy sensor data and complex obstacle distribution patterns.