Hierarchical Fuzzy Controller for Large Rule-Base Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fuzzy logic controllers for autonomous vehicles face challenges in efficiently managing a large rule-base as the number of input and output variables increases, leading to computational inefficiencies and increased complexity.
Innovation Solution
The implementation of a hierarchical fuzzy controller with reduced rule-base, utilizing an Adaptive Neuro-Fuzzy Inference System (ANFIS) with symmetric trapezoidal membership functions and reinforcement learning, to selectively prioritize and reduce the rule-base while maintaining control fidelity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the number of input and output variables in a fuzzy logic controller increases, then the control capability and adaptability improve, but the rule-base size grows exponentially leading to computational inefficiency
Solution Approach 1:
The patent applies segmentation by dividing the fuzzy logic controller into multiple hierarchical levels. Each level processes a subset of input variables and generates intermediate outputs, which are then fed to higher levels. This hierarchical segmentation allows the system to handle multiple input variables without creating an exponentially growing monolithic rule-base, as each level manages only its local subset of variables and rules.
Solution Approach 2:
The patent introduces a hierarchical dimension to the traditional flat fuzzy logic structure. By organizing rules and variables across multiple levels (e.g., level 1, level 2, level 3), the system transforms the problem from a two-dimensional input-output mapping into a multi-level processing architecture. This dimensional transformation enables the controller to manage complex variable interactions without requiring an exponentially large rule-base at any single level.
2Measurement precision
If a complete rule-base covering all possible combinations is used, then control accuracy is maximized, but computational load and processing time increase significantly
Solution Approach 1:
The patent extracts and removes redundant or less critical rules from the complete rule-base. By analyzing the hierarchical structure and identifying rules that contribute minimally to control accuracy, the system eliminates these rules while maintaining essential control functionality. This extraction process reduces the overall rule-base size and computational load without significantly compromising control precision.
Solution Approach 2:
The patent implements partial action by processing only the most relevant input combinations at each hierarchical level rather than evaluating all possible combinations. The hierarchical structure allows the system to focus computational resources on critical decision paths while ignoring less important scenarios, achieving satisfactory control accuracy with reduced processing time.
3Productivity
If the rule-base is reduced to essential components, then computational efficiency improves, but control fidelity may be compromised
Solution Approach 1:
The patent performs preliminary action by pre-organizing the rule-base into a hierarchical structure during the design phase. This preliminary organization identifies and prioritizes essential rules at each level, ensuring that the most critical control logic is preserved in the reduced rule-base. By preparing this hierarchical framework in advance, the system maintains control fidelity while enabling efficient real-time processing.
Solution Approach 2:
The patent applies local quality by ensuring that each hierarchical level contains rules specifically optimized for its local context and variable subset. Rather than uniformly reducing all rules, the system preserves high-fidelity rules where they are most needed at each level while allowing greater reduction in less critical areas. This localized optimization maintains overall control fidelity while achieving computational efficiency.
Data Source
AI summary
A waypoint, navigation controller and corresponding controlling methods are described, where the controller functions as a multiple input-multiple output, e.g., nonlinear angular velocity and linear speed controller for a land vessel such as a skid-steer vehicle. The controller and the controlling methods may be based on a fuzzy logic controller (alternatively referred to as “fuzzy controller”). The membership functions of the fuzzy controller may employ a trapezoidal structure with a symmetric rule-base. In addition, a Hierarchical Rule-Base Reduction (HRBR) is incorporated into the controller so as to select only the rules most influential on state errors by selecting inputs/outputs, determining the most globally influential inputs, and generating a hierarchy relating inputs via a Fuzzy Relations Control Strategy (FRCS). This disclosure is further directed to a fuzzy logic controller with Hierarchical Rule-Base Reduction (HRBR) and implemented as neural network and training of such a fuzzy logic controller via reinforcement learning based on an ANFIS actor.