Fuzzy Logic-Based Optimization Techniques in Autonomous Systems

Fuzzy logic-based optimisation techniques integrate the human-like reasoning of fuzzy inference systems with the adaptive search capabilities of metaheuristic algorithms to enhance decision making and control in autonomous systems. These methods leverage fuzzy sets to model uncertainty and approximate reasoning, while metaheuristic methods such as particle swarm optimisation, bee colony optimisation, harmony search and marine predator algorithms are endowed with adaptive fuzzy controllers whose membership functions and rule bases are tuned dynamically. This hybridisation addresses the exploration–exploitation trade-off by adjusting algorithmic parameters in response to evolving system states, environmental uncertainties and mission objectives. Practical applications span trajectory planning and stability control in mobile robots to energy-efficient navigation in unmanned vehicles. Advances in type-2 fuzzy systems enable more robust handling of higher-order uncertainty, improving adaptability and fault tolerance in complex and noisy environments. The global significance of these techniques lies in their capacity to deliver intelligent, flexible and resilient control strategies, paving the way for safer and more efficient autonomous operations across robotics, transportation and industrial automation.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Research from all publishers

In a hybrid approach to mobile robot trajectory control, dynamic adaptation of parameters within a bee colony optimisation algorithm was achieved through the integration of type-1, interval type-2 and generalised type-2 fuzzy inference systems. The study demonstrated that the generalised type-2 fuzzy logic system yielded superior trajectory stability under perturbations compared with its lower-order counterparts, highlighting the value of higher-order uncertainty modelling in real-time autonomous navigation.

A fuzzy dynamic parameter adaptation framework was developed for the harmony search algorithm to optimise the control of a ball–beam benchmark system. By employing type-1, interval type-2 and generalised type-2 fuzzy systems to adjust harmony memory size and pitch adjustment rate during optimisation, the method achieved significant reductions in integral error metrics under noisy and noise-free conditions, illustrating enhanced intensification and diversification for precise controller tuning.

A recent extension of the marine predator algorithm incorporated generalised type-2 fuzzy logic for real-time parameter adjustment in autonomous mobile robot controllers. The generalised fuzzy adaptation balanced exploration and exploitation across iterations, improving global search performance on standard benchmark functions. When applied to fuzzy controller design, the approach showed robust performance in noisy environments, reinforcing the efficacy of type-2 fuzzy systems for complex optimisation tasks in autonomous platforms.

Fuzzy Logic-Based Optimization Techniques in Autonomous Systems publication trend

The graph below shows the total number of articles in fuzzy logic-based optimization techniques in autonomous systems across all publications each year (not limited to Nature Index journals).

Technical terms

Fuzzy Logic: A form of multi-valued logic that models reasoning with approximate values and uncertain information through membership functions and fuzzy rules.

Membership Function: A curve defining the degree to which a given input belongs to a fuzzy set, ranging from 0 to 1.

Type-1 Fuzzy Logic System (T1FLS): A fuzzy inference framework wherein membership functions are crisp and yield precise membership degrees for input values.

Type-2 Fuzzy Logic System (T2FLS): An advanced fuzzy inference framework featuring fuzzy membership functions with secondary membership grades to handle higher-order uncertainty.

Metaheuristic Optimisation: A class of high-level algorithmic frameworks that guide underlying heuristics to explore and exploit complex search spaces.

Exploration and Exploitation: Dual aspects of optimisation algorithms where exploration seeks diverse regions of the search space and exploitation refines existing promising solutions.

References

1. Fuzzy Sets in Dynamic Adaptation of Parameters of a Bee Colony Optimization for Controlling the Trajectory of an Autonomous Mobile Robot. Sensors (2016).
2. Fuzzy Dynamic Parameter Adaptation in the Harmony Search Algorithm for the Optimization of the Ball and Beam Controller. Advances in Operations Research (2018).
3. Generalized Type-2 Fuzzy Parameter Adaptation in the Marine Predator Algorithm for Fuzzy Controller Parameterization in Mobile Robots. Symmetry (2022).